Deep Contrastive Multiview Network Embedding

TL;DR

This paper introduces CREME, a novel contrastive learning framework for multiview network embedding that effectively fuses multiple views and captures their complementary information, leading to improved node representations.

Contribution

The work proposes a unified contrastive learning approach with view fusion and inter-view objectives, enhancing multiview network embedding performance.

Findings

CREME outperforms state-of-the-art methods on three real-world datasets.

The dual objectives improve the quality of fused and complementary view embeddings.

The framework effectively captures semantic consistency and view complementarities.

Abstract

Multiview network embedding aims at projecting nodes in the network to low-dimensional vectors, while preserving their multiple relations and attribute information. Contrastive learning approaches have shown promising performance in this task. However, they neglect the semantic consistency between fused and view representations and have difficulty in modeling complementary information between different views. To deal with these deficiencies, this work presents a novel Contrastive leaRning framEwork for Multiview network Embedding (CREME). In our work, different views can be obtained based on the various relations among nodes. Then, we generate view embeddings via proper view encoders and utilize an attentive multiview aggregator to fuse these representations. Particularly, we design two collaborative contrastive objectives, view fusion InfoMax and inter-view InfoMin, to train the model in a self-supervised manner. The former objective distills information from embeddings generated from different views, while the latter captures complementary information among views to promote distinctive view embeddings. We also show that the two objectives can be unified into one objective for model training. Extensive experiments on three real-world datasets demonstrate that our proposed CREME is able to consistently outperform state-of-the-art methods.