Contrastive Multi-View Graph Hashing

TL;DR

This paper introduces CMGHash, a novel end-to-end contrastive learning framework that generates unified binary embeddings from multi-view graph data, effectively capturing complex topological information for improved retrieval accuracy.

Contribution

The paper presents a new contrastive multi-view graph hashing method that encodes complex topological information into binary codes, addressing limitations of attribute-based multi-view hashing techniques.

Findings

CMGHash outperforms existing methods in retrieval accuracy on benchmark datasets.

The framework effectively fuses multi-view graph information into discriminative binary embeddings.

Contrastive loss improves the quality of node representations across multiple graph views.

Abstract

Multi-view graph data, which both captures node attributes and rich relational information from diverse sources, is becoming increasingly prevalent in various domains. The effective and efficient retrieval of such data is an important task. Although multi-view hashing techniques have offered a paradigm for fusing diverse information into compact binary codes, they typically assume attributes-based inputs per view. This makes them unsuitable for multi-view graph data, where effectively encoding and fusing complex topological information from multiple heterogeneous graph views to generate unified binary embeddings remains a significant challenge. In this work, we propose Contrastive Multi-view Graph Hashing (CMGHash), a novel end-to-end framework designed to learn unified and discriminative binary embeddings from multi-view graph data. CMGHash learns a consensus node representation space using a contrastive multi-view graph loss, which aims to pull $k$-nearest neighbors from all graphs closer while pushing away negative pairs, i.e., non-neighbor nodes. Moreover, we impose binarization constraints on this consensus space, enabling its conversion to a corresponding binary embedding space at minimal cost. Extensive experiments on several benchmark datasets demonstrate that CMGHash significantly outperforms existing approaches in terms of retrieval accuracy.