Refining the Information Bottleneck via Adversarial Information Separation
Shuai Ning Zhenpeng Wang Lin Wang Bing Chen Shuangrong Liu Xu Wu Jin Zhou Bo Yang
作者信息
Abstract
Generalizing from limited data is particularly critical for models in domains such as material science, where task-relevant features in experimental datasets are often heavily confounded by measurement noise and experimental artifacts. Standard regularization techniques fail to precisely separate meaningful features from noise, while existing adversarial adaptation methods are limited by their reliance on explicit separation labels. To address this challenge, we propose the Adversarial Information Separation Framework (AdverISF), which isolates task-relevant features from noise without requiring explicit supervision. AdverISF introduces a self-supervised adversarial mechanism to enforce statistical independence between task-relevant features and noise representations. It further employs a multi-layer separation architecture that progressively recycles noise information across feature hierarchies to recover features inadvertently discarded as noise, thereby enabling finer-grained feature extraction. Extensive experiments demonstrate that AdverISF outperforms state-of-the-art methods in data-scarce scenarios. In addition, evaluations on real-world material design tasks show that it achieves superior generalization performance.引用本文复制引用
Shuai Ning,Zhenpeng Wang,Lin Wang,Bing Chen,Shuangrong Liu,Xu Wu,Jin Zhou,Bo Yang.Refining the Information Bottleneck via Adversarial Information Separation[EB/OL].(2026-02-09)[2026-02-12].https://arxiv.org/abs/2602.06549.学科分类
计算技术、计算机技术
|国家预印本平台
评论