Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks

[2608.14823] Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14823 (cs) [Submitted on 14 Aug 2026] Title: Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks Authors: Preben M. Ness , Fariz Ikhwantri , Dusica Marijan View a PDF of the paper titled Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks, by Preben M. Ness and 2 other authors View PDF HTML (experimental) Abstract: Are heterophilic nodes in a graph harder to classify because they are heterophilic or because they are rare? Some existing work frames classification of such nodes as a subgroup generalisation problem, where a model performs well on the majority group at the expense of the rare group. Others explain this as a problem of neighbourhood aggregation in graph neural networks (GNNs). We assess these two viewpoints through a detailed evaluation of six GNNs on five datasets of varying homophily, and find that homophilic nodes tend to be easier to classify, even when they are rare---challenging the subgroup framing. However, our findings also nuance existing beliefs about how GNNs misrepresent heterophilic nodes. We demonstrate that the information needed to classify heterophilic nodes correctly is often recoverable by retraining the classification head of a model, or even just the final linear classification layer. Comments: 9 pages of main text, 33 pages total, 11 figures, 17 tables Subjects: Machine Learning (cs.LG) Cite as: arXiv:2608.14823 [cs.LG] (or arXiv:2608.14823v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14823 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Fariz Ikhwantri [ view email ] [v1] Fri, 14 Aug 2026 18:52:32 UTC (983 KB) Full-text links: Access Paper: View a PDF of the paper titled Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks, by Preben M. Ness and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Relevant Walk Search for Explaining Graph Neural Networks#222597
• Structural Negative Transfer in Federated Graph Neural Networks: Diagnosis, Causal Investigation, and the Limits of Divergence-Aware Mitigation#1123385
• Structural Negative Transfer in Federated Graph Neural Networks: Diagnosis, Causal Investigation, and the Limits of Divergence-Aware Mitigation#919330
• MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning#927850
• Let the Neurons Die: Exploiting ReLU-Induced Model Degradation#1130109