LGJun 23

The Gentle Collapse: Distributional Metrics for Continual Learning

arXiv:2606.251655.8
Predicted impact top 71% in LG · last 90 daysOriginality Incremental advance
AI Analysis

For continual learning researchers, this work provides finer-grained tools to analyze and mitigate catastrophic forgetting, offering actionable improvements over standard accuracy-based methods.

The authors propose six softmax-derived metrics that characterize catastrophic forgetting continuously, revealing structure hidden by accuracy. On CIFAR-100, using these metrics as loss weights reduces forgetting by 1.3 percentage points over uniform experience replay, and on TinyImageNet, log-TLR trend sampling reduces forgetting by 7.7 percentage points.

Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapses discretely at task boundaries, hiding the internal structure of what is being forgotten. We introduce six softmax-derived metrics spanning true-label rank (TLR), predictive confidence, and distributional divergence that characterize forgetting continuously, each normalized to [0, 1] with no modification to training. On CIFAR-100, these metrics carry information where accuracy does not: at 0% accuracy, the Confusion Margin spans an IQR of [0.32, 0.50] across classes that accuracy treats identically. We demonstrate that this richer signal is actionable in mitigating catastrophic forgetting. Per-sample metric scores used as loss weights reduce forgetting by 1.3 percentage points over uniform experience replay (ER) on CIFAR-100. Furthermore, the slope of a metric over a small window provides a stable sampling criterion: at a small-window size (e.g. 3 epochs), accuracy-trend degrades to 34.79% (std. = 2.32) while log-TLR achieves 41.07% (std. = 0.57). This gap is structural since reliable small-window trend estimation requires a continuous signal. On TinyImageNet, log-TLR trend sampling reduces forgetting by 7.7 percentage points over the ER baseline.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes