Interpretable Multi-View Representation Learning Towards Complex Scenes: From Homogeneity to Heterogeneity

Multi-view representation learning is recognized for its effectiveness in multi-source data analysis, yet it faces significant challenges: 1) Deep model structures remain opaque, lacking interpretability; 2) Research on compatibility models toward multi-feature and multi-relation data is insufficient. In this paper, we introduce an interpretable multi-view representation learning framework specifically designed for the complex multi-view scene. The barrier to achieving compatibility stems from the need to simultaneously process the homogeneous information inherent in multiple features and the heterogeneous characteristic of multi-relation data. To address this, we design an objective function solved by iterative methods to learn comprehensive relations and consistent representation. The introduction of comprehensive relations aims to mitigate mutual interference among different data types while combining information abstracted from original features and relations into a unified representation. We then convert iterative solutions into feed-forward network layers with embedded learnable modules, resulting in a deep network architecture that is interpretable at the design level. Extensive experimental results demonstrate the superior performance of the proposed method over state-of-the-art approaches.

• Publication year

  2026

• Venue

  IEEE transactions on multimedia

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/TMM.2025.3623557
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Reconstructed Graph Constrained Auto-Encoders for Multi-View Representation Learning

  2024cited by this paper
• Collaborative structure and feature learning for multi-view clustering

  2023cited by this paper
• Unsupervised feature selection via multiple graph fusion and feature weight learning

  2023cited by this paper
• Reinforcement Learning from Passive Data via Latent Intentions

  2023cited by this paper
• Interpretable Graph Convolutional Network for Multi-View Semi-Supervised Learning

  2023cited by this paper
• Affine Subspace Robust Low-Rank Self-Representation: From Matrix to Tensor

  2023cited by this paper
• Cross Modal Transformer: Towards Fast and Robust 3D Object Detection

  2023cited by this paper
• Dual Fusion-Propagation Graph Neural Network for Multi-View Clustering

  2023cited by this paper
• Unified One-Step Multi-View Spectral Clustering

  2023cited by this paper
• Graph Contrastive Partial Multi-View Clustering

  2023cited by this paper
• Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning

  2022cited by this paper
• Variational Distillation for Multi-View Learning

  2022cited by this paper
• Comprehensive Multi-view Representation Learning

  2022cited by this paper
• Multiplex Heterogeneous Graph Convolutional Network

  2022cited by this paper
• Trusted Multi-View Deep Learning with Opinion Aggregation

  2022cited by this paper
• Multi-View Graph Convolutional Networks with Differentiable Node Selection

  2022cited by this paper
• Learning Deep Sparse Regularizers With Applications to Multi-View Clustering and Semi-Supervised Classification

  2021cited by this paper
• Consistent Multiple Graph Embedding for Multi-View Clustering

  2021cited by this paper
• Graph Filter-based Multi-view Attributed Graph Clustering

  2021cited by this paper
• Towards Self-Explainable Graph Neural Network

  2021cited by this paper
• Multi-view Contrastive Graph Clustering

  2021cited by this paper
• Deep Graph Clustering via Dual Correlation Reduction

  2021cited by this paper
• Multi-View Attribute Graph Convolution Networks for Clustering

  2020cited by this paper
• One2Multi Graph Autoencoder for Multi-view Graph Clustering

  2020cited by this paper
• Hyper-Laplacian Regularized Multilinear Multiview Self-Representations for Clustering and Semisupervised Learning

  2020cited by this paper
• Robust Kernelized Multiview Self-Representation for Subspace Clustering

  2020cited by this paper
• Co-GCN for Multi-View Semi-Supervised Learning

  2020cited by this paper
• Joint Deep Multi-View Learning for Image Clustering

  2020cited by this paper
• Unsupervised Attributed Multiplex Network Embedding

  2019cited by this paper
• Towards Explainable Deep Neural Networks (xDNN)

  2019cited by this paper
• Graph Transformer Networks

  2019cited by this paper
• Deep Proximal Unrolling: Algorithmic Framework, Convergence Analysis and Applications

  2019cited by this paper
• Heterogeneous Graph Attention Network

  2019cited by this paper
• Graph Structure Fusion for Multiview Clustering

  2019cited by this paper
• A Survey of Methods for Explaining Black Box Models

  2018cited by this paper
• Interpret Neural Networks by Identifying Critical Data Routing Paths

  2018cited by this paper
• Beyond Sparsity: Tree Regularization of Deep Models for Interpretability

  2017cited by this paper
• Interpretable Convolutional Neural Networks

  2017cited by this paper
• ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing

  2017cited by this paper
• Interpreting Deep Visual Representations via Network Dissection

  2017cited by this paper
• On Unifying Multi-view Self-Representations for Clustering by Tensor Multi-rank Minimization

  2016cited by this paper

• No citing papers are available for this paper.