{"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/ckgconv-general-graph-convolution-with","title":"CKGConv: General Graph Convolution with Continuous Kernels","arxiv_id":"2404.13604","date":"2024-04-21","proceeding":null,"authors":["Liheng Ma","Soumyasundar Pal","Yitian Zhang","Jiaming Zhou","Yingxue Zhang","Mark Coates"],"abstract":"The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a general convolution operator in the graph domain is challenging due to the lack of canonical coordinates, the presence of irregular structures, and the properties of graph symmetries. In this work, we propose a novel and general graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel Graph Convolution (CKGConv). Theoretically, we demonstrate that CKGConv is flexible and expressive. CKGConv encompasses many existing graph convolutions, and exhibits a stronger expressiveness, as powerful as graph transformers in terms of distinguishing non-isomorphic graphs. Empirically, we show that CKGConv-based Networks outperform existing graph convolutional networks and perform comparably to the best graph transformers across a variety of graph datasets. The code and models are publicly available at https://github.com/networkslab/CKGConv.","url_abs":"https://arxiv.org/abs/2404.13604v2","url_pdf":"https://arxiv.org/pdf/2404.13604v2.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":"ckgconv-general-graph-convolution-with","repo_url":"https://github.com/networkslab/ckgconv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-cifar-10","task":"Graph Classification","dataset":"CIFAR-10","model":"CKGCN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"72.785"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mnist","task":"Graph Classification","dataset":"MNIST","model":"CKGCN","rank_in_archive_order":5,"of":13,"metrics":{"Accuracy":"98.423"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-peptides-func","task":"Graph Classification","dataset":"Peptides-func","model":"CKGCN","rank_in_archive_order":15,"of":44,"metrics":{"AP":"0.6952"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-peptides-struct","task":"Graph Regression","dataset":"Peptides-struct","model":"CKGCN","rank_in_archive_order":17,"of":39,"metrics":{"MAE":"0.2477"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc","task":"Graph Regression","dataset":"ZINC","model":"CKGCN","rank_in_archive_order":6,"of":27,"metrics":{"MAE":"0.059"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-500k","task":"Graph Regression","dataset":"ZINC-500k","model":"CKGCN","rank_in_archive_order":36,"of":36,"metrics":{"MAE":"5.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cluster","task":"Node Classification","dataset":"CLUSTER","model":"CKGCN","rank_in_archive_order":4,"of":12,"metrics":{"Accuracy":"79.003"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pattern","task":"Node Classification","dataset":"PATTERN","model":"CKGCN","rank_in_archive_order":1,"of":11,"metrics":{"Accuracy":"88.661"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.13604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13604"}},"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":"deterministic:regex_extraction","url":"https://github.com/networkslab/CKGConv","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/networkslab/ckgconv","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":11,"samples":[{"code_sha256_prefix":"ecf14287d3465c48","entry":"accuracy_SBM","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/logger.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/logger.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":"ecf14287d3465c48"}},{"code_sha256_prefix":"9dc78001d467fc9d","entry":"eval_spearmanr","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/logger.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/logger.py","link_basis":"harvester_set","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":"9dc78001d467fc9d"}},{"code_sha256_prefix":"1bb331bf70a78136","entry":"get_final_pretrained_ckpt","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/finetuning.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/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":"b5c9e7acf599a98a","entry":"get_log_deg","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/layer/ckgconv_layer.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/layer/ckgconv_layer.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":"b5c9e7acf599a98a"}},{"code_sha256_prefix":"ef96c45530e5a76b","entry":"get_sqrt_deg","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/layer/ckgconv_layer.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/layer/ckgconv_layer.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":"ef96c45530e5a76b"}},{"code_sha256_prefix":"309b367fdc9f4994","entry":"init_model_from_pretrained","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/finetuning.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/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":"309b367fdc9f4994"}},{"code_sha256_prefix":"bdfc097c2a07782f","entry":"load_pretrained_model_cfg","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/finetuning.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/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":"bdfc097c2a07782f"}},{"code_sha256_prefix":"47e492109e6d308f","entry":"subtoken_cross_entropy","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/loss/subtoken_prediction_loss.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/loss/subtoken_prediction_loss.py","link_basis":"plan_row","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":"47e492109e6d308f"}},{"code_sha256_prefix":"dc82c18c9d42c1c1","entry":"adj_l1_losses","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/loss/adj.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/loss/adj.py","link_basis":"plan_row","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":"dc82c18c9d42c1c1"}},{"code_sha256_prefix":"d59c374db2cf64ae","entry":"l1_losses","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/loss/l1.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/loss/l1.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":"d59c374db2cf64ae"}},{"code_sha256_prefix":"f1cbbbc857d8b871","entry":"multilabel_cross_entropy","repo":"networkslab/CKGConv","repo_kind":"official","path":"ckgconv/loss/multilabel_classification_loss.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/loss/multilabel_classification_loss.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":"f1cbbbc857d8b871"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}