{"ID":2894559,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.11710","arxiv_id":"2507.11710","title":"Subgraph Generation for Generalizing on Out-of-Distribution Links","abstract":"Graphs Neural Networks (GNNs) demonstrate high-performance on the link prediction (LP) task. However, these models often rely on all dataset samples being drawn from the same distribution. In addition, graph generative models (GGMs) show a pronounced ability to generate novel output graphs. Despite this, GGM applications remain largely limited to domain-specific tasks. To bridge this gap, we propose FLEX as a GGM framework which leverages two mechanism: (1) structurally-conditioned graph generation, and (2) adversarial co-training between an auto-encoder and GNN. As such, FLEX ensures structural-alignment between sample distributions to enhance link-prediction performance in out-of-distribution (OOD) scenarios. Notably, FLEX does not require expert knowledge to function in different OOD scenarios. Numerous experiments are conducted in synthetic and real-world OOD settings to demonstrate FLEX's performance-enhancing ability, with further analysis for understanding the effects of graph data augmentation on link structures. The source code is available here: https://github.com/revolins/FlexOOD.","short_abstract":"Graphs Neural Networks (GNNs) demonstrate high-performance on the link prediction (LP) task. However, these models often rely on all dataset samples being drawn from the same distribution. In addition, graph generative models (GGMs) show a pronounced ability to generate novel output graphs. Despite this, GGM applicatio...","url_abs":"https://arxiv.org/abs/2507.11710","url_pdf":"https://arxiv.org/pdf/2507.11710v1","authors":"[\"Jay Revolinsky\",\"Harry Shomer\",\"Jiliang Tang\"]","published":"2025-07-15T20:30:16Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Graph Neural Network\"]","has_code":false,"code_links":[{"ID":612114,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2894559,"paper_url":"https://arxiv.org/abs/2507.11710","paper_title":"Subgraph Generation for Generalizing on Out-of-Distribution Links","repo_url":"https://github.com/revolins/FlexOOD","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}