MOAL: Multi-view Out-of-distribution Awareness Learning.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date: May 27, 2025

Abstract

Multi-view learning integrates data from multiple sources to enhance task performance by improving data quality. However, existing approaches primarily focus on intra-distribution data learning and consequently fail to identify out-of-distribution instances effectively. This paper introduces a method to improve the perception of out-of-distribution data in multi-view situations. First, we employ multi-view consistency and complementarity principles to develop sub-view complementarity representation learning and multi-view consistency fusion layers, thereby enhancing the model's perception ability to typical intra-distribution features. Additionally, we introduce a specialized multi-view training loss and an agent mechanism tailored for out-of-distribution scenarios, facilitating the ability to differentiate between known and new or anomalous instances effectively. The proposed approach enhances the recognition of out-of-distribution data by improving intra-distribution feature representations and minimizing the entropy associated with out-of-distribution instances. Experimental results on multiple multi-view datasets simulating out-of-distribution scenarios confirm the effectiveness of MOLA, which consistently outperforms all baselines with average accuracy improvements of over 5%.

Authors

  • Xuzheng Wang
    College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China; Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University, Fuzhou 350108, China. Electronic address: wangxuzheng@126.com.
  • Zihan Fang
    College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China. Electronic address: fzihan11@163.com.
  • Shide Du
    College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China; Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University, Fuzhou 350108, China. Electronic address: dushidems@gmail.com.
  • Wenzhong Guo
    College of Mathematics and Computer Sciences, Fuzhou University, Fujian, China.
  • Shiping Wang
    College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong, Shenzhen 518172, China. Electronic address: shipingwangphd@163.com.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals