# Are Independently Estimated View Uncertainties Comparable? Unified Routing for Trusted Multi-View Classification

arXiv: https://arxiv.org/abs/2604.09288 · HTML: https://mlsanity.com/paper/2604.09288/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 51 references that are in the map.
- First posted on arXiv 10 Apr 2026.

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

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Uncertainty Estimation by Fisher Information-based Evidential Deep Learning](https://mlsanity.com/paper/2303.02045/) (2023)
- [I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts](https://mlsanity.com/paper/2505.19190/) (2025)
- [Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification](https://mlsanity.com/paper/2304.03981/) (2023)
- [Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification](https://mlsanity.com/paper/2409.00755/) (2024)
- [Revisiting Essential and Nonessential Settings of Evidential Deep Learning](https://mlsanity.com/paper/2410.00393/) (2024)
- [Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty](https://mlsanity.com/paper/2404.10980/) (2024)
- [Navigating Conflicting Views: Harnessing Trust for Learning](https://mlsanity.com/paper/2406.00958/) (2024)
- [Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing](https://mlsanity.com/paper/2508.01227/) (2025)

## Abstract (arXiv)

Trusted multi-view classification typically relies on a view-wise evidential fusion process: each view independently produces class evidence and uncertainty, and the final prediction is obtained by aggregating these independent opinions. While this design is modular and uncertainty-aware, it implicitly assumes that evidence from different views is numerically comparable. In practice, however, this assumption is fragile. Different views often differ in feature space, noise level, and semantic granularity, while independently trained branches are optimized only for prediction correctness, without any constraint enforcing cross-view consistency in evidence strength. As a result, the uncertainty used for fusion can be dominated by branch-specific scale bias rather than true sample-level reliability. To address this issue, we propose Trusted Multi-view learning with Unified Routing (TMUR), which decouples view-specific evidence extraction from fusion arbitration. TMUR uses view-private experts and one collaborative expert, and employs a unified router that observes the global multi-view context to generate sample-level expert weights. Soft load-balancing and diversity regularization further encourage balanced expert utilization and more discriminative expert specialization. We also provide theoretical analysis showing why independent evidential supervision does not identify a common cross-view evidence scale. Extensive experiments on 14 datasets and comparisons with 15 recent baselines demonstrate that TMUR consistently improves both classification performance and reliability. Code is available at https://github.com/YilinZhang107/TMUR.