# Trusted Multi-view Learning under Noisy Supervision

arXiv: https://arxiv.org/abs/2404.11944 · HTML: https://mlsanity.com/paper/2404.11944/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 18 Apr 2024.

## Builds on (most cited first, 18 of 18)

- [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)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise](https://mlsanity.com/paper/1802.05300/) (2018)
- [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)
- [Learning with Instance-Dependent Label Noise: A Sample Sieve Approach](https://mlsanity.com/paper/2010.02347/) (2020)
- [Trusted Multi-View Classification](https://mlsanity.com/paper/2102.02051/) (2021)
- [Confidence Scores Make Instance-dependent Label-noise Learning Possible](https://mlsanity.com/paper/2001.03772/) (2020)
- [Uncertainty Estimation by Fisher Information-based Evidential Deep Learning](https://mlsanity.com/paper/2303.02045/) (2023)
- [Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation](https://mlsanity.com/paper/2206.02791/) (2022)
- [Reliable Conflictive Multi-View Learning](https://mlsanity.com/paper/2402.16897/) (2024)
- [A Survey on Incomplete Multi-view Clustering](https://mlsanity.com/paper/2208.08040/) (2022)
- [Information Recovery-Driven Deep Incomplete Multiview Clustering Network](https://mlsanity.com/paper/2304.00429/) (2023)
- [Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification](https://mlsanity.com/paper/2304.05165/) (2023)
- [Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels](https://mlsanity.com/paper/2312.01169/) (2023)
- [BERTERS: Multimodal Representation Learning for Expert Recommendation System with Transformer](https://mlsanity.com/paper/2007.07229/) (2020)

## Built on by (most cited first, 8 of 8)

- [Navigating Conflicting Views: Harnessing Trust for Learning](https://mlsanity.com/paper/2406.00958/) (2024)
- [Generalizable and Robust Spectral Method for Multi-view Representation Learning](https://mlsanity.com/paper/2411.02138/) (2024)
- [Generalized Trusted Multi-view Classification Framework with Hierarchical Opinion Aggregation](https://mlsanity.com/paper/2411.03713/) (2024)
- [Reliable Disentanglement Multi-view Learning Against View Adversarial Attacks](https://mlsanity.com/paper/2505.04046/) (2025)
- [Fairness-Aware Multi-view Evidential Learning with Adaptive Prior](https://mlsanity.com/paper/2508.12997/) (2025)
- [Pareto-Guided Optimization for Uncertainty-Aware Medical Image Segmentation](https://mlsanity.com/paper/2601.19365/) (2026)
- [Robust Fuzzy Multi-view Learning under View Conflict](https://mlsanity.com/paper/2605.24475/) (2026)
- [Robust Multi-View Classification under Noisy Supervision via Global Anchor Consensus](https://mlsanity.com/paper/2607.18561/) (2026)

## Abstract (arXiv)

Multi-view learning methods often focus on improving decision accuracy while neglecting the decision uncertainty, which significantly restricts their applications in safety-critical scenarios. To address this, trusted multi-view learning methods estimate prediction uncertainties by learning class distributions from each instance. However, these methods heavily rely on high quality ground-truth labels. This motivates us to delve into a new problem: how to develop a reliable multi-view learning model under the guidance of noisy labels? We propose the Trusted Multi view Noise Refining (TMNR) method to address this challenge by modeling label noise arising from low-quality data features and easily-confused classes. TMNR employs evidential deep neural networks to construct view-specific opinions that capture both beliefs and uncertainty. These opinions are then transformed through noise correlation matrices to align with the noisy supervision, where matrix elements are constrained by sample uncertainty to reflect label reliability. Furthermore, considering the challenge of jointly optimizing the evidence network and noise correlation matrices under noisy supervision, we further propose Trusted Multi-view Noise Re-Refining (TMNR^2 ), which disentangles this complex co-training problem by establishing different training objectives for distinct modules. TMNR^2 identifies potentially mislabeled samples through evidence-label consistency and generates pseudo-labels from neighboring information. By assigning clean samples to optimize evidential networks and noisy samples to guide noise correlation matrices, respectively, TMNR^2 reduces mapping interference and achieves stabilizes training. Experimental results demonstrate that TMNR^2 significantly outperforms baseline methods, with average accuracy improvements of 7% on datasets with 50% label noise.