BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance

AI Digest - ArXiv AI

BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance

Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its frozen backbone behaves when a new head is learned. We introduce BiasFlow, a hook-based toolkit for monitoring class-attribute centroid alignment (IBMI), within-class centroid separation (W-IBMI), and feature-projection sensitivity. IBMI is confounded by class-attribute correlation and is not a measure of causal feature reliance. We pair these diagnostics with BiasFlow Regularization (BFR), a supervised, c

Source: ArXiv AI