C^3L以語義概念引導打破持續學習中的解釋漂移循環
Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning
C^3L(Concept-Consistent Continual Learning)以離線發現的語義概念作為正則化錨點,打破持續學習中的解釋漂移循環。方法無需人工標註概念集,並以全自動方式發現概念及定位其空間位置。在五個基準測試及 20 多個基線上的評估中,C^3L於準確率、遺忘、解釋質素、虛假相關緩解及分佈外穩健性取得最先進表現。
Published on Oct 24
Authors:
,
Abstract
C3L prevents explanation drift in continual learning by anchoring saliency regularization to offline-discovered semantic concepts, suppressing spurious correlations through a relevance crowding-out effect.
Catastrophic forgetting in continual learning (CL) manifests not only as accuracy degradation but also as explanation drift: models maintain predictive accuracy while silently shifting attention from diagnostic features to spurious correlations. This work identifies and resolves a previously overlooked structural flaw in explanation-aware CL: pixel-level saliency regularization derives supervision targets from the model's own frozen saliency maps, creating a self-referential drift loop that actively reinforces spurious attention across tasks. We introduce C^3L (Concept-Consistent Continual Learning), which breaks this loop by anchoring regularization to class-consistent semantic concepts (e.g., ``curved beak'', ``striped pattern'') discovered offline, independent of model state, providing (i) target independence from model drift, and (ii) cross-instance semantic consistency across every instance of a class. We identify that our concept-based objective, combined with approximate LRP relevance conservation, induces a crowding-out effect: since concept and background regions compete for the relevance of the same prediction, enforcing high relevance within concept regions implicitly suppresses spurious background correlations without explicit penalization. \method does not require human-annotated concept sets, as it employs a fully automated concept discovery and spatial grounding. Extensive evaluation across five benchmarks and over 20 baselines demonstrates state-of-the-art performance in accuracy, forgetting, explanation quality, spurious correlation mitigation, and out-of-distribution robustness.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.33877
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.33877 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.33877 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.33877 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co