{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/wasserstein-weisfeiler-lehman-graph-kernels","title":"Wasserstein Weisfeiler-Lehman Graph Kernels","arxiv_id":"1906.01277","date":"2019-06-04","proceeding":"NeurIPS 2019 12","authors":["Matteo Togninalli","Elisabetta Ghisu","Felipe Llinares-López","Bastian Rieck","Karsten Borgwardt"],"abstract":"Most graph kernels are an instance of the class of $\\mathcal{R}$-Convolution kernels, which measure the similarity of objects by comparing their substructures. Despite their empirical success, most graph kernels use a naive aggregation of the final set of substructures, usually a sum or average, thereby potentially discarding valuable information about the distribution of individual components. Furthermore, only a limited instance of these approaches can be extended to continuously attributed graphs. We propose a novel method that relies on the Wasserstein distance between the node feature vector distributions of two graphs, which allows to find subtler differences in data sets by considering graphs as high-dimensional objects, rather than simple means. We further propose a Weisfeiler-Lehman inspired embedding scheme for graphs with continuous node attributes and weighted edges, enhance it with the computed Wasserstein distance, and thus improve the state-of-the-art prediction performance on several graph classification tasks.","url_abs":"https://arxiv.org/abs/1906.01277v2","url_pdf":"https://arxiv.org/pdf/1906.01277v2.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":"wasserstein-weisfeiler-lehman-graph-kernels","repo_url":"https://github.com/BorgwardtLab/WWL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"wasserstein-weisfeiler-lehman-graph-kernels","repo_url":"https://github.com/wenbintum/wwl-gpr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"WWL","rank_in_archive_order":16,"of":53,"metrics":{"Accuracy":"79.69%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-enzymes","task":"Graph Classification","dataset":"ENZYMES","model":"WWL","rank_in_archive_order":31,"of":54,"metrics":{"Accuracy":"59.13%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"WWL","rank_in_archive_order":48,"of":74,"metrics":{"Accuracy":"87.27%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"WWL","rank_in_archive_order":8,"of":69,"metrics":{"Accuracy":"85.75%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"WWL","rank_in_archive_order":80,"of":103,"metrics":{"Accuracy":"74.28%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-ptc","task":"Graph Classification","dataset":"PTC","model":"WWL","rank_in_archive_order":18,"of":37,"metrics":{"Accuracy":"66.31%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.01277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01277"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wenbintum/wwl-gpr","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BorgwardtLab/WWL","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1},"listed":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"62b399837d7b060b","entry":"ActiveSiteIndex","repo":"wenbintum/wwl-gpr","repo_kind":"listed","path":"wwlgpr/Utility.py","file_url":"https://github.com/wenbintum/wwl-gpr/blob/HEAD/wwlgpr/Utility.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62b399837d7b060b"}},{"code_sha256_prefix":"0098868d2b7d06f2","entry":"R_conv_attributes","repo":"wenbintum/wwl-gpr","repo_kind":"listed","path":"wwlgpr/WWL_GPR.py","file_url":"https://github.com/wenbintum/wwl-gpr/blob/HEAD/wwlgpr/WWL_GPR.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0098868d2b7d06f2"}},{"code_sha256_prefix":"ba303ab69efaf9ca","entry":"cal_node_weights","repo":"wenbintum/wwl-gpr","repo_kind":"listed","path":"wwlgpr/Utility.py","file_url":"https://github.com/wenbintum/wwl-gpr/blob/HEAD/wwlgpr/Utility.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba303ab69efaf9ca"}},{"code_sha256_prefix":"f0bdc08b57eafabf","entry":"compute_wasserstein_distance","repo":"BorgwardtLab/WWL","repo_kind":"official","path":"experiments/wwl.py","file_url":"https://github.com/BorgwardtLab/WWL/blob/HEAD/experiments/wwl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f0bdc08b57eafabf"}},{"code_sha256_prefix":"008f645125a4df09","entry":"multiprocessing_WD","repo":"wenbintum/wwl-gpr","repo_kind":"listed","path":"wwlgpr/Utility.py","file_url":"https://github.com/wenbintum/wwl-gpr/blob/HEAD/wwlgpr/Utility.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"008f645125a4df09"}},{"code_sha256_prefix":"f8ef354516fa701c","entry":"pairwise_wasserstein_distance","repo":"BorgwardtLab/WWL","repo_kind":"official","path":"src/wwl/wwl.py","file_url":"https://github.com/BorgwardtLab/WWL/blob/HEAD/src/wwl/wwl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f8ef354516fa701c"}},{"code_sha256_prefix":"2e18ef039fb12dd4","entry":"read_gml","repo":"BorgwardtLab/WWL","repo_kind":"official","path":"experiments/utilities.py","file_url":"https://github.com/BorgwardtLab/WWL/blob/HEAD/experiments/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2e18ef039fb12dd4"}},{"code_sha256_prefix":"72df551d8c4af0e4","entry":"read_labels","repo":"BorgwardtLab/WWL","repo_kind":"official","path":"experiments/utilities.py","file_url":"https://github.com/BorgwardtLab/WWL/blob/HEAD/experiments/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"72df551d8c4af0e4"}},{"code_sha256_prefix":"f057079b9895ba72","entry":"retrieve_graph_filenames","repo":"BorgwardtLab/WWL","repo_kind":"official","path":"src/wwl/utilities.py","file_url":"https://github.com/BorgwardtLab/WWL/blob/HEAD/src/wwl/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f057079b9895ba72"}},{"code_sha256_prefix":"da6828d3a76384fd","entry":"wwl","repo":"BorgwardtLab/WWL","repo_kind":"official","path":"src/wwl/wwl.py","file_url":"https://github.com/BorgwardtLab/WWL/blob/HEAD/src/wwl/wwl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"da6828d3a76384fd"}},{"code_sha256_prefix":"d889f576e7f6730e","entry":"wwl_custom_grid_search_cv","repo":"BorgwardtLab/WWL","repo_kind":"official","path":"src/wwl/utilities.py","file_url":"https://github.com/BorgwardtLab/WWL/blob/HEAD/src/wwl/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d889f576e7f6730e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}