Towards One-for-All Foundation Model for Attributed Graph Clustering

Key points

• In this paper, we study a one-for-all alternative: can a single model be trained once and directly applied to diverse attributed graphs without graph-specific training, fine-tuning, or hyperparameter search?1
• We propose OFAG, a foundation model for attributed graph clustering.1
• Building upon Prior-data Fitted Networks, OFAG learns a reusable clustering inference strategy from synthetic attributed graphs generated under broad priors over latent clusters, node attributes, and graph structures.1
• To handle incompatible feature spaces across graphs, OFAG adopts a dimension-agnostic signal-wise graph encoder that treats each feature channel as a graph signal and models its response to shared graph filters.1

Sources (1)

• [1]Towards One-for-All Foundation Model for Attributed Graph Clustering
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:13 AM

  Attributed graph clustering aims to discover node groups by jointly exploiting node attributes and graph topology, yet its unsupervised nature makes model selection and adaptation inherently difficult.

  In this paper, we study a one-for-all alternative: can a single model be trained once and directly applied to diverse attributed graphs without graph-specific training, fine-tuning, or hyperparameter search?

Extractive summary: sentences quoted from the sources.