Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
FIRM: Fisher-Informed Retention Merging for Federated LLM Unlearning
Reeyansh Shah, Maram Hasan, Subhasis Chaudhuri +1
Federated LLM unlearning addresses targeted knowledge removal when forget and retain data remain distributed across private clients and are inaccessible to the server. The resultin…
cs.LG2024
Revised Regularization for Efficient Continual Learning through Correlation-Based Parameter Update in Bayesian Neural Networks
Sanchar Palit, Biplab Banerjee, Subhasis Chaudhuri
We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in cont…