{"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/dropgnn-random-dropouts-increase-the","title":"DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks","arxiv_id":"2111.06283","date":"2021-11-11","proceeding":"NeurIPS 2021 12","authors":["Pál András Papp","Karolis Martinkus","Lukas Faber","Roger Wattenhofer"],"abstract":"This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs of a GNN on the input graph, with some of the nodes randomly and independently dropped in each of these runs. Then, we combine the results of these runs to obtain the final result. We prove that DropGNNs can distinguish various graph neighborhoods that cannot be separated by message passing GNNs. We derive theoretical bounds for the number of runs required to ensure a reliable distribution of dropouts, and we prove several properties regarding the expressive capabilities and limits of DropGNNs. We experimentally validate our theoretical findings on expressiveness. Furthermore, we show that DropGNNs perform competitively on established GNN benchmarks.","url_abs":"https://arxiv.org/abs/2111.06283v1","url_pdf":"https://arxiv.org/pdf/2111.06283v1.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":"dropgnn-random-dropouts-increase-the","repo_url":"https://github.com/karolismart/dropgnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"DropGIN","rank_in_archive_order":29,"of":53,"metrics":{"Accuracy":"78.151±3.711"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-enzymes","task":"Graph Classification","dataset":"ENZYMES","model":"DropGIN","rank_in_archive_order":22,"of":54,"metrics":{"Accuracy":"65.128±4.117"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"DropGIN","rank_in_archive_order":21,"of":51,"metrics":{"Accuracy":"75.7%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-m","task":"Graph Classification","dataset":"IMDb-M","model":"DropGIN","rank_in_archive_order":15,"of":36,"metrics":{"Accuracy":"51.4%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"DropGIN","rank_in_archive_order":21,"of":74,"metrics":{"Accuracy":"90.4%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"DropGIN","rank_in_archive_order":21,"of":69,"metrics":{"Accuracy":"84.331±1.564"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci109","task":"Graph Classification","dataset":"NCI109","model":"DropGIN","rank_in_archive_order":8,"of":38,"metrics":{"Accuracy":"83.961±1.141"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"DropGIN","rank_in_archive_order":52,"of":103,"metrics":{"Accuracy":"76.3%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-ptc","task":"Graph Classification","dataset":"PTC","model":"DropGIN","rank_in_archive_order":19,"of":37,"metrics":{"Accuracy":"66.3%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-esr2","task":"Graph Regression","dataset":"ESR2","model":"DropGIN","rank_in_archive_order":3,"of":9,"metrics":{"R2":"0.675±0.000","RMSE":"0.503±0.675"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-f2","task":"Graph Regression","dataset":"F2","model":"DropGIN","rank_in_archive_order":5,"of":9,"metrics":{"R2":"0.886±0.000","RMSE":"0.343±0.886"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-kit","task":"Graph Regression","dataset":"KIT","model":"GINDrop","rank_in_archive_order":3,"of":9,"metrics":{"R2":"0.835±0.000","RMSE":"0.441±0.835"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-lipophilicity","task":"Graph Regression","dataset":"Lipophilicity","model":"DropGIN","rank_in_archive_order":6,"of":23,"metrics":{"R2":"0.809±0.008","RMSE":"0.552±0.012"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-parp1","task":"Graph Regression","dataset":"PARP1","model":"DropGIN","rank_in_archive_order":5,"of":9,"metrics":{"R2":"0.920±0.000","RMSE":"0.354±0.920"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-pgr","task":"Graph Regression","dataset":"PGR","model":"GINDrop","rank_in_archive_order":3,"of":9,"metrics":{"R2":"0.702±0.000","RMSE":"0.527±0.702"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-esol","task":"Molecular Property Prediction","dataset":"ESOL","model":"DropGIN","rank_in_archive_order":5,"of":20,"metrics":{"R2":"0.935±0.012","RMSE":"0.520±0.048"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-freesolv","task":"Molecular Property Prediction","dataset":"FreeSolv","model":"DropGIN","rank_in_archive_order":2,"of":22,"metrics":{"R2":"0.972±0.005","RMSE":"0.657±0.059"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.06283","atlas_url":"https://app.syntology.ai/?focus=2111.06283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06283"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/karolismart/dropgnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"ca79c0c0249b5487","entry":"S2V_to_PyG","repo":"karolismart/dropgnn","repo_kind":"official","path":"ptc_dataset.py","file_url":"https://github.com/karolismart/dropgnn/blob/HEAD/ptc_dataset.py","link_basis":"harvester_set","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":"ca79c0c0249b5487"}},{"code_sha256_prefix":"22f66d8c36eceac7","entry":"load_data","repo":"karolismart/dropgnn","repo_kind":"official","path":"ptc_dataset.py","file_url":"https://github.com/karolismart/dropgnn/blob/HEAD/ptc_dataset.py","link_basis":"harvester_set","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":"22f66d8c36eceac7"}},{"code_sha256_prefix":"0245c4edf22b808d","entry":"main","repo":"karolismart/dropgnn","repo_kind":"official","path":"gin-synthetic.py","file_url":"https://github.com/karolismart/dropgnn/blob/HEAD/gin-synthetic.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":"0245c4edf22b808d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}