Reliable Neighborhood-Aware Multi-View Outlier Detection
Huijie Ma, Haoyuan Xin, Lei Meng, Guanzhou Ke, Yongyong Chen, Guoqing Chao
Abstract
In recent years, multi-view outlier detection (MVOD) has gained increasing attention, with the primary objective of recovering the underlying structure of normal data from outlier-contaminated multi-view datasets. However, this objective is hindered by two fundamental challenges:(i) outlier propagation, (ii) scale discrepancy. To address these issues, we propose RNAMOD (Reliable Neighborhood-Aware Multi-View Outlier Detection), which introduces the concept of reliability and constructs a reliable neighborhood structure to avoid outlier propagation. We introduce a leave-one-out directional consensus mechanism to align cross-view neighborhood structures while preventing scale discrepancy by aligning geometric directions that remain invariant to scaling. Extensive experiments on six benchmark datasets demonstrate that RNAMOD consistently outperforms state-of-the-art methods.
BibTeX
@inproceedings{
ma2026reliable,
title={Reliable Neighborhood-Aware Multi-View Outlier Detection},
author={Huijie Ma and Haoyuan Xin and Lei Meng and Guanzhou Ke and Yongyong Chen and Guoqing Chao},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=mL4B6DdgPU}
}