arXiv cs.AI· Zhen Zhang, Jielei Chu, Jiangtao Hu, Bin Liu, Jie Wang, Ya Liu, Fengmao Lv, Tianrui Li·· 10 小时前AI 评分18
基于反事实特征正则化的扩展式类增量学习方法
Counterfactual Feature Regularization for Expansion-Based Class-Incremental Learning
AI 导读
针对扩展式类增量学习中新任务特征与旧特征碰撞的问题,研究者提出基于必要性与充分性概率(PNS)的正则化方法 CPNS,从任务内与任务间两个层面量化特征的因果完整性与可分离性。该方法借助双网络反事实生成器同时生成任务内反事实特征与任务间干扰特征,以降低两类 PNS 风险,且为即插即用模块。理论分析与实验均验证了其有效性。
正文 · 原文
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