FirsthandTech
arXiv: cs.AI preprintsInternational20 November 2026

Counterfactual Feature Regularization for Expansion-Based Class-Incremental Learning

This is an official announcement record

Firsthand records what arXiv: cs.AI preprints announced and links to the original. The wording below is theirs, not ours.

arXiv:2603.09145v4 Announce Type: replace-cross Abstract: Current expansion-based methods for Class Incremental Learning (CIL) effectively mitigate catastrophic forgetting by freezing old features. However, such task-specific features learned from the new task may collide with the old features. From a causal perspective, spurious feature correlations are the main cause of this collision, manifesting in two scopes: (i) guided by empirical risk minimization (ERM), intra-task spurious correlations cause task-specific features to rely on shortcut features. These non-robust features are vulnerable
Source: arXiv: cs.AI preprints

More from arXiv: cs.AI preprints

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.