50 citations · 92 across the 40 of their papers we have counts for
3 papers · 1 filter
A Path Integral Surrogate for Multi-Step Gradient Inversion in Federated Learning
Agnivo Ghosh, Saumik Bhattacharya
Federated learning lets many clients train a shared model together without ever sending their private data to a central server. Each client shares only a model update, and this upd…
Dynamically Scaled Temperature in Self-Supervised Contrastive Learning
Siladittya Manna, Soumitri Chattopadhyay, Rakesh Dey +2
In contemporary self-supervised contrastive algorithms like SimCLR, MoCo, etc., the task of balancing attraction between two semantically similar samples and repulsion between two…
Multipath Graph Convolutional Neural Networks
Rangan Das, Bikram Boote, Saumik Bhattacharya +1
Graph convolution networks have recently garnered a lot of attention for representation learning on non-Euclidean feature spaces. Recent research has focused on stacking multiple l…