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.
By Yunhui Liu, Xudong Jin, Kang Zhang, Danshuo An, Yu Xing, Te Song, Jia Liu, Tieke He
The paper investigates a failure mode in Graph-JEPA, a joint‑embedding predictive model trained on a large scientific‑reasoning graph. Despite achieving high linear‑probe accuracy and effective rank, the learned representation contains almost no usable instance information, as shown by retrieval metrics. The authors diagnose the issue to variance allocation in the objective, propose a repair that restores near‑perfect information recovery, and demonstrate that the problem persists even after repair, highlighting limitations in the evaluation metrics used.
By Gollam Rabby, S\"oren Auer
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.
By Megha P, Harshit Kumar, Srajan Agarwal, Anirban Banerjee, Olaf Wolkenhauer, Saptarshi Bej
arXiv:2606. 11562v1 Announce Type: new Abstract: Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repurposing, user preference, and scientific theme are all inferred from a node together with its neighbourhood.
By Zhuoyi Peng, Jingzhou Jiang, Hanlin Gu, Lixin Fan, Yi Yang
GraphSkillAA introduces an attribution-guided skill-graph framework that organizes external skills into addressable nodes and typed edges, enabling precise selection, execution, failure attribution, and targeted updates. The system uses a Local Gate to retest affected examples and a Big Gate to evaluate the entire updated graph, rolling back any rejected changes. Experiments with GPT‑5.6‑sol show high performance on SearchQA, LiveMath, and DocVQA, demonstrating that object-level attribution and graph-scoped validation make skill graphs locally optimizable, testable, and reversible.
By Ziqiao Shang, Ling-Yue Ge, Lan-Zhe Guo
The paper introduces Schema, a generative model that recursively decomposes a single large attributed graph into a hierarchy of soft communities, assigning each node a membership distribution. Generation proceeds in three independently trained stages: synthesizing node attributes conditioned on soft memberships, generating intra-community edges from local structural context, and modeling inter-community connections via bridge nodes. Schema avoids constructing the full adjacency matrix, operates on subgraphs bounded by community size, and demonstrates superior balance between local and long-range structure while preserving downstream accuracy and scalability to graphs with up to 10 million nodes.
By Ahmet T\"uzen, Helge Langseth, Kjetil N{\o}rv{\aa}g
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.
By Guilherme Henrique Messias, Mariana Caravanti de Souza, Sylvia Iasulaitis, Alan Dem\'etrius Baria Valejo
arXiv:2502. 17614v3 Announce Type: replace Abstract: The rapid growth of graph data creates significant scalability challenges as most graph algorithms scale quadratically with size.
By Shengbo Gong, Mohammad Hashemi, Juntong Ni, Carl Yang, Wei Jin
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...
By Jinmo Lee, Dooho Lee, Minho Jeong, Jaemin Yoo
arXiv:2602.08519v2 Announce Type: replace
Abstract: Attributed Graph Clustering (AGC) is a fundamental unsupervised task that integrates structural topology and node attributes to uncover latent patt...
By Yunhui Liu, Pengyu Qiu, Yu Xing, Yongchao Liu, Peng Du, Chuntao Hong, Jiajun Zheng, Tao Zheng, Tieke He
arXiv:2609. 19210v1 Announce Type: cross Abstract: Graph neural networks are widely used for transductive node classification, with accuracy typically measured on randomly drawn train/validation/test splits.
By Naga Venkata Sai Jitin Jami, Thomas Altstidl, Sebastian Hoefler, Jonas Mueller, Dario Zanca, Bjoern Eskofier, Heike Leutheuser
SkillAA (Skill Abductive Attribution) is a structured skill‑optimization framework designed for frozen language models. It represents skill applicability, execution, and composition in a unified graph, enabling skill selection, attribution‑guided repair, and update validation within the same structure. By contrasting successful and failed executions, SkillAA routes candidate repairs to specific graph objects, updates only the selected local structure, and uses Local and Big Gates to screen candidate changes before commitment, achieving high performance on SearchQA, LiveMath, and DocVQA.
By Ziqiao Shang, Ling-Yue Ge, Lan-Zhe Guo