{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/r-gcn-the-r-could-stand-for-random","title":"R-GCN: The R Could Stand for Random","arxiv_id":"2203.02424","date":"2022-03-04","proceeding":null,"authors":["Vic Degraeve","Gilles Vandewiele","Femke Ongenae","Sofie Van Hoecke"],"abstract":"The inception of the Relational Graph Convolutional Network (R-GCN) marked a milestone in the Semantic Web domain as a widely cited method that generalises end-to-end hierarchical representation learning to Knowledge Graphs (KGs). R-GCNs generate representations for nodes of interest by repeatedly aggregating parameterised, relation-specific transformations of their neighbours. However, in this paper, we argue that the the R-GCN's main contribution lies in this \"message passing\" paradigm, rather than the learned weights. To this end, we introduce the \"Random Relational Graph Convolutional Network\" (RR-GCN), which leaves all parameters untrained and thus constructs node embeddings by aggregating randomly transformed random representations from neighbours, i.e., with no learned parameters. We empirically show that RR-GCNs can compete with fully trained R-GCNs in both node classification and link prediction settings.","url_abs":"https://arxiv.org/abs/2203.02424v2","url_pdf":"https://arxiv.org/pdf/2203.02424v2.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":"r-gcn-the-r-could-stand-for-random","repo_url":"https://github.com/predict-idlab/RR-GCN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"RR-GCN-PPV","rank_in_archive_order":54,"of":75,"metrics":{"Hits@1":"0.157","Hits@10":"0.412","Hits@3":"0.256","MRR":"0.238"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-aifb","task":"Node Classification","dataset":"AIFB","model":"RR-GCN-PPV-CUT","rank_in_archive_order":2,"of":7,"metrics":{"Accuracy":"95.83"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-aifb","task":"Node Classification","dataset":"AIFB","model":"RR-GCN-PPV","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"86.11"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-am","task":"Node Classification","dataset":"AM","model":"RR-GCN-PPV-CUT (Unimportant relations removed)","rank_in_archive_order":2,"of":8,"metrics":{"Accuracy":"91.31"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-am","task":"Node Classification","dataset":"AM","model":"RR-GCN-PPV-CUT","rank_in_archive_order":7,"of":8,"metrics":{"Accuracy":"84.8"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-am","task":"Node Classification","dataset":"AM","model":"RR-GCN-PPV","rank_in_archive_order":8,"of":8,"metrics":{"Accuracy":"84.65"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amplus","task":"Node Classification","dataset":"AMPLUS","model":"RR-GCN-PPV","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"84.54"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amplus","task":"Node Classification","dataset":"AMPLUS","model":"R-GCN","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"83.81"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-bgs","task":"Node Classification","dataset":"BGS","model":"RR-GCN-PPV-CUT","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"84.14"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-bgs","task":"Node Classification","dataset":"BGS","model":"RR-GCN-PPV","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"78.97"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dblp","task":"Node Classification","dataset":"DBLP","model":"RR-GCN-PPV","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"70.61"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dblp","task":"Node Classification","dataset":"DBLP","model":"R-GCN","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"68.51"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dmg777k","task":"Node Classification","dataset":"DMG777K","model":"RR-GCN-PPV","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"63.97"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dmg777k","task":"Node Classification","dataset":"DMG777K","model":"R-GCN","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"62.51"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dmgfull","task":"Node Classification","dataset":"DMGFULL","model":"RR-GCN-PPV","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"63.38"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dmgfull","task":"Node Classification","dataset":"DMGFULL","model":"R-GCN","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"57.52"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mdgenre","task":"Node Classification","dataset":"MDGENRE","model":"R-GCN","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"67.33"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mdgenre","task":"Node Classification","dataset":"MDGENRE","model":"RR-GCN-PPV","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"67.15"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-mutag","task":"Node Classification","dataset":"MUTAG","model":"RR-GCN-PPV","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"79.41"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.02424","atlas_url":"https://app.syntology.ai/?focus=2203.02424","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2203.02424"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.02424\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.02424"},"call":"get_concepts_for_paper(arxiv_id=\"2203.02424\")"}],"by_repo":[{"repo":"predict-idlab/RR-GCN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ad319e87b0e6fc656ae59e635ccab2d95a3014a66bdbcdaac24443429bb6e07e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}