{"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/graph-infoclust-leveraging-cluster-level-node","title":"Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning","arxiv_id":"2009.06946","date":"2020-09-15","proceeding":null,"authors":["Costas Mavromatis","George Karypis"],"abstract":"Unsupervised (or self-supervised) graph representation learning is essential to facilitate various graph data mining tasks when external supervision is unavailable. The challenge is to encode the information about the graph structure and the attributes associated with the nodes and edges into a low dimensional space. Most existing unsupervised methods promote similar representations across nodes that are topologically close. Recently, it was shown that leveraging additional graph-level information, e.g., information that is shared among all nodes, encourages the representations to be mindful of the global properties of the graph, which greatly improves their quality. However, in most graphs, there is significantly more structure that can be captured, e.g., nodes tend to belong to (multiple) clusters that represent structurally similar nodes. Motivated by this observation, we propose a graph representation learning method called Graph InfoClust (GIC), that seeks to additionally capture cluster-level information content. These clusters are computed by a differentiable K-means method and are jointly optimized by maximizing the mutual information between nodes of the same clusters. This optimization leads the node representations to capture richer information and nodal interactions, which improves their quality. Experiments show that GIC outperforms state-of-art methods in various downstream tasks (node classification, link prediction, and node clustering) with a 0.9% to 6.1% gain over the best competing approach, on average.","url_abs":"https://arxiv.org/abs/2009.06946v1","url_pdf":"https://arxiv.org/pdf/2009.06946v1.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":"graph-infoclust-leveraging-cluster-level-node","repo_url":"https://github.com/cmavro/Graph-InfoClust-GIC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-infoclust-leveraging-cluster-level-node","repo_url":"https://github.com/cmavro/HeMI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-clustering","task_name":"Node Clustering"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"gic","method_name":"GIC"}],"datasets_introduced":[],"methods_introduced":[{"slug":"gic","name":"GIC","full_name":"Graph InfoClust"}],"results":[{"leaderboard":"/sota/link-prediction-on-citeseer","task":"Link Prediction","dataset":"Citeseer","model":"Graph InfoClust (GIC)","rank_in_archive_order":3,"of":13,"metrics":{"AP":"96.8","AUC":"97"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-cora","task":"Link Prediction","dataset":"Cora","model":"sGraphite-VAE","rank_in_archive_order":7,"of":13,"metrics":{"AP":"93.5%","AUC":"93.7%"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-pubmed","task":"Link Prediction","dataset":"Pubmed","model":"Graph InfoClust (GIC)","rank_in_archive_order":11,"of":13,"metrics":{"AP":"93.5%","AUC":"93.7%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amz-comp","task":"Node Classification","dataset":"AMZ Comp","model":"Graph InfoClust (GIC)","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"81.5 ± 1.0"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amz-photo","task":"Node Classification","dataset":"AMZ Photo","model":"Graph InfoClust (GIC)","rank_in_archive_order":14,"of":14,"metrics":{"Accuracy":"90.4 ± 1.0"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"Graph InfoClust (GIC)","rank_in_archive_order":46,"of":71,"metrics":{"Accuracy":"71.9 ± 1.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-cs","task":"Node Classification","dataset":"Coauthor CS","model":"Graph InfoClust (GIC)","rank_in_archive_order":22,"of":24,"metrics":{"Accuracy":"89.4 ± 0.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-phy","task":"Node Classification","dataset":"Coauthor Phy","model":"Graph InfoClust (GIC)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"93.1 ± 0.7"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-fixed-20-node-per","task":"Node Classification","dataset":"Cora: fixed 20 node per class","model":"Graph InfoClust (GIC)","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"81.7 ± 1.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"Graph InfoClust (GIC)","rank_in_archive_order":59,"of":70,"metrics":{"Accuracy":"77.4 ± 1.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.06946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.06946"}},"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/cmavro/Graph-InfoClust-GIC","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cmavro/HeMI","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"375035e86b4d8f45","entry":"get_roc_score","repo":"cmavro/Graph-InfoClust-GIC","repo_kind":"listed","path":"GIC/execute_link.py","file_url":"https://github.com/cmavro/Graph-InfoClust-GIC/blob/HEAD/GIC/execute_link.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"375035e86b4d8f45"}},{"code_sha256_prefix":"c6f62788994e24d4","entry":"cluster","repo":"cmavro/HeMI","repo_kind":"listed","path":"layers/cluster.py","file_url":"https://github.com/cmavro/HeMI/blob/HEAD/layers/cluster.py","link_basis":"harvester_set","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":"c6f62788994e24d4"}},{"code_sha256_prefix":"c04d72b804d055b8","entry":"val_loss","repo":"cmavro/HeMI","repo_kind":"listed","path":"execute_link.py","file_url":"https://github.com/cmavro/HeMI/blob/HEAD/execute_link.py","link_basis":"harvester_set","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":"c04d72b804d055b8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}