# Dynamic Evidence Decoupling for Trusted Multi-view Learning

arXiv: https://arxiv.org/abs/2410.03796 · HTML: https://mlsanity.com/paper/2410.03796/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 44 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [Uncertainty Estimation by Fisher Information-based Evidential Deep Learning](https://mlsanity.com/paper/2303.02045/) (2023)
- [Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering](https://mlsanity.com/paper/2106.11232/) (2021)
- [Multimodal Fusion on Low-quality Data: A Comprehensive Survey](https://mlsanity.com/paper/2404.18947/) (2024)
- [Reliable Conflictive Multi-View Learning](https://mlsanity.com/paper/2402.16897/) (2024)
- [Majority Vote of Diverse Classifiers for Late Fusion](https://mlsanity.com/paper/1404.7796/) (2014)
- [Disentangled Multimodal Representation Learning for Recommendation](https://mlsanity.com/paper/2203.05406/) (2022)
- [Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels](https://mlsanity.com/paper/2312.01169/) (2023)

## Built on by (most cited first, 4 of 4)

- [Generalized Trusted Multi-view Classification Framework with Hierarchical Opinion Aggregation](https://mlsanity.com/paper/2411.03713/) (2024)
- [CFCML: A Coarse-to-Fine Crossmodal Learning Framework For Disease Diagnosis Using Multimodal Images and Tabular Data](https://mlsanity.com/paper/2603.20016/) (2026)
- [Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration](https://mlsanity.com/paper/2605.03820/) (2026)
- [Robust Fuzzy Multi-view Learning under View Conflict](https://mlsanity.com/paper/2605.24475/) (2026)

## Abstract (arXiv)

Multi-view learning methods often focus on improving decision accuracy, while neglecting the decision uncertainty, limiting their suitability for safety-critical applications. To mitigate this, researchers propose trusted multi-view learning methods that estimate classification probabilities and uncertainty by learning the class distributions for each instance. However, these methods assume that the data from each view can effectively differentiate all categories, ignoring the semantic vagueness phenomenon in real-world multi-view data. Our findings demonstrate that this phenomenon significantly suppresses the learning of view-specific evidence in existing methods. We propose a Consistent and Complementary-aware trusted Multi-view Learning (CCML) method to solve this problem. We first construct view opinions using evidential deep neural networks, which consist of belief mass vectors and uncertainty estimates. Next, we dynamically decouple the consistent and complementary evidence. The consistent evidence is derived from the shared portions across all views, while the complementary evidence is obtained by averaging the differing portions across all views. We ensure that the opinion constructed from the consistent evidence strictly aligns with the ground-truth category. For the opinion constructed from the complementary evidence, we allow it for potential vagueness in the evidence. We compare CCML with state-of-the-art baselines on one synthetic and six real-world datasets. The results validate the effectiveness of the dynamic evidence decoupling strategy and show that CCML significantly outperforms baselines on accuracy and reliability. The code is released at https://github.com/Lihong-Liu/CCML.