AdaMuS: Adaptive Multi-view Sparsity Learning for Dimensionally Unbalanced Data

TL;DR

AdaMuS introduces an adaptive multi-view learning framework that effectively handles severe dimensional disparities among views, improving representation alignment and generalization in complex data scenarios.

Contribution

The paper proposes a novel adaptive multi-view sparsity learning method with view-specific encoders, parameter-free pruning, and a sparse fusion paradigm to address unbalanced multi-view data.

Findings

AdaMuS outperforms existing methods on synthetic and real-world benchmarks.

The framework achieves superior classification and semantic segmentation results.

It demonstrates strong generalization across diverse tasks.

Abstract

Multi-view learning primarily aims to fuse multiple features to describe data comprehensively. Most prior studies implicitly assume that different views share similar dimensions. In practice, however, severe dimensional disparities often exist among different views, leading to the unbalanced multi-view learning issue. For example, in emotion recognition tasks, video frames often reach dimensions of $10^6$, while physiological signals comprise only $10^1$ dimensions. Existing methods typically face two main challenges for this problem: (1) They often bias towards high-dimensional data, overlooking the low-dimensional views. (2) They struggle to effectively align representations under extreme dimensional imbalance, which introduces severe redundancy into the low-dimensional ones. To address these issues, we propose the Adaptive Multi-view Sparsity Learning (AdaMuS) framework. First, to prevent ignoring the information of low-dimensional views, we construct view-specific encoders to map them into a unified dimensional space. Given that mapping low-dimensional data to a high-dimensional space often causes severe overfitting, we design a parameter-free pruning method to adaptively remove redundant parameters in the encoders. Furthermore, we propose a sparse fusion paradigm that flexibly suppresses redundant dimensions and effectively aligns each view. Additionally, to learn representations with stronger generalization, we propose a self-supervised learning paradigm that obtains supervision information by constructing similarity graphs. Extensive evaluations on a synthetic toy dataset and seven real-world benchmarks demonstrate that AdaMuS consistently achieves superior performance and exhibits strong generalization across both classification and semantic segmentation tasks.