Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Quanjiang, Liu, Zhiming, Xu, Tianxiang, Luo, Tingjin, Hou, Chenping
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914243315499008
author Li, Quanjiang
Liu, Zhiming
Xu, Tianxiang
Luo, Tingjin
Hou, Chenping
author_facet Li, Quanjiang
Liu, Zhiming
Xu, Tianxiang
Luo, Tingjin
Hou, Chenping
contents Multi-view multi-label learning frequently suffers from simultaneous feature absence and incomplete annotations, due to challenges in data acquisition and cost-intensive supervision. To tackle the complex yet highly practical problem while overcoming the existing limitations of feature recovery, representation disentanglement, and label semantics modeling, we propose an Adaptive Disentangled Representation Learning method (ADRL). ADRL achieves robust view completion by propagating feature-level affinity across modalities with neighborhood awareness, and reinforces reconstruction effectiveness by leveraging a stochastic masking strategy. Through disseminating category-level association across label distributions, ADRL refines distribution parameters for capturing interdependent label prototypes. Besides, we formulate a mutual-information-based objective to promote consistency among shared representations and suppress information overlap between view-specific representation and other modalities. Theoretically, we derive the tractable bounds to train the dual-channel network. Moreover, ADRL performs prototype-specific feature selection by enabling independent interactions between label embeddings and view representations, accompanied by the generation of pseudo-labels for each category. The structural characteristics of the pseudo-label space are then exploited to guide a discriminative trade-off during view fusion. Finally, extensive experiments on public datasets and real-world applications demonstrate the superior performance of ADRL.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05785
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification
Li, Quanjiang
Liu, Zhiming
Xu, Tianxiang
Luo, Tingjin
Hou, Chenping
Computer Vision and Pattern Recognition
Artificial Intelligence
Multi-view multi-label learning frequently suffers from simultaneous feature absence and incomplete annotations, due to challenges in data acquisition and cost-intensive supervision. To tackle the complex yet highly practical problem while overcoming the existing limitations of feature recovery, representation disentanglement, and label semantics modeling, we propose an Adaptive Disentangled Representation Learning method (ADRL). ADRL achieves robust view completion by propagating feature-level affinity across modalities with neighborhood awareness, and reinforces reconstruction effectiveness by leveraging a stochastic masking strategy. Through disseminating category-level association across label distributions, ADRL refines distribution parameters for capturing interdependent label prototypes. Besides, we formulate a mutual-information-based objective to promote consistency among shared representations and suppress information overlap between view-specific representation and other modalities. Theoretically, we derive the tractable bounds to train the dual-channel network. Moreover, ADRL performs prototype-specific feature selection by enabling independent interactions between label embeddings and view representations, accompanied by the generation of pseudo-labels for each category. The structural characteristics of the pseudo-label space are then exploited to guide a discriminative trade-off during view fusion. Finally, extensive experiments on public datasets and real-world applications demonstrate the superior performance of ADRL.
title Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.05785