{"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/from-relational-pooling-to-subgraph-gnns-a","title":"From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks","arxiv_id":"2305.04963","date":"2023-05-08","proceeding":null,"authors":["Cai Zhou","Xiyuan Wang","Muhan Zhang"],"abstract":"Relational pooling is a framework for building more expressive and permutation-invariant graph neural networks. However, there is limited understanding of the exact enhancement in the expressivity of RP and its connection with the Weisfeiler Lehman hierarchy. Starting from RP, we propose to explicitly assign labels to nodes as additional features to improve expressive power of message passing neural networks. The method is then extended to higher dimensional WL, leading to a novel $k,l$-WL algorithm, a more general framework than $k$-WL. Theoretically, we analyze the expressivity of $k,l$-WL with respect to $k$ and $l$ and unifies it with a great number of subgraph GNNs. Complexity reduction methods are also systematically discussed to build powerful and practical $k,l$-GNN instances. We theoretically and experimentally prove that our method is universally compatible and capable of improving the expressivity of any base GNN model. Our $k,l$-GNNs achieve superior performance on many synthetic and real-world datasets, which verifies the effectiveness of our framework.","url_abs":"https://arxiv.org/abs/2305.04963v1","url_pdf":"https://arxiv.org/pdf/2305.04963v1.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":"from-relational-pooling-to-subgraph-gnns-a","repo_url":"https://github.com/zhouc20/KLGNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.04963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04963"}},"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/zhouc20/KLGNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"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":"8134b52cd16bee5c","entry":"cumsum_pad0","repo":"zhouc20/KLGNN","repo_kind":"official","path":"OGB/util.py","file_url":"https://github.com/zhouc20/KLGNN/blob/HEAD/OGB/util.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8134b52cd16bee5c"}},{"code_sha256_prefix":"42519ba0adc90b40","entry":"deg2rowptr","repo":"zhouc20/KLGNN","repo_kind":"official","path":"OGB/util.py","file_url":"https://github.com/zhouc20/KLGNN/blob/HEAD/OGB/util.py","link_basis":"first_harvest_node","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":"42519ba0adc90b40"}},{"code_sha256_prefix":"fa0f06a122a1bfe6","entry":"extractsubg","repo":"zhouc20/KLGNN","repo_kind":"official","path":"OGB/preprocess.py","file_url":"https://github.com/zhouc20/KLGNN/blob/HEAD/OGB/preprocess.py","link_basis":"first_harvest_node","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":"fa0f06a122a1bfe6"}},{"code_sha256_prefix":"353bd683adeed414","entry":"extracttuple","repo":"zhouc20/KLGNN","repo_kind":"official","path":"OGB/util.py","file_url":"https://github.com/zhouc20/KLGNN/blob/HEAD/OGB/util.py","link_basis":"first_harvest_node","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":"353bd683adeed414"}},{"code_sha256_prefix":"d5bc45a4bfa5fab3","entry":"indexbmm","repo":"zhouc20/KLGNN","repo_kind":"official","path":"OGB/IDMPNN_Global.py","file_url":"https://github.com/zhouc20/KLGNN/blob/HEAD/OGB/IDMPNN_Global.py","link_basis":"first_harvest_node","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":"d5bc45a4bfa5fab3"}},{"code_sha256_prefix":"4825f61c1afb6cbb","entry":"noindexbmm","repo":"zhouc20/KLGNN","repo_kind":"official","path":"OGB/IDMPNN_Global.py","file_url":"https://github.com/zhouc20/KLGNN/blob/HEAD/OGB/IDMPNN_Global.py","link_basis":"first_harvest_node","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":"4825f61c1afb6cbb"}},{"code_sha256_prefix":"0d541a5bec4a4c53","entry":"to_dense_batch","repo":"zhouc20/KLGNN","repo_kind":"official","path":"QM9/IDPPGN.py","file_url":"https://github.com/zhouc20/KLGNN/blob/HEAD/QM9/IDPPGN.py","link_basis":"first_harvest_node","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":"0d541a5bec4a4c53"}},{"code_sha256_prefix":"bc15613c664952e7","entry":"train","repo":"zhouc20/KLGNN","repo_kind":"official","path":"OGB/molhiv.py","file_url":"https://github.com/zhouc20/KLGNN/blob/HEAD/OGB/molhiv.py","link_basis":"first_harvest_node","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":"bc15613c664952e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}