FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening

[2410.15001] FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2410.15001 (cs) [Submitted on 19 Oct 2024 ( v1 ), last revised 10 Apr 2026 (this version, v5)] Title: FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening Authors: Shubhajit Roy , Hrriday Ruparel , Kishan Ved , Anirban Dasgupta View a PDF of the paper titled FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening, by Shubhajit Roy and 3 other authors View PDF HTML (experimental) Abstract: Scalability of Graph Neural Networks (GNNs) remains a significant challenge. To tackle this, methods like coarsening, condensation, and computation trees are used to train on a smaller graph, resulting in faster computation. Nonetheless, prior research has not adequately addressed the computational costs during the inference phase. This paper presents a novel approach to improve the scalability of GNNs by reducing computational burden during the inference phase using graph coarsening. We demonstrate two different methods -- Extra Nodes and Cluster Nodes. Our study extends the application of graph coarsening for graph-level tasks, including graph classification and graph regression. We conduct extensive experiments on multiple benchmark datasets to evaluate the performance of our approach. Our results show that the proposed method achieves orders of magnitude improvements in single-node inference time compared to traditional approaches. Furthermore, it significantly reduces memory consumption for node and graph classification and regression tasks, enabling efficient training and inference on low-resource devices where conventional methods are impractical. Notably, these computational advantages are achieved while maintaining competitive performance relative to baseline models. Comments: Published in Transactions on Machine Learning Research (TMLR), 2026. Available at this https URL Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML) Cite as: arXiv:2410.15001 [cs.LG] (or arXiv:2410.15001v5 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2410.15001 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Trans.Mach.Learn.Res.(2026) Submission history From: Shubhajit Roy [ view email ] [v1] Sat, 19 Oct 2024 06:27:24 UTC (2,830 KB) [v2] Fri, 24 Jan 2025 20:45:33 UTC (236 KB) [v3] Sun, 31 Aug 2025 12:17:32 UTC (354 KB) [v4] Sat, 6 Dec 2025 18:04:32 UTC (1,812 KB) [v5] Fri, 10 Apr 2026 10:07:06 UTC (1,938 KB) Full-text links: Access Paper: View a PDF of the paper titled FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening, by Shubhajit Roy and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2024-10 Change to browse by: cs stat stat.ML 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

• Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance#1050870
• Split CNN Inference on Networked Microcontrollers#175217
• Provably Lossless Acceleration of DNN Mutation Testing via Memoization#386936
• How to Achieve the Intended Aim of Deep Clustering Now, without Deep Learning#670483
• How to Achieve the Intended Aim of Deep Clustering Now, without Deep Learning#668418