{"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/template-based-graph-neural-network-with","title":"Template based Graph Neural Network with Optimal Transport Distances","arxiv_id":"2205.15733","date":"2022-05-31","proceeding":null,"authors":["Cédric Vincent-Cuaz","Rémi Flamary","Marco Corneli","Titouan Vayer","Nicolas Courty"],"abstract":"Current Graph Neural Networks (GNN) architectures generally rely on two important components: node features embedding through message passing, and aggregation with a specialized form of pooling. The structural (or topological) information is implicitly taken into account in these two steps. We propose in this work a novel point of view, which places distances to some learnable graph templates at the core of the graph representation. This distance embedding is constructed thanks to an optimal transport distance: the Fused Gromov-Wasserstein (FGW) distance, which encodes simultaneously feature and structure dissimilarities by solving a soft graph-matching problem. We postulate that the vector of FGW distances to a set of template graphs has a strong discriminative power, which is then fed to a non-linear classifier for final predictions. Distance embedding can be seen as a new layer, and can leverage on existing message passing techniques to promote sensible feature representations. Interestingly enough, in our work the optimal set of template graphs is also learnt in an end-to-end fashion by differentiating through this layer. After describing the corresponding learning procedure, we empirically validate our claim on several synthetic and real life graph classification datasets, where our method is competitive or surpasses kernel and GNN state-of-the-art approaches. We complete our experiments by an ablation study and a sensitivity analysis to parameters.","url_abs":"https://arxiv.org/abs/2205.15733v1","url_pdf":"https://arxiv.org/pdf/2205.15733v1.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":"template-based-graph-neural-network-with","repo_url":"https://github.com/cedricvincentcuaz/TFGW","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-collab","task":"Graph Classification","dataset":"COLLAB","model":"TFGW ADJ (L=2)","rank_in_archive_order":2,"of":39,"metrics":{"Accuracy":"84.3%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-enzymes","task":"Graph Classification","dataset":"ENZYMES","model":"TFGW SP (L=2)","rank_in_archive_order":6,"of":54,"metrics":{"Accuracy":"75.1"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"TFGW ADJ (L=2)","rank_in_archive_order":12,"of":51,"metrics":{"Accuracy":"78.3%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-m","task":"Graph Classification","dataset":"IMDb-M","model":"TFGW ADJ (L=2)","rank_in_archive_order":2,"of":36,"metrics":{"Accuracy":"56.8%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"TFGW ADJ (L=2)","rank_in_archive_order":3,"of":74,"metrics":{"Accuracy":"96.4%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"TFGW ADJ (L=2)","rank_in_archive_order":1,"of":69,"metrics":{"Accuracy":"88.1%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"TFGW ADJ (L=2)","rank_in_archive_order":3,"of":103,"metrics":{"Accuracy":"82.9"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-ptc","task":"Graph Classification","dataset":"PTC","model":"TFGW ADJ (L=2)","rank_in_archive_order":11,"of":37,"metrics":{"Accuracy":"72.4%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.15733","atlas_url":"https://app.syntology.ai/?focus=2205.15733","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2205.15733"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.15733\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.15733"},"call":"get_concepts_for_paper(arxiv_id=\"2205.15733\")"}],"by_repo":[{"repo":"cedricvincentcuaz/TFGW","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":"811585a0743dd3a0a33b4e93ff5998f06f8d5d672bcf82177a35f2932ef51dfe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}