The paper introduces OFAG, a foundation model designed for attributed graph clustering that can be trained once and applied to diverse graphs without graph‑specific tuning. It learns a reusable clustering strategy from synthetic graphs and uses a dimension‑agnostic encoder to handle varying feature spaces, producing clustering‑friendly node representations in a single forward pass. Across ten datasets, a frozen OFAG model outperforms baselines in both speed and clustering quality, and the authors provide code and pretrained checkpoints for easy adoption.
arXiv:2606. 17667v1 Announce Type: cross Abstract: In recent years, the rapid development of foundation models and graph pre-training technologies has spurred increasing interest in constructing a universal pre-trained graph model or Graph Foundation Model (GFM).
The paper introduces Inductive Correlation Clustering, a new framework that uses Graph Neural Networks to solve the Correlation Clustering problem on unseen graph instances. By learning common structural patterns and node features, the method generalizes to new graphs with minimal computational overhead, achieving inference times up to five orders of magnitude faster while maintaining an approximation ratio within about 10% of the best baseline. It also demonstrates competitive performance on standard transductive benchmarks and serves as an efficient learnable pooling layer for graph classification tasks.
arXiv:2607. 17272v1 Announce Type: new Abstract: Node representation learning has advanced rapidly, yet most existing methods rely on per-dataset training and hyperparameter tuning.
The paper introduces Selective Hypergraph Refinement (SHR), a post‑processing technique for frozen graph clustering models that does not alter model parameters, node representations, or the original graph. SHR uses an attribute hypergraph to generate candidate refinement directions and selectively updates only nodes with sufficient support, preserving the majority of original assignments. Experiments on 15 backbone‑dataset combinations show modest macro gains (up to 0.137 pp) with very few hard assignment changes, indicating a limited but measurable refinement space after training.
arXiv:2607. 19128v1 Announce Type: new Abstract: Vision-language models (VLMs) provide a unified representation space for textual and visual information, yet their potential as general-purpose backbones for graph-structured data remains largely unexplored.
SynCo is a synthetic graph generator that lets users control node degree distributions and sub‑community structures, addressing limitations of existing generators that rely on power‑law distributions and lack flexibility. It is evaluated on graph mimicking, hyperparameter tuning, and node clustering, outperforming state‑of‑the‑art methods while preserving original data distributions. SynCo can generate large graphs with up to 2.1 million nodes.
HyperFuse is a new, label‑free pipeline for fast self‑supervised node embeddings on attributed hypergraphs. It computes structural node coordinates via a spectral relaxation of hypergraph modularity, builds multi‑scale feature summaries with utility‑weighted hyperedges, and trains a lightweight encoder for only 100 epochs. In experiments on nine public hypergraphs, HyperFuse achieved 13–179× speed‑ups over baselines and matched or exceeded their accuracy on most downstream tasks.
arXiv:2609.37057v1 Announce Type: new Abstract: Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeat...
arXiv:2607. 11374v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains.
arXiv:2609.39673v1 Announce Type: new Abstract: Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality a...
Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains. Recent advancements in GFMs have been largely dominated by two paradigms: Graph Neural Network and Large Language Model (LLM) based methods.
arXiv:2509. 21489v4 Announce Type: replace Abstract: Graph foundation models face several fundamental challenges including transferability across diverse domains and data scarcity, which calls into question the very feasibility of creating such models.