# Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification

arXiv: https://arxiv.org/abs/2304.05165 · HTML: https://mlsanity.com/paper/2304.05165/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 58 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 15 of 15)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Multimodal Generative Models for Scalable Weakly-Supervised Learning](https://mlsanity.com/paper/1802.05335/) (2018)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [A Survey of Multi-View Representation Learning](https://mlsanity.com/paper/1610.01206/) (2016)
- [Deep Partial Multi-View Learning](https://mlsanity.com/paper/2011.06170/) (2020)
- [What's a good imputation to predict with missing values?](https://mlsanity.com/paper/2106.00311/) (2021)
- [A Variational Information Bottleneck Approach to Multi-Omics Data Integration](https://mlsanity.com/paper/2102.03014/) (2021)
- [Tensor Canonical Correlation Analysis for Multi-view Dimension Reduction](https://mlsanity.com/paper/1502.02330/) (2015)
- [Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning](https://mlsanity.com/paper/1910.14179/) (2019)
- [Task Uncertainty Loss Reduce Negative Transfer in Asymmetric Multi-task Feature Learning](https://mlsanity.com/paper/2012.09575/) (2020)

## Built on by (most cited first, 13 of 13)

- [Multimodal Fusion on Low-quality Data: A Comprehensive Survey](https://mlsanity.com/paper/2404.18947/) (2024)
- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [Revisiting Essential and Nonessential Settings of Evidential Deep Learning](https://mlsanity.com/paper/2410.00393/) (2024)
- [Trusted Multi-view Learning under Noisy Supervision](https://mlsanity.com/paper/2404.11944/) (2024)
- [Evidential Deep Partial Multi-View Classification With Discount Fusion](https://mlsanity.com/paper/2408.13123/) (2024)
- [Representation Retrieval Learning for Heterogeneous Data Integration](https://mlsanity.com/paper/2503.09494/) (2025)
- [Towards Robust Uncertainty-Aware Incomplete Multi-View Classification](https://mlsanity.com/paper/2409.06270/) (2024)
- [Simple Yet Effective Selective Imputation for Incomplete Multi-view Clustering](https://mlsanity.com/paper/2512.10327/) (2025)
- [GIIM: Graph-based Learning of Inter- and Intra-view Dependencies for Multi-view Medical Image Diagnosis](https://mlsanity.com/paper/2603.09446/) (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)
- [MOSAIC: Modality-agnostic Spectral Alignment for Federated Image-level Weakly Supervised Tumor Segmentation under Client-specific Missing Modalities](https://mlsanity.com/paper/2608.19788/) (2026)
- [When Semantically Consistent Encoding Meets View-Label Heterogeneity Modeling: A Unified Framework for Incomplete Multi-View Multi-Label Learning](https://mlsanity.com/paper/2609.07525/) (2026)

## Abstract (arXiv)

Classifying incomplete multi-view data is inevitable since arbitrary view missing widely exists in real-world applications. Although great progress has been achieved, existing incomplete multi-view methods are still difficult to obtain a trustworthy prediction due to the relatively high uncertainty nature of missing views. First, the missing view is of high uncertainty, and thus it is not reasonable to provide a single deterministic imputation. Second, the quality of the imputed data itself is of high uncertainty. To explore and exploit the uncertainty, we propose an Uncertainty-induced Incomplete Multi-View Data Classification (UIMC) model to classify the incomplete multi-view data under a stable and reliable framework. We construct a distribution and sample multiple times to characterize the uncertainty of missing views, and adaptively utilize them according to the sampling quality. Accordingly, the proposed method realizes more perceivable imputation and controllable fusion. Specifically, we model each missing data with a distribution conditioning on the available views and thus introducing uncertainty. Then an evidence-based fusion strategy is employed to guarantee the trustworthy integration of the imputed views. Extensive experiments are conducted on multiple benchmark data sets and our method establishes a state-of-the-art performance in terms of both performance and trustworthiness.