Papers | Parallel Computing

@inproceedings{sdm-ghiassi23,

title = {Robust Learning via Golden Symmetric Loss of (un)Trusted Labels},

author = {Amirmasoud Ghiassi and Robert Birke and Lydia Chen},

url = {https://datacloud.di.unito.it/index.php/s/b6z3moNLxnNiCxz},

doi = {10.1137/1.9781611977653.ch64},

year  = {2023},

date = {2023-01-01},

booktitle = {SDM '23: SIAM International Conference on Data Mining},

pages = {568–576},

abstract = {Learning robust deep models against noisy labels becomes ever critical when today's data is commonly collected from open platforms and subject to adversarial corruption. The information on the label corruption process, i.e., corruption matrix, can greatly enhance the robustness of deep models but still fall behind in combating hard classes. In this paper, we propose to construct a golden symmetric loss (GSL) based on the estimated corruption matrix as to avoid overfitting to noisy labels and learn effectively from hard classes. GSL is the weighted sum of the corrected regular cross entropy and reverse cross entropy. By leveraging a small fraction of trusted clean data, we estimate the corruption matrix and use it to correct the loss as well as to determine the weights of GSL. We theoretically prove the robustness of the proposed loss function in the presence of dirty labels. We provide a heuristics to adaptively tune the loss weights of GSL according to the noise rate and diversity measured from the dataset. We evaluate our proposed golden symmetric loss on both vision and natural language deep models subject to different types of label noise patterns. Empirical results show that GSL can significantly outperform the existing robust training methods on different noise patterns, showing accuracy improvement up to 18% on CIFAR-100 and 1% on real world noisy dataset of Clothing1M.},

keywords = {textarossa},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{21:DSD:textarossa,

title = {TEXTAROSSA: Towards EXtreme scale Technologies and Accelerators for euROhpc hw/Sw Supercomputing Applications for exascale},

author = {Giovanni Agosta and William Fornaciari and Andrea Galimberti and Giuseppe Massari and Federico Reghenzani and Federico Terraneo and Davide Zoni and Carlo Brandolese and Massimo Celino and Francesco Iannone and Paolo Palazzari and Giuseppe Zummo and Massimo Bernaschi and Pasqua D'Ambra and Sergio Saponara and Marco Danelutto and Massimo Torquati and Marco Aldinucci and Yasir Arfat and Barbara Cantalupo and Iacopo Colonnelli and Roberto Esposito and Alberto Riccardo Martinelli and Gianluca Mittone and Olivier Beaumont and Berenger Bramas and Lionel Eyraud-Dubois and Brice Goglin and Abdou Guermouche and Raymond Namyst and Samuel Thibault and Antonio Filgueras and Miquel Vidal and Carlos Alvarez and Xavier Martorell and Ariel Oleksiak and Michal Kulczewski and Alessandro Lonardo and Piero Vicini and Francesco Lo Cicero and Francesco Simula and Andrea Biagioni and Paolo Cretaro and Ottorino Frezza and Pier Stanislao Paolucci and Matteo Turisini and Francesco Giacomini and Tommaso Boccali and Simone Montangero and Roberto Ammendola},

doi = {10.1109/DSD53832.2021.00051},

year  = {2021},

date = {2021-08-01},

booktitle = {Proc. of the 24th Euromicro Conference on Digital System Design (DSD)},

publisher = {IEEE},

address = {Palermo, Italy},

abstract = {To achieve high performance and high energy effi- ciency on near-future exascale computing systems, three key technology gaps needs to be bridged. These gaps include: en- ergy efficiency and thermal control; extreme computation effi- ciency via HW acceleration and new arithmetics; methods and tools for seamless integration of reconfigurable accelerators in heterogeneous HPC multi-node platforms. TEXTAROSSA aims at tackling this gap through a co-design approach to heterogeneous HPC solutions, supported by the integration and extension of HW and SW IPs, programming models and tools derived from European research.},

keywords = {streamflow, textarossa},

pubstate = {published},

tppubtype = {inproceedings}

}

@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}

}