跳到正文
arXiv cs.AI· Zhen Zhang, Jielei Chu, Jiangtao Hu, Bin Liu, Jie Wang, Ya Liu, Fengmao Lv, Tianrui Li·· 2 小时前AI 评分27

反事实特征正则化:解决基于扩展的类增量学习中的特征冲突

Counterfactual Feature Regularization for Expansion-Based Class-Incremental Learning

AI 导读

一项 arXiv 研究提出基于必要与充分概率(PNS)的正则化方法 CPNS,用于缓解基于扩展的类增量学习(CIL)中的特征冲突。该方法将特征冲突归因于任务内与任务间两类伪相关,并通过基于孪生网络的双范围反事实生成器分别保证任务内表征的因果完整性与任务间表征的可分性。该正则化是即插即用方法,理论分析与大量实验验证了其有效性。

正文 · 原文

View PDF HTML (experimental)

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 to interference, inevitably drifting into the feature space of other tasks; (ii) inter-task spurious correlations induce semantic confusion between visually similar classes across tasks. To address this, we propose a Probability of Necessity and Sufficiency (PNS)-based regularization method to guide feature expansion in CIL. Specifically, we first extend the definition of PNS to expansion-based CIL, termed CPNS, which quantifies both the causal completeness of intra-task representations and the separability of inter-task representations. We then introduce a dual-scope counterfactual generator based on twin networks to ensure the measurement of CPNS, which simultaneously generates: (i) intra-task counterfactual features to minimize intra-task PNS risk and ensure causal completeness of task-specific features, and (ii) inter-task interfering features to minimize inter-task PNS risk, ensuring the separability of inter-task representations. Theoretical analyses confirm its reliability. The regularization is a plug-and-play method for expansion-based CIL to mitigate feature collision. Extensive experiments demonstrate the effectiveness of the proposed method.
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2603.09145 [cs.LG]
  (or arXiv:2603.09145v4 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2603.09145

arXiv-issued DOI via DataCite

Submission history

From: Zhen Zhang [view email]
[v1] Tue, 10 Mar 2026 03:33:33 UTC (2,766 KB)
[v2] Mon, 13 Apr 2026 12:23:08 UTC (4,724 KB)
[v3] Wed, 29 Apr 2026 07:50:12 UTC (14,469 KB)
[v4] Wed, 18 Nov 2026 01:38:09 UTC (14,795 KB)

来源:arXiv cs.AI · arxiv.org