Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View

TL;DR

This paper proposes a novel loss reweighting method for long-tailed classification, inspired by Neural Collapse, which dynamically infers class weights to achieve an ideal equal loss target, improving performance.

Contribution

It introduces an inverse problem perspective for loss reweighting based on Neural Collapse geometry, enabling dynamic class weight inference for better imbalance handling.

Findings

Effectively reduces loss imbalance coefficient.

Aligns class features closer to Neural Collapse geometry.

Outperforms strong long-tailed classification baselines.

Abstract

Loss reweighting is a widely used strategy for long-tailed classification, but existing reweighting strategies often rely on heuristics and rarely define a well-specified target. Inspired by Neural Collapse (NC), the ideal simplex Equiangular Tight Frame (ETF) terminal geometry suggests equal per-class average loss as a reasonable target for reweighting. Based on the ideal equal loss objective, we consider loss reweighting as an inverse problem and propose an inverse-view reweighting strategy that infers class weights dynamically to match this ideal objective. Empirically, NC metrics suggest our method can effectively reduce the loss imbalance coefficient and closer alignment with NC geometry while consistently outperforming strong long-tailed baselines on different datasets.