{"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/breaking-the-limit-of-graph-neural-networks","title":"Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns","arxiv_id":"2106.06586","date":"2021-06-11","proceeding":null,"authors":["Susheel Suresh","Vinith Budde","Jennifer Neville","Pan Li","Jianzhu Ma"],"abstract":"Graph neural networks (GNNs) have achieved tremendous success on multiple graph-based learning tasks by fusing network structure and node features. Modern GNN models are built upon iterative aggregation of neighbor's/proximity features by message passing. Its prediction performance has been shown to be strongly bounded by assortative mixing in the graph, a key property wherein nodes with similar attributes mix/connect with each other. We observe that real world networks exhibit heterogeneous or diverse mixing patterns and the conventional global measurement of assortativity, such as global assortativity coefficient, may not be a representative statistic in quantifying this mixing. We adopt a generalized concept, node-level assortativity, one that is based at the node level to better represent the diverse patterns and accurately quantify the learnability of GNNs. We find that the prediction performance of a wide range of GNN models is highly correlated with the node level assortativity. To break this limit, in this work, we focus on transforming the input graph into a computation graph which contains both proximity and structural information as distinct type of edges. The resulted multi-relational graph has an enhanced level of assortativity and, more importantly, preserves rich information from the original graph. We then propose to run GNNs on this computation graph and show that adaptively choosing between structure and proximity leads to improved performance under diverse mixing. Empirically, we show the benefits of adopting our transformation framework for semi-supervised node classification task on a variety of real world graph learning benchmarks.","url_abs":"https://arxiv.org/abs/2106.06586v1","url_pdf":"https://arxiv.org/pdf/2106.06586v1.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":"breaking-the-limit-of-graph-neural-networks","repo_url":"https://github.com/susheels/gnns-and-local-assortativity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-classification-on-non-homophilic","task_name":"Node Classification on Non-Homophilic (Heterophilic) Graphs"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"WRGAT","rank_in_archive_order":34,"of":62,"metrics":{"Accuracy":"36.53 ± 0.77"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"WRGAT","rank_in_archive_order":44,"of":61,"metrics":{"Accuracy":"65.24 ±  0.87"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":15,"of":26,"metrics":{"1:1 Accuracy":"76.81 ± 1.89"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-48-32-20-fixed","task":"Node Classification","dataset":"Cora (48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":6,"of":26,"metrics":{"1:1 Accuracy":"88.20 ± 2.26"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"WRGAT","rank_in_archive_order":38,"of":60,"metrics":{"Accuracy":"81.62 ± 3.90"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-penn94","task":"Node Classification","dataset":"Penn94","model":"WRGAT","rank_in_archive_order":27,"of":32,"metrics":{"Accuracy":"74.32 ± 0.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-48-32-20-fixed","task":"Node Classification","dataset":"PubMed (48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":18,"of":26,"metrics":{"1:1 Accuracy":"88.52 ± 0.92"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"WRGAT","rank_in_archive_order":43,"of":59,"metrics":{"Accuracy":"48.85 ± 0.78"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"WRGAT","rank_in_archive_order":41,"of":62,"metrics":{"Accuracy":"83.62 ± 5.50"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-11","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Chameleon (48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":20,"of":29,"metrics":{"1:1 Accuracy":"65.24 ± 0.87 "},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-7","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Cornell (48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":18,"of":27,"metrics":{"1:1 Accuracy":"81.62 ±3.90 "},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-10","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Film(48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":13,"of":26,"metrics":{"1:1 Accuracy":"36.53 ± 0.77 "},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-13","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Penn94","model":"WRGAT","rank_in_archive_order":23,"of":28,"metrics":{"1:1 Accuracy":"74.32 ± 0.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-12","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Squirrel (48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":20,"of":29,"metrics":{"1:1 Accuracy":"48.85 ± 0.78"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-9","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Texas (48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":15,"of":26,"metrics":{"1:1 Accuracy":"83.62 ± 5.50 "},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-8","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Wisconsin (48%/32%/20% fixed splits)","model":"WRGAT","rank_in_archive_order":14,"of":26,"metrics":{"1:1 Accuracy":"86.98 ± 3.78 "},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.06586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06586"}},"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/susheels/gnns-and-local-assortativity","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":11},"by_repo_kind":{"official":{"samples":12,"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":"5e3663ee66aeb1d8","entry":"filter_rels","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"exp.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/exp.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5e3663ee66aeb1d8"}},{"code_sha256_prefix":"5d28fa208f6b62a9","entry":"build_multigraph_from_layers","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"build_multigraph.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/build_multigraph.py","link_basis":"plan_row","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":"5d28fa208f6b62a9"}},{"code_sha256_prefix":"f6a38e82cb7bacde","entry":"check_rm","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"datasets/bgp.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/datasets/bgp.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":"f6a38e82cb7bacde"}},{"code_sha256_prefix":"a031777e4ebeff8a","entry":"chooseNeighbor","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"struc_sim/algorithms.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/struc_sim/algorithms.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":"a031777e4ebeff8a"}},{"code_sha256_prefix":"7984390414b770ba","entry":"convert_ndarray","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"datasets/bgp.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/datasets/bgp.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":"7984390414b770ba"}},{"code_sha256_prefix":"e2522114d54ff7a8","entry":"exec_ramdom_walks_for_chunck","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"struc_sim/algorithms.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/struc_sim/algorithms.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":"e2522114d54ff7a8"}},{"code_sha256_prefix":"686c85e304c59420","entry":"exec_random_walk","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"struc_sim/algorithms.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/struc_sim/algorithms.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":"686c85e304c59420"}},{"code_sha256_prefix":"be0549eb08da272a","entry":"getCompactDegreeLists","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"struc_sim/algorithms_distances.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/struc_sim/algorithms_distances.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":"be0549eb08da272a"}},{"code_sha256_prefix":"0dfca563e6da5c5a","entry":"getCompactDegreeListsVertices","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"struc_sim/algorithms_distances.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/struc_sim/algorithms_distances.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":"0dfca563e6da5c5a"}},{"code_sha256_prefix":"4ae621b1fc59fd88","entry":"getDegreeListsVertices","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"struc_sim/algorithms_distances.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/struc_sim/algorithms_distances.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":"4ae621b1fc59fd88"}},{"code_sha256_prefix":"a093c2a5cfaf259d","entry":"get_degrees","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"datasets/airports.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/datasets/airports.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":"a093c2a5cfaf259d"}},{"code_sha256_prefix":"4102c2d70e0e526f","entry":"rm_useless","repo":"susheels/gnns-and-local-assortativity","repo_kind":"official","path":"datasets/bgp.py","file_url":"https://github.com/susheels/gnns-and-local-assortativity/blob/HEAD/datasets/bgp.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":"4102c2d70e0e526f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}