A Conflict-aware Evidential Framework for Reliable Sleep Stage Classification

2026-05-16

AI Summary

This work addresses the unreliability of sleep staging in real-world scenarios caused by inconsistencies among multimodal sleep data. To tackle this challenge, the authors propose ConfSleepNet, a novel framework that dynamically handles inter-modal conflicts through a two-stage mechanism: multi-view evidence extraction followed by conflict-aware fusion. The approach innovatively incorporates a hybrid categorical structure tailored to the distinct characteristics of different modalities and introduces an evidence theory–based conflict-aware aggregation method to effectively integrate uncertain multi-view opinions. Both theoretical analysis and extensive experiments demonstrate that ConfSleepNet significantly enhances the accuracy and reliability of automated sleep staging.

Abstract

Multi-view learning has been widely applied for sleep stage classification using multi-modal data. However, existing methods typically assume that different modalities are well-aligned, which is often unattainable in real-world scenarios, thereby compromising the reliability of the staging results. In this paper, we propose ConfSleepNet, a conflict-aware evidential framework that dynamically resolves inter-view conflicts. The framework consists of multi-view evidence extraction and conflict-aware aggregation. In the first phase, it learns category-related evidence from different modalities, which represents the degree of support for individual sleep stages. Considering the inherent characteristics of varying modalities, we propose hybrid category structures for different modalities to promote more reasonable evidence learning. In the second phase, view-specific opinions, including prediction results and uncertainty, are constructed from the learned evidence. Notably, we propose a novel conflict-aware aggregation method that integrates these view-specific opinions into a reliable joint decision. This mechanism can effectively resolve conflicts among opinions and synthesize them into a reliable joint decision. Both theoretical analysis and experimental results demonstrate the effectiveness of ConfSleepNet in sleep staging tasks. The code is available at https://github.com/By4te/ConfSleepNet_ICML2026/.

Problem

• sleep stage classification
• multi-view learning
• modality misalignment
• inter-view conflict
• reliability

Innovation

• conflict-aware
• evidential reasoning
• multi-view learning
• sleep stage classification
• uncertainty quantification