# Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation

arXiv: https://arxiv.org/abs/2604.04170 · HTML: https://mlsanity.com/paper/2604.04170/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 11 of 11)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [A Concise yet Effective model for Non-Aligned Incomplete Multi-view and Missing Multi-label Learning](https://mlsanity.com/paper/2005.00976/) (2020)
- [Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers](https://mlsanity.com/paper/2303.07180/) (2023)
- [DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification](https://mlsanity.com/paper/2303.08358/) (2023)
- [Reliable Representation Learning for Incomplete Multi-View Missing Multi-Label Classification](https://mlsanity.com/paper/2303.17117/) (2023)
- [Multi-Label Knowledge Distillation](https://mlsanity.com/paper/2308.06453/) (2023)
- [Masked Two-channel Decoupling Framework for Incomplete Multi-view Weak Multi-label Learning](https://mlsanity.com/paper/2404.17340/) (2024)

## Abstract (arXiv)

Although multi-view multi-label learning has been extensively studied, research on the dual-missing scenario, where both views and labels are incomplete, remains largely unexplored. Existing methods mainly rely on contrastive learning or information bottleneck theory to learn consistent representations under missing-view conditions, but loss-based alignment without explicit structural constraints limits the ability to capture stable and discriminative shared semantics. To address this issue, we introduce a more structured mechanism for consistent representation learning: we learn discrete consistent representations through a multi-view shared codebook and cross-view reconstruction, which naturally align different views within the limited shared codebook embeddings and reduce feature redundancy. At the decision level, we design a weight estimation method that evaluates the ability of each view to preserve label correlation structures, assigning weights accordingly to enhance the quality of the fused prediction. In addition, we introduce a fused-teacher self-distillation framework, where the fused prediction guides the training of view-specific classifiers and feeds the global knowledge back into the single-view branches, thereby enhancing the generalization ability of the model under missing-label conditions. The effectiveness of our proposed method is thoroughly demonstrated through extensive comparative experiments with advanced methods on five benchmark datasets. Code is available at https://github.com/xuy11/SCSD.