Papers | Parallel Computing
2024
Miruna Bețianu, Abele Mălan, Marco Aldinucci, Robert Birke, Lydia Chen
DALLMi: Domain Adaption for LLM-based Multi-label Classifier Proceedings Article
In: Proceedings of the 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Taipei, Taiwan, 2024.
Abstract | 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},
year = {2024},
date = {2024-05-01},
booktitle = {Proceedings of the 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining},
address = {Taipei, Taiwan},
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}
}
Chi Hong, Robert Birke, Pin-Yu Chen, Lydia Chen
On Dark Knowledge for Distilling Generators Proceedings Article
In: Proceedings of the 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Taipei, Taiwan, 2024.
Abstract | BibTeX | Tags: ai, epi, icsc
@inproceedings{24:chen:llm,
title = {On Dark Knowledge for Distilling Generators},
author = {Chi Hong and Robert Birke and Pin-Yu Chen and Lydia Chen},
year = {2024},
date = {2024-05-01},
booktitle = {Proceedings of the 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining},
address = {Taipei, Taiwan},
abstract = {Knowledge distillation has been applied on generative models, such as Variational Autoencoder (VAE) and Generative Adversarial Networks (GANs). To distill the knowledge, the synthetic outputs of a teacher generator are used to train a student model. While the dark knowledge, i.e., the probabilistic output, is well explored in distilling classifiers, little is known about the existence of an equivalent dark knowledge for generative models and its extractability. In this paper, we derive the first kind of empirical risk bound for distilling generative models from a Bayesian perspective. Through our analysis, we show the existence of the dark knowledge for generative models, i.e., Bayes probability distribution of a synthetic output from a given input, which achieves lower empirical risk bound than merely using the synthetic output of the generators. Furthermore, we propose a Dark Knowledge based Distillation , DKtill, which trains the student generator based on the (approximate) dark knowledge. Our extensive evaluation on distilling VAE, conditional GANs, and translation GANs on Facades and CelebA datasets show that the FID of student generators trained by DKtill combining dark knowledge are lower than student generators trained only by the synthetic outputs by up to 42.66%, and 78.99%, respectively.},
keywords = {ai, epi, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
2023
Gianluca Mittone, Giulio Malenza, Marco Aldinucci, Robert Birke
Distributed Edge Inference: an Experimental Study on Multiview Detection Proceedings Article
In: UCC '23: Proceedings of the 16th IEEE/ACM International Conference on Utility and Cloud Computing Companion, Taormina, Italy, 2023, (eupilot, icsc, In press).
Abstract | Links | BibTeX | Tags: ai
@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},
year = {2023},
date = {2023-12-01},
booktitle = {UCC '23: Proceedings of the 16th IEEE/ACM International Conference on Utility and Cloud Computing Companion},
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, In press},
keywords = {ai},
pubstate = {published},
tppubtype = {inproceedings}
}
Samuele Fonio, Lorenzo Paletto, Mattia Cerrato, Dino Ienco, Roberto Esposito
Hierarchical priors for Hyperspherical Prototypical Networks Proceedings Article
In: 31th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN, Bruges, Belgium, 2023, (In print).
Abstract | Links | BibTeX | Tags: ai, icsc
@inproceedings{23:esann:fonio,
title = {Hierarchical priors for Hyperspherical Prototypical Networks},
author = {Samuele Fonio and Lorenzo Paletto and Mattia Cerrato and Dino Ienco and Roberto Esposito},
url = {https://www.esann.org/sites/default/files/proceedings/2023/ES2023-65.pdf},
year = {2023},
date = {2023-10-01},
booktitle = {31th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN},
address = {Bruges, Belgium},
abstract = {In this paper, we explore the usage of hierarchical priors to improve learning in contexts where the number of available examples is extremely low. Specifically, we consider a Prototype Learning setting where deep neural networks are used to embed data in hyperspherical geometries.In this scenario, we propose an innovative way to learn the prototypes by combining class separation and hierarchical information. In addition, we introduce a contrastive loss function capable of balancing the exploitation of prototypes through a prototype pruning mechanism. We compare the proposed method with state-of-the-art approaches on two public datasets.},
note = {In print},
keywords = {ai, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
Samuele Fonio
Benchmarking Federated Learning Frameworks for Medical Imaging Tasks Proceedings Article
In: Image Analysis and Processing - ICIAP 2023 - 22th International Conference - FedMed, Springer LNCS, Udine, Italy, 2023, (In print).
Abstract | Links | BibTeX | Tags: ai, confidential, eupilot, icsc
@inproceedings{23:iciap:fedmed:ws:fonio,
title = {Benchmarking Federated Learning Frameworks for Medical Imaging Tasks},
author = {Samuele Fonio},
url = {https://iris.unito.it/retrieve/c6be8be7-3980-4c4c-874e-68b6fd855ebc/FedMed23-3.pdf},
year = {2023},
date = {2023-09-01},
booktitle = {Image Analysis and Processing - ICIAP 2023 - 22th International Conference - FedMed},
publisher = {Springer LNCS},
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, confidential, eupilot, icsc},
pubstate = {published},
tppubtype = {inproceedings}
}
Zilong Zhao, Robert Birke, Lydia Y. Chen
GDTS: GAN-based Distributed Tabular Synthesizer Proceedings Article
In: 16th IEEE International Conference on Cloud Computing (CLOUD), IEEE, Chicago, USA, 2023.
Abstract | Links | BibTeX | Tags: ai
@inproceedings{23:cloud:gdts,
title = {GDTS: GAN-based Distributed Tabular Synthesizer},
author = {Zilong Zhao and Robert Birke and Lydia Y. Chen},
url = {https://iris.unito.it/retrieve/8bc610de-3ccd-4a0a-b97f-ee329e487b76/GDTS_IEEE_CLOUD_preprint.pdf},
doi = {10.1109/CLOUD60044.2023.00078},
year = {2023},
date = {2023-07-01},
booktitle = {16th IEEE International Conference on Cloud Computing (CLOUD)},
publisher = {IEEE},
address = {Chicago, USA},
abstract = {Generative Adversarial Networks (GANs) are typically trained to synthesize data, from images and more recently tabular data, under the assumption of directly accessible training data. While learning image GANs on Federated Learning (FL) and Multi-Discriminator (MD) systems has just been demonstrated, it is unknown if tabular GANs can be learned from decentralized data sources. Different from image GANs, state-of-the-art tabular GANs require prior knowledge on the data distribution of each (discrete and continuous) column to agree on a common encoding – risking privacy guarantees. In this paper, we propose GDTS, a distributed framework for GAN-based tabular synthesizer. GDTS provides different system architectures to match the two training paradigms termed GDTS FL and GDTS MD. Key to enable learning on distributed data is the proposed novel privacy-preserving multi-source feature encoding to capture the global data properties. In addition GDTS encompasses a weighting strategy based on table similarity to counter the detrimental effects of non-IID data and a validation pipeline to easily assess and compare the performance of different paradigms and hyper parameters. We evaluate the effectiveness of GDTS in terms of synthetic data quality, and overall training scalability. Experiments show that GDTS FL achieves better statistical similarity and machine learning utility between generated and original data compared to GDTS MD.},
keywords = {ai},
pubstate = {published},
tppubtype = {inproceedings}
}
Matteo Pennisi, Federica Proietto Salanitri, Giovanni Bellitto, Bruno Casella, Marco Aldinucci, Simone Palazzo, Concetto Spampinato
Experience Replay as an Effective Strategy for Optimizing Decentralized Federated Learning Proceedings Article
In: Proceedings of the 1st Workshop on Visual Continual Learning, ICCV 2023, Paris, France, 2 October 2023, 2023, (https://ieeexplore.ieee.org/document/10350429).
Abstract | Links | BibTeX | Tags: ai, confidential
@inproceedings{23:casella:ERGANs,
title = {Experience Replay as an Effective Strategy for Optimizing Decentralized Federated Learning},
author = {Matteo Pennisi and Federica Proietto Salanitri and Giovanni Bellitto and Bruno Casella and Marco Aldinucci and Simone Palazzo and Concetto Spampinato},
url = {https://openaccess.thecvf.com/content/ICCV2023W/VCL/papers/Pennisi_Experience_Replay_as_an_Effective_Strategy_for_Optimizing_Decentralized_Federated_ICCVW_2023_paper.pdf},
doi = {10.1109/ICCVW60793.2023.00362},
year = {2023},
date = {2023-01-01},
booktitle = {Proceedings of the 1st Workshop on Visual Continual Learning, ICCV 2023, Paris, France, 2 October 2023},
abstract = {Federated and continual learning are training paradigms addressing data distribution shift in space and time. More specifically, federated learning tackles non-i.i.d data in space as information is distributed in multiple nodes, while continual learning faces with temporal aspect of training as it deals with continuous streams of data. Distribution shifts over space and time is what it happens in real federated learning scenarios that show multiple challenges. First, the federated model needs to learn sequentially while retaining knowledge from the past training rounds. Second, the model has also to deal with concept drift from the distributed data distributions. To address these complexities, we attempt to combine continual and federated learning strategies by proposing a solution inspired by experience replay and generative adversarial concepts for supporting decentralized distributed training. In particular, our approach relies on using limited memory buffers of synthetic privacy-preserving samples and interleaving training on local data and on buffer data. By translating the CL formulation into the task of integrating distributed knowledge with local knowledge, our method enables models to effectively integrate learned representation from local nodes, providing models the capability to generalize across multiple datasets.We test our integrated strategy on two realistic medical image analysis tasks — tuberculosis and melanoma classification — using multiple datasets in order to simulate realistic non-i.i.d. medical data scenarios. Results show that our approach achieves performance comparable to standard (non-federated) learning and significantly outperforms state-of-the-art federated methods in their centralized (thus, more favourable) formulation.},
note = {https://ieeexplore.ieee.org/document/10350429},
keywords = {ai, confidential},
pubstate = {published},
tppubtype = {inproceedings}
}
Matteo Pennisi, Federica Proietto Salanitri, Giovanni Bellitto, Bruno Casella, Marco Aldinucci, Simone Palazzo, Concetto Spampinato
FedER: Federated Learning through Experience Replay and Privacy-Preserving Data Synthesis Journal Article
In: Computer Vision and Image Understanding, vol. 238, pp. 103882, 2023.
Abstract | Links | BibTeX | Tags: ai, confidential
@article{23:casella:FedER,
title = {FedER: Federated Learning through Experience Replay and Privacy-Preserving Data Synthesis},
author = {Matteo Pennisi and Federica Proietto Salanitri and Giovanni Bellitto and Bruno Casella and Marco Aldinucci and Simone Palazzo and Concetto Spampinato},
url = {https://www.sciencedirect.com/science/article/pii/S107731422300262X?via%3Dihub},
doi = {10.1016/j.cviu.2023.103882},
year = {2023},
date = {2023-01-01},
journal = {Computer Vision and Image Understanding},
volume = {238},
pages = {103882},
institution = {Computer Science Department, University of Torino},
abstract = {In the medical field, multi-center collaborations are often sought to yield more generalizable findings by leveraging the heterogeneity of patient and clinical data. However, recent privacy regulations hinder the possibility to share data, and consequently, to come up with machine learning-based solutions that support diagnosis and prognosis. Federated learning (FL) aims at sidestepping this limitation by bringing AI-based solutions to data owners and only sharing local AI models, or parts thereof, that need then to be aggregated. However, most of the existing federated learning solutions are still at their infancy and show several shortcomings, from the lack of a reliable and effective aggregation scheme able to retain the knowledge learned locally to weak privacy preservation as real data may be reconstructed from model updates. Furthermore, the majority of these approaches, especially those dealing with medical data, relies on a centralized distributed learning strategy that poses robustness, scalability and trust issues. In this paper we present a federated and decentralized learning strategy, FedER, that, exploiting experience replay and generative adversarial concepts, effectively integrates features from local nodes, providing models able to generalize across multiple datasets while maintaining privacy. FedER is tested on two tasks — tuberculosis and melanoma classification — using multiple datasets in order to simulate realistic non-i.i.d. medical data scenarios. Results show that our approach achieves performance comparable to standard (non-federated) learning and significantly outperforms state-of-the-art federated methods in their centralized (thus, more favourable) formulation. Code is available at https://github.com/perceivelab/FedER},
keywords = {ai, confidential},
pubstate = {published},
tppubtype = {article}
}
Bruno Casella, Walter Riviera, Marco Aldinucci, Gloria Menegaz
MERGE: A model for multi-input biomedical federated learning Journal Article
In: Patterns, pp. 100856, 2023, ISSN: 2666-3899.
Abstract | Links | BibTeX | Tags: ai, confidential, epi, icsc
@article{23:fl:patterns,
title = {MERGE: A model for multi-input biomedical federated learning},
author = {Bruno Casella and Walter Riviera and Marco Aldinucci and Gloria Menegaz},
url = {https://www.sciencedirect.com/science/article/pii/S2666389923002404},
doi = {10.1016/j.patter.2023.100856},
issn = {2666-3899},
year = {2023},
date = {2023-01-01},
journal = {Patterns},
pages = {100856},
abstract = {Driven by the deep learning (DL) revolution, artificial intelligence (AI) has become a fundamental tool for many biomedical tasks, including analyzing and classifying diagnostic images. Imaging, however, is not the only source of information. Tabular data, such as personal and genomic data and blood test results, are routinely collected but rarely considered in DL pipelines. Nevertheless, DL requires large datasets that often must be pooled from different institutions, raising non-trivial privacy concerns. Federated learning (FL) is a cooperative learning paradigm that aims to address these issues by moving models instead of data across different institutions. Here, we present a federated multi-input architecture using images and tabular data as a methodology to enhance model performance while preserving data privacy. We evaluated it on two showcases: the prognosis of COVID-19 and patients' stratification in Alzheimer's disease, providing evidence of enhanced accuracy and F1 scores against single-input models and improved generalizability against non-federated models.},
keywords = {ai, confidential, epi, icsc},
pubstate = {published},
tppubtype = {article}
}
Ovidio Filippo, Francesco Bruno, Tineke H. Pinxterhuis, Mariusz Gasior, Leor Perl, Luca Gaido, Domenico Tuttolomondo, Antonio Greco, Roberto Verardi, Gianluca Lo Martire, Mario Iannaccone, Attilio Leone, Gaetano Liccardo, Serena Caglioni, Rocio González Ferreiro, Giulio Rodinò, Giuseppe Musumeci, Giuseppe Patti, Irene Borzillo, Giuseppe Tarantini, Wojciech Wańha, Bruno Casella, Eline H Ploumen, Lukasz Pyka, Ran Kornowski, Andrea Gagnor, Raffaele Piccolo, Sergio Raposeiras Roubin, Davide Capodanno, Paolo Zocca, Federico Conrotto, Gaetano M De Ferrari, Clemens Birgelen, Fabrizio D'Ascenzo
In: Catheterization and Cardiovascular Interventions, 2023.
Abstract | Links | BibTeX | Tags: ai
@article{23:casella:ultra,
title = {Predictors of target lesion failure after treatment of left main, bifurcation, or chronic total occlusion lesions with ultrathin-strut drug-eluting coronary stents in the ULTRA registry},
author = {Ovidio Filippo and Francesco Bruno and Tineke H. Pinxterhuis and Mariusz Gasior and Leor Perl and Luca Gaido and Domenico Tuttolomondo and Antonio Greco and Roberto Verardi and Gianluca Lo Martire and Mario Iannaccone and Attilio Leone and Gaetano Liccardo and Serena Caglioni and Rocio González Ferreiro and Giulio Rodinò and Giuseppe Musumeci and Giuseppe Patti and Irene Borzillo and Giuseppe Tarantini and Wojciech Wańha and Bruno Casella and Eline H Ploumen and Lukasz Pyka and Ran Kornowski and Andrea Gagnor and Raffaele Piccolo and Sergio Raposeiras Roubin and Davide Capodanno and Paolo Zocca and Federico Conrotto and Gaetano M De Ferrari and Clemens Birgelen and Fabrizio D'Ascenzo},
url = {https://onlinelibrary.wiley.com/doi/full/10.1002/ccd.30696},
doi = {10.1002/ccd.30696},
year = {2023},
date = {2023-01-01},
journal = {Catheterization and Cardiovascular Interventions},
abstract = {Background: Data about the long-term performance of new-generation ultrathin-strut drug-eluting stents (DES) in challenging coronary lesions, such as left main (LM), bifurcation, and chronic total occlusion (CTO) lesions are scant. Methods: The international multicenter retrospective observational ULTRA study included consecutive patients treated from September 2016 to August 2021 with ultrathin-strut (<70µm) DES in challenging de novo lesions. Primary endpoint was target lesion failure (TLF): composite of cardiac death, target-lesion revascularization (TLR), target-vessel myocardial infarction (TVMI), or definite stent thrombosis (ST). Secondary endpoints included all-cause death, acute myocardial infarction (AMI), target vessel revascularization, and TLF components. TLF predictors were assessed with Cox multivariable analysis. Results: Of 1801 patients (age: 66.6$±$11.2 years; male: 1410 [78.3%]), 170 (9.4%) experienced TLF during follow-up of 3.1$±$1.4 years. In patients with LM, CTO, and bifurcation lesions, TLF rates were 13.5%, 9.9%, and 8.9%, respectively. Overall, 160 (8.9%) patients died (74 [4.1%] from cardiac causes). AMI and TVMI rates were 6.0% and 3.2%, respectively. ST occurred in 11 (1.1%) patients while 77 (4.3%) underwent TLR. Multivariable analysis identified the following predictors of TLF: age, STEMI with cardiogenic shock, impaired left ventricular ejection fraction, diabetes, and renal dysfunction. Among the procedural variables, total stent length increased TLF risk (HR: 1.01, 95% CI: 1-1.02 per mm increase), while intracoronary imaging reduced the risk substantially (HR: 0.35, 95% CI: 0.12-0.82). Conclusions: Ultrathin-strut DES showed high efficacy and satisfactory safety, even in patients with challenging coronary lesions. Yet, despite using contemporary gold-standard DES, the association persisted between established patient- and procedure-related features of risk and impaired 3-year clinical outcome.},
keywords = {ai},
pubstate = {published},
tppubtype = {article}
}
2022
Emilio Sulis, Ilaria Angela Amantea, Marco Aldinucci, Guido Boella, Renata Marinello, Marco Grosso, Paolo Platter, Serena Ambrosini
An ambient assisted living architecture for hospital at home coupled with a process-oriented perspective Journal Article
In: Journal of Ambient Intelligence and Humanized Computing, 2022, ISBN: 1868-5145.
Abstract | Links | BibTeX | Tags: ai
@article{Sulis2022,
title = {An ambient assisted living architecture for hospital at home coupled with a process-oriented perspective},
author = {Emilio Sulis and Ilaria Angela Amantea and Marco Aldinucci and Guido Boella and Renata Marinello and Marco Grosso and Paolo Platter and Serena Ambrosini},
url = {https://iris.unito.it/retrieve/c7eaab0b-f78b-4af0-8c17-fa5479d776e6/jaihc2021-preprint.pdf},
doi = {10.1007/s12652-022-04388-6},
isbn = {1868-5145},
year = {2022},
date = {2022-09-21},
journal = {Journal of Ambient Intelligence and Humanized Computing},
abstract = {The growing number of next-generation applications offers a relevant opportunity for healthcare services, generating an urgent need for architectures for systems integration. Moreover, the huge amount of stored information related to events can be explored by adopting a process-oriented perspective. This paper discusses an Ambient Assisted Living healthcare architecture to manage hospital home-care services. The proposed solution relies on adopting an event manager to integrate sources ranging from personal devices to web-based applications. Data are processed on a federated cloud platform offering computing infrastructure and storage resources to improve scientific research. In a second step, a business process analysis of telehealth and telemedicine applications is considered. An initial study explored the business process flow to capture the main sequences of tasks, activities, events. This step paves the way for the integration of process mining techniques to compliance monitoring in an AAL architecture framework.},
keywords = {ai},
pubstate = {published},
tppubtype = {article}
}
Bart Cox, Robert Birke, Lydia Y. Chen
Memory-aware and context-aware multi-DNN inference on the edge Journal Article
In: Pervasive and Mobile Computing, vol. 83, pp. 1–16, 2022, ISSN: 1574-1192.
Abstract | Links | BibTeX | Tags: ai
@article{COX2022101594,
title = {Memory-aware and context-aware multi-DNN inference on the edge},
author = {Bart Cox and Robert Birke and Lydia Y. Chen},
url = {https://www.sciencedirect.com/science/article/pii/S1574119222000372},
doi = {https://doi.org/10.1016/j.pmcj.2022.101594},
issn = {1574-1192},
year = {2022},
date = {2022-01-01},
journal = {Pervasive and Mobile Computing},
volume = {83},
pages = {1–16},
abstract = {Deep neural networks (DNNs) are becoming the core components of many applications running on edge devices, especially for real time image-based analysis. Increasingly, multi-faced knowledge is extracted by executing multiple DNNs inference models, e.g., identifying objects, faces, and genders from images. It is of paramount importance to guarantee low response times of such multi-DNN executions as it affects not only users quality of experience but also safety. The challenge, largely unaddressed by the state of the art, is how to overcome the memory limitation of edge devices without altering the DNN models. In this paper, we design and implement Masa, a responsive memory-aware multi-DNN execution and scheduling framework, which requires no modification of DNN models. The aim of Masa is to consistently ensure the average response time when deterministically and stochastically executing multiple DNN-based image analyses. The enabling features of Masa are (i) modeling inter- and intra-network dependency, (ii) leveraging complimentary memory usage of each layer, and (iii) exploring the context dependency of DNNs. We verify the correctness and scheduling optimality via mixed integer programming. We extensively evaluate two versions of Masa, context-oblivious and context-aware, on three configurations of Raspberry Pi and a large set of popular DNN models triggered by different generation patterns of images. Our evaluation results show that Masa can achieve lower average response times by up to 90% on devices with small memory, i.e., 512 MB to 1 GB, compared to the state of the art multi-DNN scheduling solutions.},
keywords = {ai},
pubstate = {published},
tppubtype = {article}
}
2021
Chi Hong, Amirmasoud Ghiassi, Yichi Zhou, Robert Birke, Lydia Y. Chen
Online Label Aggregation: A Variational Bayesian Approach Proceedings Article
In: Leskovec, Jure, Grobelnik, Marko, Najork, Marc, Tang, Jie, Zia, Leila (Ed.): WWW '21: The Web Conference 2021, pp. 1904–1915, ACM / IW3C2, 2021.
Abstract | Links | BibTeX | Tags: ai
@inproceedings{www-hong21,
title = {Online Label Aggregation: A Variational Bayesian Approach},
author = {Chi Hong and Amirmasoud Ghiassi and Yichi Zhou and Robert Birke and Lydia Y. Chen},
editor = {Jure Leskovec and Marko Grobelnik and Marc Najork and Jie Tang and Leila Zia},
url = {https://doi.org/10.1145/3442381.3449933},
doi = {10.1145/3442381.3449933},
year = {2021},
date = {2021-04-01},
booktitle = {WWW '21: The Web Conference 2021},
pages = {1904–1915},
publisher = {ACM / IW3C2},
abstract = {Noisy labeled data is more a norm than a rarity for crowd sourced contents. It is effective to distill noise and infer correct labels through aggregating results from crowd workers. To ensure the time relevance and overcome slow responses of workers, online label aggregation is increasingly requested, calling for solutions that can incrementally infer true label distribution via subsets of data items. In this paper, we propose a novel online label aggregation framework, BiLA , which employs variational Bayesian inference method and designs a novel stochastic optimization scheme for incremental training. BiLA is flexible to accommodate any generating distribution of labels by the exact computation of its posterior distribution. We also derive the convergence bound of the proposed optimizer. We compare BiLA with the state of the art based on minimax entropy, neural networks and expectation maximization algorithms, on synthetic and real-world data sets. Our evaluation results on various online scenarios show that BiLA can effectively infer the true labels, with an error rate reduction of at least 10 to 1.5 percent points for synthetic and real-world datasets, respectively.},
keywords = {ai},
pubstate = {published},
tppubtype = {inproceedings}
}
C. Pino, G. Vecchio, Marco Fronda, Marco Calandri, Marco Aldinucci, Concetto Spampinato
TwinLiverNet: Predicting TACE Treatment Outcome from CT scans for Hepatocellular Carcinoma using Deep Capsule Networks Proceedings Article
In: 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, EMBC 2021, Mexico, November 1-5, 2021, pp. 3039–3043, IEEE, 2021.
Abstract | Links | BibTeX | Tags: ai
@inproceedings{21:DBLP:conf/embc/PinoVFCAS21,
title = {TwinLiverNet: Predicting TACE Treatment Outcome from CT scans for Hepatocellular Carcinoma using Deep Capsule Networks},
author = {C. Pino and G. Vecchio and Marco Fronda and Marco Calandri and Marco Aldinucci and Concetto Spampinato},
url = {https://doi.org/10.1109/EMBC46164.2021.9630913},
doi = {10.1109/EMBC46164.2021.9630913},
year = {2021},
date = {2021-01-01},
booktitle = {43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, EMBC 2021, Mexico, November 1-5, 2021},
pages = {3039–3043},
publisher = {IEEE},
abstract = {Predicting response to treatment plays a key role to assist radiologists in hepato-cellular carcinoma (HCC) therapy planning. The most widely used treatment for unresectable HCC is the trans-arterial chemoembolization (TACE). A complete radiological response after the first TACE is a reliable predictor of treatment favourable outcome. However, visual inspection of contrast-enhanced CT scans is time-consuming, error prone and too operator-dependent. Thus, in this paper we propose TwinLiverNet: a deep neural network that is able to predict TACE treatment outcome through learning visual cue from CT scans. TwinLiverNet, specifically, integrates 3D convolutions and capsule networks and is designed to process simultaneously late arterial and delayed phases from contrast-enhanced CTs. Experimental results carried out on a dataset consisting of 126 HCC lesions show that TwinLiverNet reaches an average accuracy of 82% in predicting complete response to TACE treatment. Furthermore, combining multiple CT phases (specifically, late arterial and delayed ones) yields a performance increase of over 12 percent points. Finally, the introduction of capsule layers into the model avoids the model to overfit, while enhancing accuracy.Clinical relevance— TwinLiverNet supports radiologists in visual inspection of CT scans to assess TACE treatment outcome, while reducing inter-operator variability.},
keywords = {ai},
pubstate = {published},
tppubtype = {inproceedings}
}
Ovidio De Filippo, Jeehoon Kang, Francesco Bruno, Jung-Kyu Han, Andrea Saglietto, Han-Mo Yang, Giuseppe Patti, Kyung-Woo Park, Radoslaw Parma, Hyo-Soo Kim, Leonardo De Luca, Hyeon-Cheol Gwon, Mario Iannaccone, Woo Jung Chun, Grzegorz Smolka, Seung-Ho Hur, Enrico Cerrato, Seung Hwan Han, Carlo Mario, Young Bin Song, Javier Escaned, Ki Hong Choi, Gerard Helft, Joon-Hyung Doh, Alessandra Truffa Giachet, Soon-Jun Hong, Saverio Muscoli, Chang-Wook Nam, Guglielmo Gallone, Davide Capodanno, Daniela Trabattoni, Yoichi Imori, Veronica Dusi, Bernardo Cortese, Antonio Montefusco, Federico Conrotto, Iacopo Colonnelli, Imad Sheiban, Gaetano Maria Ferrari, Bon-Kwon Koo, Fabrizio D'Ascenzo
In: The American Journal of Cardiology, 2021, ISSN: 0002-9149.
Abstract | Links | BibTeX | Tags: ai
@article{21:ajc:bifurcat,
title = {Benefit of Extended Dual Antiplatelet Therapy Duration in Acute Coronary Syndrome Patients Treated with Drug Eluting Stents for Coronary Bifurcation Lesions (from the BIFURCAT Registry)},
author = {Ovidio De Filippo and Jeehoon Kang and Francesco Bruno and Jung-Kyu Han and Andrea Saglietto and Han-Mo Yang and Giuseppe Patti and Kyung-Woo Park and Radoslaw Parma and Hyo-Soo Kim and Leonardo De Luca and Hyeon-Cheol Gwon and Mario Iannaccone and Woo Jung Chun and Grzegorz Smolka and Seung-Ho Hur and Enrico Cerrato and Seung Hwan Han and Carlo Mario and Young Bin Song and Javier Escaned and Ki Hong Choi and Gerard Helft and Joon-Hyung Doh and Alessandra Truffa Giachet and Soon-Jun Hong and Saverio Muscoli and Chang-Wook Nam and Guglielmo Gallone and Davide Capodanno and Daniela Trabattoni and Yoichi Imori and Veronica Dusi and Bernardo Cortese and Antonio Montefusco and Federico Conrotto and Iacopo Colonnelli and Imad Sheiban and Gaetano Maria Ferrari and Bon-Kwon Koo and Fabrizio D'Ascenzo},
url = {https://www.sciencedirect.com/science/article/pii/S0002914921006354},
doi = {10.1016/j.amjcard.2021.07.005},
issn = {0002-9149},
year = {2021},
date = {2021-01-01},
journal = {The American Journal of Cardiology},
abstract = {Optimal dual antiplatelet therapy (DAPT) duration for patients undergoing percutaneous coronary intervention (PCI) for coronary bifurcations is an unmet issue. The BIFURCAT registry was obtained by merging two registries on coronary bifurcations. Three groups were compared in a two-by-two fashion: short-term DAPT (≤ 6 months), intermediate-term DAPT (6-12 months) and extended DAPT (>12 months). Major adverse cardiac events (MACE) (a composite of all-cause death, myocardial infarction (MI), target-lesion revascularization and stent thrombosis) were the primary endpoint. Single components of MACE were the secondary endpoints. Events were appraised according to the clinical presentation: chronic coronary syndrome (CCS) versus acute coronary syndrome (ACS). 5537 patients (3231 ACS, 2306 CCS) were included. After a median follow-up of 2.1 years (IQR 0.9-2.2), extended DAPT was associated with a lower incidence of MACE compared with intermediate-term DAPT (2.8% versus 3.4%, adjusted HR 0.23 [0.1-0.54], p <0.001), driven by a reduction of all-cause death in the ACS cohort. In the CCS cohort, an extended DAPT strategy was not associated with a reduced risk of MACE. In conclusion, among real-world patients receiving PCI for coronary bifurcation, an extended DAPT strategy was associated with a reduction of MACE in ACS but not in CCS patients.},
keywords = {ai},
pubstate = {published},
tppubtype = {article}
}
Matteo Pennisi, Isaak Kavasidis, Concetto Spampinato, Vincenzo Schinina, Simone Palazzo, Federica Proietto Salanitri, Giovanni Bellitto, Francesco Rundo, Marco Aldinucci, Massimo Cristofaro, others
An Explainable AI System for Automated COVID-19 Assessment and Lesion Categorization from CT-scans Journal Article
In: Artificial Intelligence in Medicine, pp. 102114, 2021.
Abstract | Links | BibTeX | Tags: ai
@article{pennisi2021explainable,
title = {An Explainable AI System for Automated COVID-19 Assessment and Lesion Categorization from CT-scans},
author = {Matteo Pennisi and Isaak Kavasidis and Concetto Spampinato and Vincenzo Schinina and Simone Palazzo and Federica Proietto Salanitri and Giovanni Bellitto and Francesco Rundo and Marco Aldinucci and Massimo Cristofaro and others},
url = {https://iris.unito.it/retrieve/handle/2318/1792619/770952/2021_COVID_AIM_preprint.pdf},
doi = {10.1016/j.artmed.2021.102114},
year = {2021},
date = {2021-01-01},
journal = {Artificial Intelligence in Medicine},
pages = {102114},
publisher = {Elsevier},
abstract = {COVID-19 infection caused by SARS-CoV-2 pathogen has been a catastrophic pandemic outbreak all over the world, with exponential increasing of confirmed cases and, unfortunately, deaths. In this work we propose an AI-powered pipeline, based on the deep-learning paradigm, for automated COVID-19 detection and lesion categorization from CT scans. We first propose a new segmentation module aimed at automatically identifying lung parenchyma and lobes. Next, we combine the segmentation network with classification networks for COVID-19 identification and lesion categorization. We compare the model's classification results with those obtained by three expert radiologists on a dataset of 166 CT scans. Results showed a sensitivity of 90.3% and a specificity of 93.5% for COVID-19 detection, at least on par with those yielded by the expert radiologists, and an average lesion categorization accuracy of about 84%. Moreover, a significant role is played by prior lung and lobe segmentation, that allowed us to enhance classification performance by over 6 percent points. The interpretation of the trained AI models reveals that the most significant areas for supporting the decision on COVID-19 identification are consistent with the lesions clinically associated to the virus, i.e., crazy paving, consolidation and ground glass. This means that the artificial models are able to discriminate a positive patient from a negative one (both controls and patients with interstitial pneumonia tested negative to COVID) by evaluating the presence of those lesions into CT scans. Finally, the AI models are integrated into a user-friendly GUI to support AI explainability for radiologists, which is publicly available at http://perceivelab.com/covid-ai. The whole AI system is unique since, to the best of our knowledge, it is the first AI-based software, publicly available, that attempts to explain to radiologists what information is used by AI methods for making decisions and that proactively involves them in the decision loop to further improve the COVID-19 understanding.},
keywords = {ai},
pubstate = {published},
tppubtype = {article}
}
Zilong Zhao, Robert Birke, Rui Han, Bogdan Robu, Sara Bouchenak, Sonia Ben Mokhtar, Lydia Y. Chen
Enhancing Robustness of On-Line Learning Models on Highly Noisy Data Journal Article
In: IEEE Trans. Dependable Secur. Comput., vol. 18, no. 5, pp. 2177–2192, 2021.
Abstract | Links | BibTeX | Tags: ai
@article{ZhaoBHRBMC21,
title = {Enhancing Robustness of On-Line Learning Models on Highly Noisy Data},
author = {Zilong Zhao and Robert Birke and Rui Han and Bogdan Robu and Sara Bouchenak and Sonia Ben Mokhtar and Lydia Y. Chen},
url = {https://doi.org/10.1109/TDSC.2021.3063947},
doi = {10.1109/TDSC.2021.3063947},
year = {2021},
date = {2021-01-01},
journal = {IEEE Trans. Dependable Secur. Comput.},
volume = {18},
number = {5},
pages = {2177–2192},
abstract = {Classification algorithms have been widely adopted to detect anomalies for various systems, e.g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i.e., features and labels are correctly set. However, data collected from the wild can be unreliable due to careless annotations or malicious data transformation for incorrect anomaly detection. In this article, we extend a two-layer on-line data selection framework: Robust Anomaly Detector (RAD) with a newly designed ensemble prediction where both layers contribute to the final anomaly detection decision. To adapt to the on-line nature of anomaly detection, we consider additional features of conflicting opinions of classifiers, repetitive cleaning, and oracle knowledge. We on-line learn from incoming data streams and continuously cleanse the data, so as to adapt to the increasing learning capacity from the larger accumulated data set. Moreover, we explore the concept of oracle learning that provides additional information of true labels for difficult data points. We specifically focus on three use cases, (i) detecting 10 classes of IoT attacks, (ii) predicting 4 classes of task failures of big data jobs, and (iii) recognising 100 celebrities faces. Our evaluation results show that RAD can robustly improve the accuracy of anomaly detection, to reach up to 98.95 percent for IoT device attacks (i.e., +7%), up to 85.03 percent for cloud task failures (i.e., +14%) under 40 percent label noise, and for its extension, it can reach up to 77.51 percent for face recognition (i.e., +39%) under 30 percent label noise. The proposed RAD and its extensions are general and can be applied to different anomaly detection algorithms.},
keywords = {ai},
pubstate = {published},
tppubtype = {article}
}
2019
Paolo Viviani, Maurizio Drocco, Daniele Baccega, Iacopo Colonnelli, Marco Aldinucci
Deep Learning at Scale Proceedings Article
In: Proc. of 27th Euromicro Intl. Conference on Parallel Distributed and network-based Processing (PDP), pp. 124–131, IEEE, Pavia, Italy, 2019.
Abstract | Links | BibTeX | Tags: ai
@inproceedings{19:deeplearn:pdp,
title = {Deep Learning at Scale},
author = {Paolo Viviani and Maurizio Drocco and Daniele Baccega and Iacopo Colonnelli and Marco Aldinucci},
url = {https://iris.unito.it/retrieve/handle/2318/1695211/487778/19_deeplearning_PDP.pdf},
doi = {10.1109/EMPDP.2019.8671552},
year = {2019},
date = {2019-01-01},
booktitle = {Proc. of 27th Euromicro Intl. Conference on Parallel Distributed and network-based Processing (PDP)},
pages = {124–131},
publisher = {IEEE},
address = {Pavia, Italy},
abstract = {This work presents a novel approach to distributed training of deep neural networks (DNNs) that aims to overcome the issues related to mainstream approaches to data parallel training. Established techniques for data parallel training are discussed from both a parallel computing and deep learning perspective, then a different approach is presented that is meant to allow DNN training to scale while retaining good convergence properties. Moreover, an experimental implementation is presented as well as some preliminary results.},
keywords = {ai},
pubstate = {published},
tppubtype = {inproceedings}
}