Papers | Parallel Computing
2024
Gianluca Mittone, Giulio Malenza, Marco Aldinucci, Robert Birke
Distributed Edge Inference: an Experimental Study on Multiview Detection Proceedings Article
In: Proc. of the 16th IEEE/ACM Intl. Conference on Utility and Cloud Computing Companion (UCC), pp. 1-6, ACM, Taormina, Italy, 2024, (eupilot, icsc).
Abstract | Links | BibTeX | Tags: ai, eupilot, icsc
@inproceedings{23:mittone:multiview,
title = {Distributed Edge Inference: an Experimental Study on Multiview Detection},
author = {Gianluca Mittone and Giulio Malenza and Marco Aldinucci and Robert Birke},
url = {https://iris.unito.it/handle/2318/1950083},
doi = {10.1145/3603166.3632561},
year = {2024},
date = {2024-12-01},
booktitle = {Proc. of the 16th IEEE/ACM Intl. Conference on Utility and Cloud Computing Companion (UCC)},
volume = {30},
pages = {1-6},
publisher = {ACM},
address = {Taormina, Italy},
institution = {Computer Science Department, University of Torino},
abstract = {Computing is evolving rapidly to cater to the increasing demand for sophisticated services, and Cloud computing lays a solid foundation for flexible on-demand provisioning. However, as the size of applications grows, the centralised client-server approach used by Cloud computing increasingly limits the applications' scalability. To achieve ultra-scalability, cloud/edge/fog computing converges into the compute continuum, completely decentralising the infrastructure to encompass universal, pervasive resources. The compute continuum makes devising applications benefitting from this complex environment a challenging research problem. We put the opportunities the compute continuum others to the test through a real-world multi-view detection model (MvDet) implemented with the FastFL C/C++ high-performance edge inference framework. Computational performance is discussed considering many experimental scenarios, encompassing different edge computational capabilities and network bandwidths. We obtain up to 1.92x speedup in inference time over a centralised solution using the same devices.},
note = {eupilot, icsc},
keywords = {ai, eupilot, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
Computing is evolving rapidly to cater to the increasing demand for sophisticated services, and Cloud computing lays a solid foundation for flexible on-demand provisioning. However, as the size of applications grows, the centralised client-server approach used by Cloud computing increasingly limits the applications' scalability. To achieve ultra-scalability, cloud/edge/fog computing converges into the compute continuum, completely decentralising the infrastructure to encompass universal, pervasive resources. The compute continuum makes devising applications benefitting from this complex environment a challenging research problem. We put the opportunities the compute continuum others to the test through a real-world multi-view detection model (MvDet) implemented with the FastFL C/C++ high-performance edge inference framework. Computational performance is discussed considering many experimental scenarios, encompassing different edge computational capabilities and network bandwidths. We obtain up to 1.92x speedup in inference time over a centralised solution using the same devices.
Miruna Bețianu, Abele Mălan, Marco Aldinucci, Robert Birke, Lydia Chen
DALLMi: Domain Adaption for LLM-based Multi-label Classifier Proceedings Article
In: Yang, De-Nian, Xie, Xing, Tseng, Vincent S., Pei, Jian, Huang, Jen-Wei, Lin, Jerry Chun-Wei (Ed.): Proceedings of the 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 277–289, Springer, Taipei, Taiwan, 2024.
Abstract | Links | BibTeX | Tags: ai, eupilot, icsc
@inproceedings{24:betianu:llm,
title = {DALLMi: Domain Adaption for LLM-based Multi-label Classifier},
author = {Miruna Bețianu and Abele Mălan and Marco Aldinucci and Robert Birke and Lydia Chen},
editor = {De-Nian Yang and Xing Xie and Vincent S. Tseng and Jian Pei and Jen-Wei Huang and Jerry Chun-Wei Lin},
url = {https://hdl.handle.net/2318/1976672},
doi = {10.1007/978-981-97-2259-4_21},
year = {2024},
date = {2024-05-01},
booktitle = {Proceedings of the 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining},
volume = {14647},
pages = {277–289},
publisher = {Springer},
address = {Taipei, Taiwan},
series = {Lecture Notes in Computer Science},
abstract = {Large language models (LLMs) increasingly serve as the backbone for classifying text associated with distinct domains and simultaneously several labels (classes). When encountering domain shifts, e.g., classifier of movie reviews from IMDb to Rotten Tomatoes, adapting such an LLM-based multi-label classifier is challenging due to incomplete label sets at the target domain and daunting training overhead. The existing domain adaptation methods address either image multi-label classifiers or text binary classifiers. In this paper, we design DALLMi, Domain Adaptation Large Language Model interpolator, a first-of-its-kind semi-supervised domain adaptation method for text data models based on LLMs, specifically BERT. The core of DALLMi is the novel variation loss and MixUp regularization, which jointly leverage the limited positively labeled and large quantity of unlabeled text and, importantly, their interpolation from the BERT word embeddings. DALLMi also introduces a label-balanced sampling strategy to overcome the imbalance between labeled and unlabeled data. We evaluate DALLMi against the partial-supervised and unsupervised approach on three datasets under different scenarios of label availability for the target domain. Our results show that DALLMi achieves higher mAP than unsupervised and partially-supervised approaches by 19.9% and 52.2%, respectively.},
keywords = {ai, eupilot, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
Large language models (LLMs) increasingly serve as the backbone for classifying text associated with distinct domains and simultaneously several labels (classes). When encountering domain shifts, e.g., classifier of movie reviews from IMDb to Rotten Tomatoes, adapting such an LLM-based multi-label classifier is challenging due to incomplete label sets at the target domain and daunting training overhead. The existing domain adaptation methods address either image multi-label classifiers or text binary classifiers. In this paper, we design DALLMi, Domain Adaptation Large Language Model interpolator, a first-of-its-kind semi-supervised domain adaptation method for text data models based on LLMs, specifically BERT. The core of DALLMi is the novel variation loss and MixUp regularization, which jointly leverage the limited positively labeled and large quantity of unlabeled text and, importantly, their interpolation from the BERT word embeddings. DALLMi also introduces a label-balanced sampling strategy to overcome the imbalance between labeled and unlabeled data. We evaluate DALLMi against the partial-supervised and unsupervised approach on three datasets under different scenarios of label availability for the target domain. Our results show that DALLMi achieves higher mAP than unsupervised and partially-supervised approaches by 19.9% and 52.2%, respectively.
Adriano Marques Garcia, Giulio Malenza, Robert Birke, Marco Aldinucci
Assessing Large Language Models Inference Performance on a 64-core RISC-V CPU with Silicon-Enabled Vectors Proceedings Article
In: Antelmi, Alessia, Carlini, Emanuele, Dazzi, Patrizio (Ed.): Proceedings of BigHPC2024: Special Track on Big Data and High-Performance Computing, co-located with the 3textsuperscriptrd Italian Conference on Big Data and Data Science, ITADATA2024, pp. 1-9, CEUR-WS.org, Pisa, Italy, 2024.
Abstract | Links | BibTeX | Tags: eupilot, icsc
@inproceedings{24:garcia:itadata,
title = {Assessing Large Language Models Inference Performance on a 64-core RISC-V CPU with Silicon-Enabled Vectors},
author = {Adriano Marques Garcia and Giulio Malenza and Robert Birke and Marco Aldinucci},
editor = {Alessia Antelmi and Emanuele Carlini and Patrizio Dazzi},
url = {https://iris.unito.it/retrieve/1540f675-5e88-4f57-95e7-df8e0fe5f1df/paper110.pdf},
year = {2024},
date = {2024-01-01},
booktitle = {Proceedings of BigHPC2024: Special Track on Big Data and High-Performance Computing, co-located with the 3textsuperscriptrd Italian Conference on Big Data and Data Science, ITADATA2024},
volume = {3785},
pages = {1-9},
publisher = {CEUR-WS.org},
address = {Pisa, Italy},
series = {CEUR Workshop Proceedings},
abstract = {The rising usage of compute-intensive AI applications with fast response time requirements, such as text generation using large language models, underscores the need for more efficient and versatile hardware solutions. This drives the exploration of emerging architectures like RISC-V, which has the potential to deliver strong performance within tight power constraints. The recent commercial release of processors with RISC-V Vector (RVV) silicon-enabled extensions further amplifies the significance of RISC-V architectures, offering enhanced capabilities for parallel processing and accelerating tasks critical to large language models and other AI applications. This work aims to evaluate the BERT and GPT-2 language models inference performance on the SOPHON SG2042 64-core RISC-V architecture with silicon-enabled RVV v0.7.1. We benchmarked the models with and without RVV, using OpenBLAS and BLIS as BLAS backends for PyTorch to enable vectorization. Enabling RVV in OpenBLAS improved the inference performance by up to 40% in some cases.},
keywords = {eupilot, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
The rising usage of compute-intensive AI applications with fast response time requirements, such as text generation using large language models, underscores the need for more efficient and versatile hardware solutions. This drives the exploration of emerging architectures like RISC-V, which has the potential to deliver strong performance within tight power constraints. The recent commercial release of processors with RISC-V Vector (RVV) silicon-enabled extensions further amplifies the significance of RISC-V architectures, offering enhanced capabilities for parallel processing and accelerating tasks critical to large language models and other AI applications. This work aims to evaluate the BERT and GPT-2 language models inference performance on the SOPHON SG2042 64-core RISC-V architecture with silicon-enabled RVV v0.7.1. We benchmarked the models with and without RVV, using OpenBLAS and BLIS as BLAS backends for PyTorch to enable vectorization. Enabling RVV in OpenBLAS improved the inference performance by up to 40% in some cases.
2023
Samuele Fonio
Benchmarking Federated Learning Frameworks for Medical Imaging Tasks Proceedings Article
In: Foresti, G. L., Fusiello, A., Hancock, E. (Ed.): Image Analysis and Processing - ICIAP 2023 Workshops. ICIAP 2023, Springer, Cham, Udine, Italy, 2023, (In print).
Abstract | Links | BibTeX | Tags: ai, eupilot, icsc
@inproceedings{23:iciap:fedmed:ws:fonio,
title = {Benchmarking Federated Learning Frameworks for Medical Imaging Tasks},
author = {Samuele Fonio},
editor = {G. L. Foresti and A. Fusiello and E. Hancock},
url = {https://link.springer.com/chapter/10.1007/978-3-031-51026-7_20},
doi = {10.1007/978-3-031-51026-7_20},
year = {2023},
date = {2023-09-01},
booktitle = {Image Analysis and Processing - ICIAP 2023 Workshops. ICIAP 2023},
volume = {14366},
publisher = {Springer, Cham},
address = {Udine, Italy},
abstract = {This paper presents a comprehensive benchmarking study of various Federated Learning (FL) frameworks applied to the task of Medical Image Classification. The research specifically addresses the often neglected and complex aspects of scalability and usability in off-the-shelf FL frameworks. Through experimental validation using real case deployments, we provide empirical evidence of the performance and practical relevance of open source FL frameworks. Our findings contribute valuable insights for anyone interested in deploying a FL system, with a particular focus on the healthcare domain—an increasingly attractive field for FL applications.},
note = {In print},
keywords = {ai, eupilot, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents a comprehensive benchmarking study of various Federated Learning (FL) frameworks applied to the task of Medical Image Classification. The research specifically addresses the often neglected and complex aspects of scalability and usability in off-the-shelf FL frameworks. Through experimental validation using real case deployments, we provide empirical evidence of the performance and practical relevance of open source FL frameworks. Our findings contribute valuable insights for anyone interested in deploying a FL system, with a particular focus on the healthcare domain—an increasingly attractive field for FL applications.
Gianluca Mittone, Samuele Fonio
Benchmarking Federated Learning Scalability Proceedings Article
In: Proceedings of the 2nd Italian Conference on Big Data and Data Science, ITADATA 2023, September 11-13, 2023, CEUR, Naples, Italy, 2023.
Abstract | Links | BibTeX | Tags: eupilot, HPC, icsc
@inproceedings{23:itadata:extabstract:mittone:fonio,
title = {Benchmarking Federated Learning Scalability},
author = {Gianluca Mittone and Samuele Fonio},
url = {https://hdl.handle.net/2318/1933852},
year = {2023},
date = {2023-09-01},
booktitle = {Proceedings of the 2nd Italian Conference on Big Data and Data Science, ITADATA 2023, September 11-13, 2023},
publisher = {CEUR},
address = {Naples, Italy},
abstract = {Federated Learning (FL) is a widespread Machine Learning paradigm handling distributed Big Data. In this work, we demonstrate that different FL frameworks expose different scaling performances despite adopting the same technologies, highlighting the need for a more comprehensive study on the topic.},
keywords = {eupilot, HPC, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
Federated Learning (FL) is a widespread Machine Learning paradigm handling distributed Big Data. In this work, we demonstrate that different FL frameworks expose different scaling performances despite adopting the same technologies, highlighting the need for a more comprehensive study on the topic.
Chi Hong, Jiyue Huang, Robert Birke, Lydia Y. Chen
Exploring and Exploiting Data-Free Model Stealing Proceedings Article
In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Turin, Italy, 2023.
Abstract | Links | BibTeX | Tags: eupilot, icsc
@inproceedings{23:hong:datafree,
title = {Exploring and Exploiting Data-Free Model Stealing},
author = {Chi Hong and Jiyue Huang and Robert Birke and Lydia Y. Chen},
url = {https://iris.unito.it/retrieve/ce44dec6-12c9-443d-99e7-f1141e50aa3a/Data-free%20Model%20Stealing.pdf},
doi = {10.1007/978-3-031-43424-2_2},
year = {2023},
date = {2023-09-01},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)},
address = {Turin, Italy},
abstract = {Deep machine learning models, e.g., image classifier, are increasingly deployed in the wild to provide services to users. Adversaries are shown capable of stealing the knowledge of these models by sending inference queries and then training substitute models based on query results. The availability and quality of adversarial query inputs are undoubtedly crucial in the stealing process. The recent prior art demonstrates the feasibility of replacing real data by exploring the synthetic adversarial queries, so called data-free attacks, under strong adversarial assumptions, i.e., the deployed classier returns not only class labels but also class probabilities. In this paper, we consider a general adversarial model and propose an effective data-free stealing algorithm, Tandem-GAN, which not only explores synthetic queries but also explicitly exploits the high quality ones. The core of TandemGAN is composed of (i) substitute model which imitates the target model through synthetic queries and their inferred labels; and (ii) a tandem generator consisting of two networks, Gx and Ge, which first explores the synthetic data space via Gx and then exploits high-quality examples via Ge to maximize the knowledge transfer from the target to the substitute model. Our results on four datasets show that the accuracy of our trained substitute model ranges between 96-67% of the target model and outperforms the existing state-of-the-art data-free model stealing approach by up to 2.5X.},
keywords = {eupilot, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
Deep machine learning models, e.g., image classifier, are increasingly deployed in the wild to provide services to users. Adversaries are shown capable of stealing the knowledge of these models by sending inference queries and then training substitute models based on query results. The availability and quality of adversarial query inputs are undoubtedly crucial in the stealing process. The recent prior art demonstrates the feasibility of replacing real data by exploring the synthetic adversarial queries, so called data-free attacks, under strong adversarial assumptions, i.e., the deployed classier returns not only class labels but also class probabilities. In this paper, we consider a general adversarial model and propose an effective data-free stealing algorithm, Tandem-GAN, which not only explores synthetic queries but also explicitly exploits the high quality ones. The core of TandemGAN is composed of (i) substitute model which imitates the target model through synthetic queries and their inferred labels; and (ii) a tandem generator consisting of two networks, Gx and Ge, which first explores the synthetic data space via Gx and then exploits high-quality examples via Ge to maximize the knowledge transfer from the target to the substitute model. Our results on four datasets show that the accuracy of our trained substitute model ranges between 96-67% of the target model and outperforms the existing state-of-the-art data-free model stealing approach by up to 2.5X.
Gianluca Mittone, Walter Riviera, Iacopo Colonnelli, Robert Birke, Marco Aldinucci
Model-Agnostic Federated Learning Proceedings Article
In: Euro-Par 2023: Parallel Processing, pp. 383–396, Springer, Limassol, Cyprus, 2023.
Abstract | Links | BibTeX | Tags: ai, confidential, eupilot, icsc, riscv
@inproceedings{23:mittone:mafl,
title = {Model-Agnostic Federated Learning},
author = {Gianluca Mittone and Walter Riviera and Iacopo Colonnelli and Robert Birke and Marco Aldinucci},
url = {https://doi.org/10.1007/978-3-031-39698-4_26},
doi = {10.1007/978-3-031-39698-4_26},
year = {2023},
date = {2023-08-01},
booktitle = {Euro-Par 2023: Parallel Processing},
volume = {14100},
pages = {383–396},
publisher = {Springer},
address = {Limassol, Cyprus},
institution = {Computer Science Department, University of Torino},
abstract = {Since its debut in 2016, Federated Learning (FL) has been tied to the inner workings of Deep Neural Networks (DNNs). On the one hand, this allowed its development and widespread use as DNNs proliferated. On the other hand, it neglected all those scenarios in which using DNNs is not possible or advantageous. The fact that most current FL frameworks only allow training DNNs reinforces this problem. To address the lack of FL solutions for non-DNN-based use cases, we propose MAFL (Model-Agnostic Federated Learning). MAFL marries a model-agnostic FL algorithm, AdaBoost.F, with an open industry-grade FL framework: Intel OpenFL. MAFL is the first FL system not tied to any specific type of machine learning model, allowing exploration of FL scenarios beyond DNNs and trees. We test MAFL from multiple points of view, assessing its correctness, flexibility and scaling properties up to 64 nodes. We optimised the base software achieving a 5.5x speedup on a standard FL scenario. MAFL is compatible with x86-64, ARM-v8, Power and RISC-V.},
keywords = {ai, confidential, eupilot, icsc, riscv},
pubstate = {published},
tppubtype = {inproceedings}
}
Since its debut in 2016, Federated Learning (FL) has been tied to the inner workings of Deep Neural Networks (DNNs). On the one hand, this allowed its development and widespread use as DNNs proliferated. On the other hand, it neglected all those scenarios in which using DNNs is not possible or advantageous. The fact that most current FL frameworks only allow training DNNs reinforces this problem. To address the lack of FL solutions for non-DNN-based use cases, we propose MAFL (Model-Agnostic Federated Learning). MAFL marries a model-agnostic FL algorithm, AdaBoost.F, with an open industry-grade FL framework: Intel OpenFL. MAFL is the first FL system not tied to any specific type of machine learning model, allowing exploration of FL scenarios beyond DNNs and trees. We test MAFL from multiple points of view, assessing its correctness, flexibility and scaling properties up to 64 nodes. We optimised the base software achieving a 5.5x speedup on a standard FL scenario. MAFL is compatible with x86-64, ARM-v8, Power and RISC-V.
Iacopo Colonnelli, Robert Birke, Marco Aldinucci
Experimenting with PyTorch on RISC-V Proceedings Article
In: RISC-V Summit Europe 2023, Barcelona, Spain, 2023, (Poster).
Abstract | Links | BibTeX | Tags: eupilot, icsc, riscv
@inproceedings{23:risc-v-summit,
title = {Experimenting with PyTorch on RISC-V},
author = {Iacopo Colonnelli and Robert Birke and Marco Aldinucci},
url = {https://iris.unito.it/retrieve/429bf344-9090-42c3-809c-1b8ac320a930/2023-06-08-Iacopo-COLONNELLI-abstract.pdf},
year = {2023},
date = {2023-06-01},
booktitle = {RISC-V Summit Europe 2023},
address = {Barcelona, Spain},
abstract = {RISC-V is an emerging instruction set architecture. Its modular and extensible open-source royalty-free design is increasingly attracting interest from both research and industry. Nowadays, different RISC-V-based boards can be bought off the shelf. However, software availability is equivalently vital in guaranteeing the RISC-V ecosystem's success. Here we contribute with the first publicly available port of PyTorch. PyTorch is one of the most popular Deep Learning libraries available today. As such, it is a crucial enabler in running state-of-the-art AI applications on RISC-V-based systems and a first step towards a fully democratic end-to-end codesign process.},
note = {Poster},
keywords = {eupilot, icsc, riscv},
pubstate = {published},
tppubtype = {inproceedings}
}
RISC-V is an emerging instruction set architecture. Its modular and extensible open-source royalty-free design is increasingly attracting interest from both research and industry. Nowadays, different RISC-V-based boards can be bought off the shelf. However, software availability is equivalently vital in guaranteeing the RISC-V ecosystem's success. Here we contribute with the first publicly available port of PyTorch. PyTorch is one of the most popular Deep Learning libraries available today. As such, it is a crucial enabler in running state-of-the-art AI applications on RISC-V-based systems and a first step towards a fully democratic end-to-end codesign process.
Gianluca Mittone, Nicolò Tonci, Robert Birke, Iacopo Colonnelli, Doriana Medić, Andrea Bartolini, Roberto Esposito, Emanuele Parisi, Francesco Beneventi, Mirko Polato, Massimo Torquati, Luca Benini, Marco Aldinucci
Experimenting with Emerging RISC-V Systems for Decentralised Machine Learning Proceedings Article
In: 20th ACM International Conference on Computing Frontiers (CF '23), ACM, Bologna, Italy, 2023, ISBN: 979-8-4007-0140-5/23/05, (https://arxiv.org/abs/2302.07946).
Abstract | Links | BibTeX | Tags: ai, confidential, eupilot, HPC, icsc, riscv
@inproceedings{23:mittone:fl-riscv,
title = {Experimenting with Emerging RISC-V Systems for Decentralised Machine Learning},
author = {Gianluca Mittone and Nicolò Tonci and Robert Birke and Iacopo Colonnelli and Doriana Medić and Andrea Bartolini and Roberto Esposito and Emanuele Parisi and Francesco Beneventi and Mirko Polato and Massimo Torquati and Luca Benini and Marco Aldinucci},
url = {https://dl.acm.org/doi/pdf/10.1145/3587135.3592211},
doi = {10.1145/3587135.3592211},
isbn = {979-8-4007-0140-5/23/05},
year = {2023},
date = {2023-05-01},
booktitle = {20th ACM International Conference on Computing Frontiers (CF '23)},
publisher = {ACM},
address = {Bologna, Italy},
institution = {Computer Science Department, University of Torino},
abstract = {Decentralised Machine Learning (DML) enables collaborative machine learning without centralised input data. Federated Learning (FL) and Edge Inference are examples of DML. While tools for DML (especially FL) are starting to flourish, many are not flexible and portable enough to experiment with novel systems (e.g., RISC-V), non-fully connected topologies, and asynchronous collaboration schemes. We overcome these limitations via a domain-specific language allowing to map DML schemes to an underlying middleware, i.e. the FastFlow parallel programming library. We experiment with it by generating different working DML schemes on two emerging architectures (ARM-v8, RISC-V) and the x86-64 platform. We characterise the performance and energy efficiency of the presented schemes and systems. As a byproduct, we introduce a RISC-V porting of the PyTorch framework, the first publicly available to our knowledge.},
note = {https://arxiv.org/abs/2302.07946},
keywords = {ai, confidential, eupilot, HPC, icsc, riscv},
pubstate = {published},
tppubtype = {inproceedings}
}
Decentralised Machine Learning (DML) enables collaborative machine learning without centralised input data. Federated Learning (FL) and Edge Inference are examples of DML. While tools for DML (especially FL) are starting to flourish, many are not flexible and portable enough to experiment with novel systems (e.g., RISC-V), non-fully connected topologies, and asynchronous collaboration schemes. We overcome these limitations via a domain-specific language allowing to map DML schemes to an underlying middleware, i.e. the FastFlow parallel programming library. We experiment with it by generating different working DML schemes on two emerging architectures (ARM-v8, RISC-V) and the x86-64 platform. We characterise the performance and energy efficiency of the presented schemes and systems. As a byproduct, we introduce a RISC-V porting of the PyTorch framework, the first publicly available to our knowledge.
Gianluca Mittone, Filip Svoboda, Marco Aldinucci, Nicholas D. Lane, Pietro Lio
A Federated Learning Benchmark for Drug-Target Interaction Proceedings Article
In: Companion Proceedings of the ACM Web Conference 2023 (WWW '23 Companion), ACM, Austin, Texas, 2023, ISBN: 978-1-4503-9419-2/23/04, (https://arxiv.org/abs/2302.07684).
Abstract | Links | BibTeX | Tags: ai, confidential, eupilot, icsc
@inproceedings{23:mittone:dti,
title = {A Federated Learning Benchmark for Drug-Target Interaction},
author = {Gianluca Mittone and Filip Svoboda and Marco Aldinucci and Nicholas D. Lane and Pietro Lio},
url = {https://hdl.handle.net/2318/1898472},
doi = {10.1145/3543873.3587687},
isbn = {978-1-4503-9419-2/23/04},
year = {2023},
date = {2023-04-01},
booktitle = {Companion Proceedings of the ACM Web Conference 2023 (WWW '23 Companion)},
publisher = {ACM},
address = {Austin, Texas},
institution = {Computer Science Department, University of Torino},
abstract = {Aggregating pharmaceutical data in the drug-target interaction (DTI) domain has the potential to deliver life-saving breakthroughs. It is, however, notoriously difficult due to regulatory constraints and commercial interests. This work proposes the application of federated learning, which we argue to be reconcilable with the industry's constraints, as it does not require sharing of any information that would reveal the entities' data or any other high-level summary of it. When used on a representative GraphDTA model and the KIBA dataset it achieves up to 15 percent improved performance relative to the best available non-privacy preserving alternative. Our extensive battery of experiments shows that, unlike in other domains, the non-IID data distribution in the DTI datasets does not deteriorate FL performance. Additionally, we identify a material trade-off between the benefits of adding new data, and the cost of adding more clients.},
note = {https://arxiv.org/abs/2302.07684},
keywords = {ai, confidential, eupilot, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
Aggregating pharmaceutical data in the drug-target interaction (DTI) domain has the potential to deliver life-saving breakthroughs. It is, however, notoriously difficult due to regulatory constraints and commercial interests. This work proposes the application of federated learning, which we argue to be reconcilable with the industry's constraints, as it does not require sharing of any information that would reveal the entities' data or any other high-level summary of it. When used on a representative GraphDTA model and the KIBA dataset it achieves up to 15 percent improved performance relative to the best available non-privacy preserving alternative. Our extensive battery of experiments shows that, unlike in other domains, the non-IID data distribution in the DTI datasets does not deteriorate FL performance. Additionally, we identify a material trade-off between the benefits of adding new data, and the cost of adding more clients.
Marco Aldinucci Mirko Polato Roberto Esposito
Boosting Methods for Federated Learning Proceedings Article
In: Calvanese, Diego, Diamantini, Claudia, Ferro, Nicola, Marchesin, Stefano, Silvello, Gianmaria, Tanca, Letizia (Ed.): Proc. of the 31th Italian Symposium on Advanced Database Systems,SEBD 2023, pp. 439–448, CEUR-WS.org, 2023.
Abstract | Links | BibTeX | Tags: eupilot
@inproceedings{DBLP:conf/sebd/Esposito23,
title = {Boosting Methods for Federated Learning},
author = {Marco Aldinucci Mirko Polato Roberto Esposito},
editor = {Diego Calvanese and Claudia Diamantini and Nicola Ferro and Stefano Marchesin and Gianmaria Silvello and Letizia Tanca},
url = {https://ceur-ws.org/Vol-3478/paper48.pdf},
year = {2023},
date = {2023-01-01},
booktitle = {Proc. of the 31th Italian Symposium on Advanced Database Systems,SEBD 2023},
pages = {439–448},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
abstract = {Federated Learning (FL) has been proposed to develop better AI systems without compromising the privacy of final users and the legitimate interests of private companies. Initially deployed by Google to predict text input on mobile devices, FL has been deployed in many other industries. Since its introduction, Federated Learning mainly exploited the inner working of neural networks and other gradient descent-based algorithms by either exchanging the weights of the model or the gradients computed during learning. While this approach has been very successful, it rules out applying FL in contexts where other models are preferred, e.g., easier to interpret or known to work better. This paper proposes to leverage distributed versions of the AdaBoost algorithm to acquire strong federated models. In contrast with previous approaches, our proposal does not put any constraint on the client-side learning models and does not rely on inner workings of the learning algorithms used in the clients. We perform a large set of experiments on ten UCI datasets, comparing the algorithms in six non-iidness settings. Results show that the approach is effective, in the case of an IID setting, results are often near to the theoretical optimum (i.e., the performances of AdaBoost on the complete dataset). In case of non-IID settings, results very much depend on the severity of the non-IIDness.},
keywords = {eupilot},
pubstate = {published},
tppubtype = {inproceedings}
}
Federated Learning (FL) has been proposed to develop better AI systems without compromising the privacy of final users and the legitimate interests of private companies. Initially deployed by Google to predict text input on mobile devices, FL has been deployed in many other industries. Since its introduction, Federated Learning mainly exploited the inner working of neural networks and other gradient descent-based algorithms by either exchanging the weights of the model or the gradients computed during learning. While this approach has been very successful, it rules out applying FL in contexts where other models are preferred, e.g., easier to interpret or known to work better. This paper proposes to leverage distributed versions of the AdaBoost algorithm to acquire strong federated models. In contrast with previous approaches, our proposal does not put any constraint on the client-side learning models and does not rely on inner workings of the learning algorithms used in the clients. We perform a large set of experiments on ten UCI datasets, comparing the algorithms in six non-iidness settings. Results show that the approach is effective, in the case of an IID setting, results are often near to the theoretical optimum (i.e., the performances of AdaBoost on the complete dataset). In case of non-IID settings, results very much depend on the severity of the non-IIDness.
Iacopo Colonnelli, Bruno Casella, Gianluca Mittone, Yasir Arfat, Barbara Cantalupo, Roberto Esposito, Alberto Riccardo Martinelli, Doriana Medić, Marco Aldinucci
Federated Learning meets HPC and cloud Proceedings Article
In: Bufano, Filomena, Riggi, Simone, Sciacca, Eva, Schillirò, Francesco (Ed.): Astrophysics and Space Science Proceedings, pp. 193–199, Springer, Catania, Italy, 2023, ISBN: 978-3-031-34167-0, (Keynote talk).
Abstract | Links | BibTeX | Tags: across, eupilot, streamflow
@inproceedings{22:ml4astro,
title = {Federated Learning meets HPC and cloud},
author = {Iacopo Colonnelli and Bruno Casella and Gianluca Mittone and Yasir Arfat and Barbara Cantalupo and Roberto Esposito and Alberto Riccardo Martinelli and Doriana Medić and Marco Aldinucci},
editor = {Filomena Bufano and Simone Riggi and Eva Sciacca and Francesco Schillirò},
url = {https://iris.unito.it/retrieve/3ac66baa-9d9a-4e9f-94a5-13700694d8aa/ML4Astro.pdf},
doi = {10.1007/978-3-031-34167-0_39},
isbn = {978-3-031-34167-0},
year = {2023},
date = {2023-01-01},
booktitle = {Astrophysics and Space Science Proceedings},
volume = {60},
pages = {193–199},
publisher = {Springer},
address = {Catania, Italy},
abstract = {HPC and AI are fated to meet for several reasons. This article will discuss some of them and argue why this will happen through the set of methods and technologies that underpin cloud computing. As a paradigmatic example, we present a new federated learning system that collaboratively trains a deep learning model in different supercomputing centers. The system is based on the StreamFlow workflow manager designed for hybrid cloud-HPC infrastructures.},
howpublished = {Machine Learning for Astrophysics (ML4ASTRO)},
note = {Keynote talk},
keywords = {across, eupilot, streamflow},
pubstate = {published},
tppubtype = {inproceedings}
}
HPC and AI are fated to meet for several reasons. This article will discuss some of them and argue why this will happen through the set of methods and technologies that underpin cloud computing. As a paradigmatic example, we present a new federated learning system that collaboratively trains a deep learning model in different supercomputing centers. The system is based on the StreamFlow workflow manager designed for hybrid cloud-HPC infrastructures.
2022
Mirko Polato, Roberto Esposito, Marco Aldinucci
Boosting the Federation: Cross-Silo Federated Learning without Gradient Descent Proceedings Article
In: Intl. Joint Conference on Neural Networks (IJCNN), pp. 1–10, IEEE, Padua, Italy, 2022.
Abstract | Links | BibTeX | Tags: eupilot, hpc4ai
@inproceedings{22:fl:ijcnn,
title = {Boosting the Federation: Cross-Silo Federated Learning without Gradient Descent},
author = {Mirko Polato and Roberto Esposito and Marco Aldinucci},
url = {https://iris.unito.it/retrieve/03a7b692-aecc-43db-a792-874c553d9ebe/ijcnn22-internal.pdf},
doi = {10.1109/IJCNN55064.2022.9892284},
year = {2022},
date = {2022-07-01},
booktitle = {Intl. Joint Conference on Neural Networks (IJCNN)},
pages = {1–10},
publisher = {IEEE},
address = {Padua, Italy},
abstract = {Federated Learning has been proposed to develop better AI systems without compromising the privacy of final users and the legitimate interests of private companies. Initially deployed by Google to predict text input on mobile devices, FL has been deployed in many other industries. Since its introduction, Federated Learning mainly exploited the inner working of neural networks and other gradient descent-based algorithms by either exchanging the weights of the model or the gradients computed during learning. While this approach has been very successful, it rules out applying FL in contexts where other models are preferred, e.g., easier to interpret or known to work better. This paper proposes FL algorithms that build federated models without relying on gradient descent-based methods. Specifically, we leverage distributed versions of the AdaBoost algorithm to acquire strong federated models. In contrast with previous approaches, our proposal does not put any constraint on the client-side learning models. We perform a large set of experiments on ten UCI datasets, comparing the algorithms in six non-iidness settings.},
keywords = {eupilot, hpc4ai},
pubstate = {published},
tppubtype = {inproceedings}
}
Federated Learning has been proposed to develop better AI systems without compromising the privacy of final users and the legitimate interests of private companies. Initially deployed by Google to predict text input on mobile devices, FL has been deployed in many other industries. Since its introduction, Federated Learning mainly exploited the inner working of neural networks and other gradient descent-based algorithms by either exchanging the weights of the model or the gradients computed during learning. While this approach has been very successful, it rules out applying FL in contexts where other models are preferred, e.g., easier to interpret or known to work better. This paper proposes FL algorithms that build federated models without relying on gradient descent-based methods. Specifically, we leverage distributed versions of the AdaBoost algorithm to acquire strong federated models. In contrast with previous approaches, our proposal does not put any constraint on the client-side learning models. We perform a large set of experiments on ten UCI datasets, comparing the algorithms in six non-iidness settings.
Bruno Casella, Roberto Esposito, Carlo Cavazzoni, Marco Aldinucci
Benchmarking FedAvg and FedCurv for Image Classification Tasks Proceedings Article
In: Anisetti, Marco, Bonifati, Angela, Bena, Nicola, Ardagna, Claudio, Malerba, Donato (Ed.): Proceedings of the 1st Italian Conference on Big Data and Data Science, ITADATA 2022, September 20-21, 2022, CEUR-WS.org, 2022.
Abstract | Links | BibTeX | Tags: eupilot
@inproceedings{casella2022benchmarking,
title = {Benchmarking FedAvg and FedCurv for Image Classification Tasks},
author = {Bruno Casella and Roberto Esposito and Carlo Cavazzoni and Marco Aldinucci},
editor = {Marco Anisetti and Angela Bonifati and Nicola Bena and Claudio Ardagna and Donato Malerba},
url = {https://ceur-ws.org/Vol-3340/paper40.pdf},
year = {2022},
date = {2022-01-01},
booktitle = {Proceedings of the 1st Italian Conference on Big Data and Data Science, ITADATA 2022, September 20-21, 2022},
volume = {3340},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
abstract = {Classic Machine Learning (ML) techniques require training on data available in a single data lake (either centralized or distributed). However, aggregating data from different owners is not always convenient for different reasons, including security, privacy and secrecy. Data carry a value that might vanish when shared with others; the ability to avoid sharing the data enables industrial applications where security and privacy are of paramount importance, making it possible to train global models by implementing only local policies which can be run independently and even on air-gapped data centres. Federated Learning (FL) is a distributed machine learning approach which has emerged as an effective way to address privacy concerns by only sharing local AI models while keeping the data decentralized. Two critical challenges of Federated Learning are managing the heterogeneous systems in the same federated network and dealing with real data, which are often not independently and identically distributed (non-IID) among the clients. In this paper, we focus on the second problem, i.e., the problem of statistical heterogeneity of the data in the same federated network. In this setting, local models might be strayed far from the local optimum of the complete dataset, thus possibly hindering the convergence of the federated model. Several Federated Learning algorithms, such as FedAvg, FedProx and Federated Curvature (FedCurv), aiming at tackling the non-IID setting, have already been proposed. This work provides an empirical assessment of the behaviour of FedAvg and FedCurv in common non-IID scenarios. Results show that the number of epochs per round is an important hyper-parameter that, when tuned appropriately, can lead to significant performance gains while reducing the communication cost. As a side product of this work, we release the non-IID version of the datasets we used so to facilitate further comparisons from the FL community.},
keywords = {eupilot},
pubstate = {published},
tppubtype = {inproceedings}
}
Classic Machine Learning (ML) techniques require training on data available in a single data lake (either centralized or distributed). However, aggregating data from different owners is not always convenient for different reasons, including security, privacy and secrecy. Data carry a value that might vanish when shared with others; the ability to avoid sharing the data enables industrial applications where security and privacy are of paramount importance, making it possible to train global models by implementing only local policies which can be run independently and even on air-gapped data centres. Federated Learning (FL) is a distributed machine learning approach which has emerged as an effective way to address privacy concerns by only sharing local AI models while keeping the data decentralized. Two critical challenges of Federated Learning are managing the heterogeneous systems in the same federated network and dealing with real data, which are often not independently and identically distributed (non-IID) among the clients. In this paper, we focus on the second problem, i.e., the problem of statistical heterogeneity of the data in the same federated network. In this setting, local models might be strayed far from the local optimum of the complete dataset, thus possibly hindering the convergence of the federated model. Several Federated Learning algorithms, such as FedAvg, FedProx and Federated Curvature (FedCurv), aiming at tackling the non-IID setting, have already been proposed. This work provides an empirical assessment of the behaviour of FedAvg and FedCurv in common non-IID scenarios. Results show that the number of epochs per round is an important hyper-parameter that, when tuned appropriately, can lead to significant performance gains while reducing the communication cost. As a side product of this work, we release the non-IID version of the datasets we used so to facilitate further comparisons from the FL community.
2021
Marco Aldinucci, Giovanni Agosta, Antonio Andreini, Claudio A. Ardagna, Andrea Bartolini, Alessandro Cilardo, Biagio Cosenza, Marco Danelutto, Roberto Esposito, William Fornaciari, Roberto Giorgi, Davide Lengani, Raffaele Montella, Mauro Olivieri, Sergio Saponara, Daniele Simoni, Massimo Torquati
The Italian research on HPC key technologies across EuroHPC Proceedings Article
In: ACM Computing Frontiers, pp. 279–286, ACM, Virtual Conference, Italy, 2021.
Abstract | Links | BibTeX | Tags: admire, eupex, eupilot, textarossa
@inproceedings{21:CINI_acm_CF,
title = {The Italian research on HPC key technologies across EuroHPC},
author = {Marco Aldinucci and Giovanni Agosta and Antonio Andreini and Claudio A. Ardagna and Andrea Bartolini and Alessandro Cilardo and Biagio Cosenza and Marco Danelutto and Roberto Esposito and William Fornaciari and Roberto Giorgi and Davide Lengani and Raffaele Montella and Mauro Olivieri and Sergio Saponara and Daniele Simoni and Massimo Torquati},
url = {https://iris.unito.it/retrieve/handle/2318/1783118/744641/preprint.pdf},
doi = {10.1145/3457388.3458508},
year = {2021},
date = {2021-05-01},
booktitle = {ACM Computing Frontiers},
pages = {279–286},
publisher = {ACM},
address = {Virtual Conference, Italy},
abstract = {High-Performance Computing (HPC) is one of the strategic priorities for research and innovation worldwide due to its relevance for industrial and scientific applications. We envision HPC as composed of three pillars: infrastructures, applications, and key technologies and tools. While infrastructures are by construction centralized in large-scale HPC centers, and applications are generally within the purview of domain-specific organizations, key technologies fall in an intermediate case where coordination is needed, but design and development are often decentralized. A large group of Italian researchers has started a dedicated laboratory within the National Interuniversity Consortium for Informatics (CINI) to address this challenge. The laboratory, albeit young, has managed to succeed in its first attempts to propose a coordinated approach to HPC research within the EuroHPC Joint Undertaking, participating in the calls 2019-20 to five successful proposals for an aggregate total cost of 95M Euro. In this paper, we outline the working group's scope and goals and provide an overview of the five funded projects, which become fully operational in March 2021, and cover a selection of key technologies provided by the working group partners, highlighting their usage development within the projects.},
keywords = {admire, eupex, eupilot, textarossa},
pubstate = {published},
tppubtype = {inproceedings}
}
High-Performance Computing (HPC) is one of the strategic priorities for research and innovation worldwide due to its relevance for industrial and scientific applications. We envision HPC as composed of three pillars: infrastructures, applications, and key technologies and tools. While infrastructures are by construction centralized in large-scale HPC centers, and applications are generally within the purview of domain-specific organizations, key technologies fall in an intermediate case where coordination is needed, but design and development are often decentralized. A large group of Italian researchers has started a dedicated laboratory within the National Interuniversity Consortium for Informatics (CINI) to address this challenge. The laboratory, albeit young, has managed to succeed in its first attempts to propose a coordinated approach to HPC research within the EuroHPC Joint Undertaking, participating in the calls 2019-20 to five successful proposals for an aggregate total cost of 95M Euro. In this paper, we outline the working group's scope and goals and provide an overview of the five funded projects, which become fully operational in March 2021, and cover a selection of key technologies provided by the working group partners, highlighting their usage development within the projects.