314 citations
- Université d'Évry Val-d'EssonneFR19 papers
- Centre National de la Recherche ScientifiqueFR15 papers
- Université Paris-SaclayFR12 papers
- LIP6FR10 papers
- Institut national de recherche en sciences et technologies du numériqueFR6 papers
- Sorbonne UniversitéFR6 papers
- Université Pierre-et-Marie-CurieFR5 papers
- Institut de Recherche en Informatique de ToulouseFR4 papers
- Institut Polytechnique de BordeauxFR3 papers
- Universidade Estadual de Campinas (UNICAMP)BR3 papers
- Université Gustave EiffelFR3 papers
- Université Paris CitéFR3 papers
8 papers · 1 filter
HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks
Yanick Chistian Tchenko, Felix Mohr, Hicham Hadj Abdelkader +1
A prevailing trend in neural network research suggests that model performance improves with increasing depth and capacity - often at the cost of integrability and efficiency. In th…
Self-supervised learning on gene expression data
Kevin Dradjat, Massinissa Hamidi, Pierre Bartet +1
Predicting phenotypes from gene expression data is a crucial task in biomedical research, enabling insights into disease mechanisms, drug responses, and personalized medicine. Trad…
Trustworthy Efficient Communication for Distributed Learning using LQ-SGD Algorithm
Hongyang Li, Lincen Bai, Caesar Wu +3
We propose LQ-SGD (Low-Rank Quantized Stochastic Gradient Descent), an efficient communication gradient compression algorithm designed for distributed training. LQ-SGD further deve…
Trustworthiness of Stochastic Gradient Descent in Distributed Learning
Hongyang Li, Caesar Wu, Mohammed Chadli +2
Distributed learning (DL) uses multiple nodes to accelerate training, enabling efficient optimization of large-scale models. Stochastic Gradient Descent (SGD), a key optimization a…
Adaptive Pruning with Module Robustness Sensitivity: Balancing Compression and Robustness
Lincen Bai, Hedi Tabia, Raúl Santos-Rodríguez
Neural network pruning has traditionally focused on weight-based criteria to achieve model compression, frequently overlooking the crucial balance between adversarial robustness an…
RRR-Net: Reusing, Reducing, and Recycling a Deep Backbone Network
Haozhe Sun, Isabelle Guyon, Felix Mohr +1
It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pre-trained on large datasets as preprocessors. Typically, the last layer…