# OpenViewer: Openness-Aware Multi-View Learning

arXiv: https://arxiv.org/abs/2412.12596 · HTML: https://mlsanity.com/paper/2412.12596/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 54 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 6 of 6)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [EIGNN: Efficient Infinite-Depth Graph Neural Networks](https://mlsanity.com/paper/2202.10720/) (2022)
- [XAI Beyond Classification: Interpretable Neural Clustering](https://mlsanity.com/paper/1808.07292/) (2018)
- [Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences](https://mlsanity.com/paper/2205.15075/) (2022)
- [MGNNI: Multiscale Graph Neural Networks with Implicit Layers](https://mlsanity.com/paper/2210.08353/) (2022)

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

- [LargeMvC-Net: Anchor-based Deep Unfolding Network for Large-scale Multi-view Clustering](https://mlsanity.com/paper/2507.20980/) (2025)
- [Association and Consolidation: Evolutionary Memory-Enhanced Incremental Multi-View Clustering](https://mlsanity.com/paper/2509.14544/) (2025)
- [Stable Multimodal Graph Unlearning via Feature-Dimension Aware Quantile Selection](https://mlsanity.com/paper/2605.03303/) (2026)
- [Robust Multi-view Clustering against Imperfect Information](https://mlsanity.com/paper/2606.04343/) (2026)

## Abstract (arXiv)

Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained; 2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples. The code is released at https://github.com/dushide/OpenViewer.