{"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/going-deeper-into-permutation-sensitive-graph","title":"Going Deeper into Permutation-Sensitive Graph Neural Networks","arxiv_id":"2205.14368","date":"2022-05-28","proceeding":null,"authors":["Zhongyu Huang","Yingheng Wang","Chaozhuo Li","Huiguang He"],"abstract":"The invariance to permutations of the adjacency matrix, i.e., graph isomorphism, is an overarching requirement for Graph Neural Networks (GNNs). Conventionally, this prerequisite can be satisfied by the invariant operations over node permutations when aggregating messages. However, such an invariant manner may ignore the relationships among neighboring nodes, thereby hindering the expressivity of GNNs. In this work, we devise an efficient permutation-sensitive aggregation mechanism via permutation groups, capturing pairwise correlations between neighboring nodes. We prove that our approach is strictly more powerful than the 2-dimensional Weisfeiler-Lehman (2-WL) graph isomorphism test and not less powerful than the 3-WL test. Moreover, we prove that our approach achieves the linear sampling complexity. Comprehensive experiments on multiple synthetic and real-world datasets demonstrate the superiority of our model.","url_abs":"https://arxiv.org/abs/2205.14368v1","url_pdf":"https://arxiv.org/pdf/2205.14368v1.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":"going-deeper-into-permutation-sensitive-graph","repo_url":"https://github.com/zhongyu1998/pg-gnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.14368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14368"}},"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/zhongyu1998/pg-gnn","reach":null}],"summary":{"ran":1,"ran_honours":6,"unverified":1},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"accd56c29438f92b","entry":"GroupCNN","repo":"zhongyu1998/pg-gnn","repo_kind":"official","path":"models/groupcnn.py","file_url":"https://github.com/zhongyu1998/pg-gnn/blob/HEAD/models/groupcnn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"accd56c29438f92b"}},{"code_sha256_prefix":"39a3193be1fde526","entry":"evaluate","repo":"zhongyu1998/pg-gnn","repo_kind":"official","path":"main_synthetic.py","file_url":"https://github.com/zhongyu1998/pg-gnn/blob/HEAD/main_synthetic.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39a3193be1fde526"}},{"code_sha256_prefix":"9cc50aedc9f2d22d","entry":"evaluate","repo":"zhongyu1998/pg-gnn","repo_kind":"official","path":"main_tu.py","file_url":"https://github.com/zhongyu1998/pg-gnn/blob/HEAD/main_tu.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9cc50aedc9f2d22d"}},{"code_sha256_prefix":"48c872a66853c858","entry":"evaluate","repo":"zhongyu1998/pg-gnn","repo_kind":"official","path":"main_benchmark.py","file_url":"https://github.com/zhongyu1998/pg-gnn/blob/HEAD/main_benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48c872a66853c858"}},{"code_sha256_prefix":"9aecb71a3ef0407b","entry":"pass_data_iteratively","repo":"zhongyu1998/pg-gnn","repo_kind":"official","path":"main_synthetic.py","file_url":"https://github.com/zhongyu1998/pg-gnn/blob/HEAD/main_synthetic.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9aecb71a3ef0407b"}},{"code_sha256_prefix":"f7d60c6f40ddeb9d","entry":"train","repo":"zhongyu1998/pg-gnn","repo_kind":"official","path":"main_tu.py","file_url":"https://github.com/zhongyu1998/pg-gnn/blob/HEAD/main_tu.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7d60c6f40ddeb9d"}},{"code_sha256_prefix":"bfb9980d1fbf755d","entry":"train","repo":"zhongyu1998/pg-gnn","repo_kind":"official","path":"main_benchmark.py","file_url":"https://github.com/zhongyu1998/pg-gnn/blob/HEAD/main_benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfb9980d1fbf755d"}},{"code_sha256_prefix":"4b30cac230232396","entry":"train","repo":"zhongyu1998/pg-gnn","repo_kind":"official","path":"main_synthetic.py","file_url":"https://github.com/zhongyu1998/pg-gnn/blob/HEAD/main_synthetic.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":"4b30cac230232396"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}