{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/faster-inference-time-for-gnns-using","title":"FIT-GNN: Faster Inference Time for GNNs Using Coarsening","arxiv_id":"2410.15001","date":"2024-10-19","proceeding":null,"authors":["Shubhajit Roy","Hrriday Ruparel","Kishan Ved","Anirban Dasgupta"],"abstract":"Scalability of Graph Neural Networks (GNNs) remains a significant challenge, particularly when dealing with large-scale graphs. To tackle this, coarsening-based methods are used to reduce the graph into 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 both training and inference phases. We demonstrate two different methods (Extra-Nodes and Cluster-Nodes). Our study also proposes a unique application of the coarsening algorithm for graph-level tasks, including graph classification and graph regression, which have not yet been explored. We conduct extensive experiments on multiple benchmark datasets in the order of $100K$ nodes to evaluate the performance of our approach. The results demonstrate that our method achieves competitive performance in tasks involving classification and regression on nodes and graphs, compared to traditional GNNs, while having single-node inference times that are orders of magnitude faster. Furthermore, our approach significantly reduces memory consumption, allowing training and inference on low-resource devices where traditional methods struggle.","url_abs":"https://arxiv.org/abs/2410.15001v2","url_pdf":"https://arxiv.org/pdf/2410.15001v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"faster-inference-time-for-gnns-using","repo_url":"https://github.com/Roy-Shubhajit/FIT-GNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-regression","task_name":"Node Regression"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-aids","task":"Graph Classification","dataset":"AIDS","model":"FIT-GNN","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"84.3","Inference Time (ms)":"0.00155"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"FIT-GNN","rank_in_archive_order":5,"of":103,"metrics":{"Accuracy":"82.1","Inference Time (ms)":"0.0016"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-qm9","task":"Graph Regression","dataset":"QM9","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Inference Time (ms)":"0.0018"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-qm9-uatom","task":"Graph Regression","dataset":"QM9: UATOM","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"MAE":"0.63"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-qm9-zpve","task":"Graph Regression","dataset":"QM9: ZPVE","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"MAE":"0.818"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-qm9-del-e","task":"Graph Regression","dataset":"QM9: del e","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"MAE":"0.875"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-qm9-mu","task":"Graph Regression","dataset":"QM9: mu","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"MAE":"0.841"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-10k","task":"Graph Regression","dataset":"ZINC 10k","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Inference Time (ms)":"0.00184","MAE":"0.578"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-5-nodes-per","task":"Node Classification","dataset":"CiteSeer: 5 nodes per class","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"FIT-GNN","rank_in_archive_order":71,"of":71,"metrics":{"Inference Time (ms)":"0.0018"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-cs","task":"Node Classification","dataset":"Coauthor CS","model":"FIT-GNN","rank_in_archive_order":24,"of":24,"metrics":{"Inference Time (ms)":"0.0017"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"FIT-GNN","rank_in_archive_order":48,"of":73,"metrics":{"Accuracy":"82.9%","Inference Time (ms)":"0.0019"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-5-nodes-per-class","task":"Node Classification","dataset":"Cora: 5 nodes per class","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"72.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dblp","task":"Node Classification","dataset":"DBLP","model":"FIT-GNN","rank_in_archive_order":6,"of":6,"metrics":{"Inference Time (ms)":"0.0018"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dblp-20-nodes-per","task":"Node Classification","dataset":"DBLP: 20 nodes per class","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"0.789"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dblp-5-nodes-per-class","task":"Node Classification","dataset":"DBLP: 5 nodes per class","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"68.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-5-nodes-per","task":"Node Classification","dataset":"PubMed: 5 nodes per class","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"67.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"FIT-GNN","rank_in_archive_order":70,"of":70,"metrics":{"Inference Time (ms)":"0.0018"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-ogbn-products","task":"Node Classification","dataset":"ogbn-products","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Inference Time (ms)":"0.0016"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-ogbn-products-20-nodes","task":"Node Classification","dataset":"ogbn-products: 20 nodes per class","model":"FIT-GNN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"0.406"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"Roy-Shubhajit/FIT-GNN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9a1e9d8034874e32fff269a0b1b8aae0b365f74f5588af22a9af3ebda6a2bb6c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}