{"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/towards-deeper-graph-neural-networks","title":"Towards Deeper Graph Neural Networks","arxiv_id":"2007.09296","date":"2020-07-18","proceeding":null,"authors":["Meng Liu","Hongyang Gao","Shuiwang Ji"],"abstract":"Graph neural networks have shown significant success in the field of graph representation learning. Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Nevertheless, one layer of these neighborhood aggregation methods only consider immediate neighbors, and the performance decreases when going deeper to enable larger receptive fields. Several recent studies attribute this performance deterioration to the over-smoothing issue, which states that repeated propagation makes node representations of different classes indistinguishable. In this work, we study this observation systematically and develop new insights towards deeper graph neural networks. First, we provide a systematical analysis on this issue and argue that the key factor compromising the performance significantly is the entanglement of representation transformation and propagation in current graph convolution operations. After decoupling these two operations, deeper graph neural networks can be used to learn graph node representations from larger receptive fields. We further provide a theoretical analysis of the above observation when building very deep models, which can serve as a rigorous and gentle description of the over-smoothing issue. Based on our theoretical and empirical analysis, we propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields. A set of experiments on citation, co-authorship, and co-purchase datasets have confirmed our analysis and insights and demonstrated the superiority of our proposed methods.","url_abs":"https://arxiv.org/abs/2007.09296v1","url_pdf":"https://arxiv.org/pdf/2007.09296v1.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":"towards-deeper-graph-neural-networks","repo_url":"https://github.com/divelab/DeeperGNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-deeper-graph-neural-networks","repo_url":"https://github.com/mengliu1998/DeeperGNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"towards-deeper-graph-neural-networks","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/dagnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-amz-computers","task":"Node Classification","dataset":"AMZ Computers","model":"DAGNN (Ours)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"84.5 ± 1.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amz-photo","task":"Node Classification","dataset":"AMZ Photo","model":"DAGNN (Ours)","rank_in_archive_order":12,"of":14,"metrics":{"Accuracy":"92%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-with-public","task":"Node Classification","dataset":"CiteSeer with Public Split: fixed 20 nodes per class","model":"DAGNN (Ours)","rank_in_archive_order":18,"of":40,"metrics":{"Accuracy":"73.3 ± 0.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-cs","task":"Node Classification","dataset":"Coauthor CS","model":"DAGNN (Ours)","rank_in_archive_order":19,"of":24,"metrics":{"Accuracy":"92.8%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-physics","task":"Node Classification","dataset":"Coauthor Physics","model":"DAGNN (Ours)","rank_in_archive_order":14,"of":14,"metrics":{"Accuracy":"94"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-with-public-split","task":"Node Classification","dataset":"Cora with Public Split: fixed 20 nodes per class","model":"DAGNN (Ours)","rank_in_archive_order":9,"of":36,"metrics":{"Accuracy":"84.4 ± 0.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-with-public","task":"Node Classification","dataset":"PubMed with Public Split: fixed 20 nodes per class","model":"DAGNN (Ours)","rank_in_archive_order":12,"of":37,"metrics":{"Accuracy":"80.5 ± 0.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"DAGNN","rank_in_archive_order":68,"of":86,"metrics":{"Ext. data":"No","Number of params":"43857","Test Accuracy":"0.7209 ± 0.0025","Validation Accuracy":"0.7290 ± 0.0011"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.09296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09296"}},"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/divelab/DeeperGNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mengliu1998/DeeperGNN","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/dagnn","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":2,"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":3,"samples":[{"code_sha256_prefix":"da80a2b9fd449bd2","entry":"index_to_mask","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"da80a2b9fd449bd2"}},{"code_sha256_prefix":"07c4cd8cc06de6de","entry":"random_coauthor_amazon_splits","repo":"divelab/DeeperGNN","repo_kind":"official","path":"DeeperGNN/train_eval.py","file_url":"https://github.com/divelab/DeeperGNN/blob/HEAD/DeeperGNN/train_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"07c4cd8cc06de6de"}},{"code_sha256_prefix":"d97355d8b1db10f9","entry":"random_planetoid_splits","repo":"divelab/DeeperGNN","repo_kind":"official","path":"DeeperGNN/train_eval.py","file_url":"https://github.com/divelab/DeeperGNN/blob/HEAD/DeeperGNN/train_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d97355d8b1db10f9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}