7 papers
Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning
Ousmane Touat, César Sabater, Mohamed Maouche +1
Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clients train a machine l…
GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework
Yacine Belal, Mohamed Maouche, Sonia Ben Mokhtar
Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers. Recent approaches rely on dyn…
DOME: Improving Signal-to-Noise in Stochastic Gradient Descent via Sharp-Direction Subspace Filtering
Julien Nicolas, Mohamed Maouche, Sonia Ben Mokhtar +1
Stochastic gradients for deep neural networks exhibit strong correlations along the optimization trajectory, and are often aligned with a small set of Hessian eigenvectors associat…
Exposing the Vulnerability of Decentralized Learning to Membership Inference Attacks Through the Lens of Graph Mixing
Ousmane Touat, Jezekael Brunon, Yacine Belal +4
The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their pre…
Differentially private and decentralized randomized power method
Julien Nicolas, César Sabater, Mohamed Maouche +2
The randomized power method has gained significant interest due to its simplicity and efficient handling of large-scale spectral analysis and recommendation tasks. However, its app…
Inferring Communities of Interest in Collaborative Learning-based Recommender Systems
Yacine Belal, Sonia Ben Mokhtar, Mohamed Maouche +1
Collaborative-learning-based recommender systems, such as those employing Federated Learning (FL) and Gossip Learning (GL), allow users to train models while keeping their history…