# When Semantically Consistent Encoding Meets View-Label Heterogeneity Modeling: A Unified Framework for Incomplete Multi-View Multi-Label Learning

arXiv: https://arxiv.org/abs/2609.07525 · HTML: https://mlsanity.com/paper/2609.07525/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 67 references that are in the map.
- First posted on arXiv 7 Sep 2026.

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

- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [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)
- [Multi-Label Learning with Global and Local Label Correlation](https://mlsanity.com/paper/1704.01415/) (2017)
- [Large Loss Matters in Weakly Supervised Multi-Label Classification](https://mlsanity.com/paper/2206.03740/) (2022)
- [A Survey on Incomplete Multi-view Clustering](https://mlsanity.com/paper/2208.08040/) (2022)
- [One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement](https://mlsanity.com/paper/2206.00517/) (2022)
- [A Concise yet Effective model for Non-Aligned Incomplete Multi-view and Missing Multi-label Learning](https://mlsanity.com/paper/2005.00976/) (2020)
- [DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification](https://mlsanity.com/paper/2303.08358/) (2023)
- [Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification](https://mlsanity.com/paper/2304.05165/) (2023)
- [Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration](https://mlsanity.com/paper/2407.06844/) (2024)
- [Reliable Representation Learning for Incomplete Multi-View Missing Multi-Label Classification](https://mlsanity.com/paper/2303.17117/) (2023)
- [Expand Globally, Shrink Locally: Discriminant Multi-label Learning with Missing Labels](https://mlsanity.com/paper/2004.03951/) (2020)
- [An Effective Approach for Multi-label Classification with Missing Labels](https://mlsanity.com/paper/2210.13651/) (2022)
- [Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion](https://mlsanity.com/paper/2510.13887/) (2025)
- [Variational Distillation for Multi-View Learning](https://mlsanity.com/paper/2206.09548/) (2022)
- [Open-world Multi-label Text Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2407.05609/) (2024)

## Abstract (arXiv)

Incomplete multi-view multi-label learning requires not only robust semantic aggregation from partially observed views, but also label-aware exploitation of view-specific evidence. Existing approaches usually emphasize either shared representation learning or decision-level fusion. The former improves robustness against missing views, yet tends to compress label-discriminative view-specific cues into a single latent representation. The latter preserves individual view predictions, but often relies on fixed or globally learned fusion weights, ignoring that different labels of different instances may require different views. To address these limitations, this paper presents V2L, a unified representation-decision framework for incomplete multi-view multi-label classification. On the representation side, V2L constructs semantically consistent variational posteriors from incomplete views through a perturbation-aware encoding mechanism, which provides a stable shared semantic basis. On the decision side, V2L introduces an active view-label relevance modeling strategy that estimates instance-wise and label-wise view contributions, allowing each label prediction to adaptively select useful view-specific evidence. From the perspective of model architecture, these two important strategies are integrated into a unified framework through a hybrid fusion architecture, simultaneously meeting the requirements of cross-view semantic consistency and representational complementarity. Extensive experiments under both incomplete and complete settings show that V2L achieves leading performance on five benchmarks. Code is available at: https://github.com/justsmart/V2L.