Learning invariances via correlation and marginal alignments for out-of-distribution generalization
文献类型：期刊论文
| 作者 | Guo, Zong1,2; Ma, Bingpeng2 |
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2026-04-14 |
| 卷号 | 674页码:11 |
| 关键词 | Out-of-distribution generalization Spurious correlation Invariant risk minimization Correlation alignment Marginal distribution alignment |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2026.132876 |
| 英文摘要 | Out-of-distribution generalization is a crucial challenge in machine learning, especially when spurious correla tions exist. To this end, Invariant Risk Minimization (IRM) proposes a promising paradigm by learning invariances from multiple training environments. However, IRM-based methods can be ineffective in certain situations. In this paper, we first analyze two main defects in IRM: the necessity of linear representation function assumption, and undesired solutions induced by misalignment of marginal distributions. Then, we propose a novel method to address these defects. We realize that the necessity of linear representation function assumption stems from not specifying the optimal classifier for each environment. Therefore, we define the optimal classifier to be the Canonical Correlation Analysis (CCA) classifier. This enables our method to be solved without linear representa tion function assumption. Furthermore, since the undesired solutions are attributed to misalignment of marginal distributions, we instead align representation-label correlation and marginal distribution of the representation. While slightly stronger, this is sufficient for matching the optimal CCA classifier. With the alignment of marginal distribution of the representation, the problem of undesired solutions can be mitigated. Experiments on five vision benchmarks and one regression task demonstrate the effectiveness of our proposed method. Our code is available at https://github.com/ZongGuo1995/CMA. |
| 资助项目 | National Natural Science Foundation of China (NSFC)[62276246] ; Fundamental Research Funds for the Central Universities |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001684145500002 |
| 出版者 | ELSEVIER |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42819]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Ma, Bingpeng |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Guo, Zong,Ma, Bingpeng. Learning invariances via correlation and marginal alignments for out-of-distribution generalization[J]. NEUROCOMPUTING,2026,674:11. |
| APA | Guo, Zong,&Ma, Bingpeng.(2026).Learning invariances via correlation and marginal alignments for out-of-distribution generalization.NEUROCOMPUTING,674,11. |
| MLA | Guo, Zong,et al."Learning invariances via correlation and marginal alignments for out-of-distribution generalization".NEUROCOMPUTING 674(2026):11. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。