2 papers
cs.LG2026
Understanding Imbalanced Forgetting in Rehearsal-Based Class-Incremental Learning
Alberto Tamajo, Srinandan Dasmahapatra, Rahman Attar
Neural networks suffer from catastrophic forgetting in class-incremental learning (CIL) settings. Rehearsal$\unicode{x2013}$replaying a subset of past samples$\unicode{x2013}$is a…
cs.LG2026
Mini-Batch Class Composition Bias in Link Prediction
Kieran Maguire, Srinandan Dasmahapatra
Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. Fo…