Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering

TL;DR

This paper introduces DyFSS, a novel method that dynamically assigns different SSL task weights to individual nodes in attributed graph clustering, improving performance by fusing diverse SSL features with a gating network.

Contribution

The paper proposes a dynamic weighting scheme for SSL tasks in graph clustering, utilizing a gating network and dual-level self-supervision for improved node-specific feature fusion.

Findings

DyFSS outperforms state-of-the-art methods by up to 8.66% in accuracy.

Dynamic SSL task weighting benefits attributed graph clustering.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Attributed graph clustering is an unsupervised task that partitions nodes into different groups. Self-supervised learning (SSL) shows great potential in handling this task, and some recent studies simultaneously learn multiple SSL tasks to further boost performance. Currently, different SSL tasks are assigned the same set of weights for all graph nodes. However, we observe that some graph nodes whose neighbors are in different groups require significantly different emphases on SSL tasks. In this paper, we propose to dynamically learn the weights of SSL tasks for different nodes and fuse the embeddings learned from different SSL tasks to boost performance. We design an innovative graph clustering approach, namely Dynamically Fusing Self-Supervised Learning (DyFSS). Specifically, DyFSS fuses features extracted from diverse SSL tasks using distinct weights derived from a gating network. To effectively learn the gating network, we design a dual-level self-supervised strategy that incorporates pseudo labels and the graph structure. Extensive experiments on five datasets show that DyFSS outperforms the state-of-the-art multi-task SSL methods by up to 8.66% on the accuracy metric. The code of DyFSS is available at: https://github.com/q086/DyFSS.