{"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/towards-a-general-gnn-framework-for","title":"Towards a General Recipe for Combinatorial Optimization with Multi-Filter GNNs","arxiv_id":"2405.20543","date":"2024-05-31","proceeding":null,"authors":["Frederik Wenkel","Semih Cantürk","Stefan Horoi","Michael Perlmutter","Guy Wolf"],"abstract":"Graph neural networks (GNNs) have achieved great success for a variety of tasks such as node classification, graph classification, and link prediction. However, the use of GNNs (and machine learning more generally) to solve combinatorial optimization (CO) problems is much less explored. Here, we introduce GCON, a novel GNN architecture that leverages a complex filter bank and localized attention mechanisms to solve CO problems on graphs. We show how our method differentiates itself from prior GNN-based CO solvers and how it can be effectively applied to the maximum cut, minimum dominating set, and maximum clique problems in a unsupervised learning setting. GCON is competitive across all tasks and consistently outperforms other specialized GNN-based approaches, and is on par with the powerful Gurobi solver on the max-cut problem. We provide an open-source implementation of our work at https://github.com/WenkelF/copt.","url_abs":"https://arxiv.org/abs/2405.20543v2","url_pdf":"https://arxiv.org/pdf/2405.20543v2.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":"towards-a-general-gnn-framework-for","repo_url":"https://github.com/wenkelf/copt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.20543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20543"}},"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/wenkelf/copt","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":6},"by_repo_kind":{"official":{"samples":13,"ran":7,"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":13,"samples":[{"code_sha256_prefix":"d67f3603be7d0949","entry":"entropy","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/loss/copt_loss.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/loss/copt_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d67f3603be7d0949"}},{"code_sha256_prefix":"1bb331bf70a78136","entry":"get_final_pretrained_ckpt","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/finetuning.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/finetuning.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1bb331bf70a78136"}},{"code_sha256_prefix":"f22df9b4f0f5f694","entry":"get_fname","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/configs_gen.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/configs_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f22df9b4f0f5f694"}},{"code_sha256_prefix":"6332aa743c0222b4","entry":"grid2list","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/configs_gen.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/configs_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6332aa743c0222b4"}},{"code_sha256_prefix":"9a4410b8a6c0cc47","entry":"init_model_from_pretrained","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/finetuning.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/finetuning.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a4410b8a6c0cc47"}},{"code_sha256_prefix":"7cb44d22cd9be697","entry":"lists_distance","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/configs_gen.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/configs_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7cb44d22cd9be697"}},{"code_sha256_prefix":"a9bc3a63c5e0c6c6","entry":"maxclique_loss_pyg","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/loss/copt_loss.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/loss/copt_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9bc3a63c5e0c6c6"}},{"code_sha256_prefix":"ae56bcfaae96da3c","entry":"apply_chunking_to_forward","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/layer/bigbird_layer.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/layer/bigbird_layer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae56bcfaae96da3c"}},{"code_sha256_prefix":"c98a702be0660ac9","entry":"is_seed","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/agg_runs.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/agg_runs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c98a702be0660ac9"}},{"code_sha256_prefix":"438635c08adfe2aa","entry":"is_split","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/agg_runs.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/agg_runs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"438635c08adfe2aa"}},{"code_sha256_prefix":"40e98e1ecbf39f34","entry":"join_list","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/agg_runs.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/agg_runs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"40e98e1ecbf39f34"}},{"code_sha256_prefix":"91c1f5bb90bbe0f3","entry":"load_pretrained_model_cfg","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/finetuning.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/finetuning.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91c1f5bb90bbe0f3"}},{"code_sha256_prefix":"236b080d75c5e46d","entry":"maxclique_loss","repo":"wenkelf/copt","repo_kind":"official","path":"graphgym/loss/copt_loss.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/loss/copt_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"236b080d75c5e46d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}