Variational Co-embedding Learning for Attributed Network Clustering

TL;DR

This paper introduces VCLANC, a novel variational co-embedding model that jointly learns node and attribute embeddings for improved attributed network clustering by exploiting mutual affinities.

Contribution

The paper proposes a dual variational auto-encoder framework that captures mutual node-attribute affinities and enhances clustering accuracy over existing methods.

Findings

VCLANC outperforms baseline methods on four real-world datasets.

Mutual affinity reconstruction improves embedding quality.

Enhanced clustering performance demonstrated through experiments.

Abstract

Recent works for attributed network clustering utilize graph convolution to obtain node embeddings and simultaneously perform clustering assignments on the embedding space. It is effective since graph convolution combines the structural and attributive information for node embedding learning. However, a major limitation of such works is that the graph convolution only incorporates the attribute information from the local neighborhood of nodes but fails to exploit the mutual affinities between nodes and attributes. In this regard, we propose a variational co-embedding learning model for attributed network clustering (VCLANC). VCLANC is composed of dual variational auto-encoders to simultaneously embed nodes and attributes. Relying on this, the mutual affinity information between nodes and attributes could be reconstructed from the embedding space and served as extra self-supervised knowledge for representation learning. At the same time, trainable Gaussian mixture model is used as priors to infer the node clustering assignments. To strengthen the performance of the inferred clusters, we use a mutual distance loss on the centers of the Gaussian priors and a clustering assignment hardening loss on the node embeddings. Experimental results on four real-world attributed network datasets demonstrate the effectiveness of the proposed VCLANC for attributed network clustering.