Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering
This work addresses the challenge of improving clustering accuracy in attributed graphs for unsupervised learning applications, representing an incremental advance by refining multi-task self-supervised learning with node-specific weighting.
The paper tackles the problem of attributed graph clustering by proposing a method that dynamically assigns different weights to self-supervised learning tasks for each node, based on their local graph structure, resulting in up to 8.66% accuracy improvement over state-of-the-art methods on five datasets.
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.