{"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/skipnode-on-alleviating-over-smoothing-for","title":"SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks","arxiv_id":"2112.11628","date":"2021-12-22","proceeding":null,"authors":["Weigang Lu","Yibing Zhan","Binbin Lin","Ziyu Guan","Liu Liu","Baosheng Yu","Wei Zhao","Yaming Yang","DaCheng Tao"],"abstract":"Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the performance degeneration to over-smoothing. In this paper, we conduct theoretical and experimental analysis to explore the fundamental causes of performance degradation in deep GCNs: over-smoothing and gradient vanishing have a mutually reinforcing effect that causes the performance to deteriorate more quickly in deep GCNs. On the other hand, existing anti-over-smoothing methods all perform full convolutions up to the model depth. They could not well resist the exponential convergence of over-smoothing due to model depth increasing. In this work, we propose a simple yet effective plug-and-play module, Skipnode, to overcome the performance degradation of deep GCNs. It samples graph nodes in each convolutional layer to skip the convolution operation. In this way, both over-smoothing and gradient vanishing can be effectively suppressed since (1) not all nodes'features propagate through full layers and, (2) the gradient can be directly passed back through ``skipped'' nodes. We provide both theoretical analysis and empirical evaluation to demonstrate the efficacy of Skipnode and its superiority over SOTA baselines.","url_abs":"https://arxiv.org/abs/2112.11628v4","url_pdf":"https://arxiv.org/pdf/2112.11628v4.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":"skipnode-on-alleviating-over-smoothing-for","repo_url":"https://github.com/weiganglu/skipnode","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"gcn","method_name":"GCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.11628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.11628"}},"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/weiganglu/skipnode","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"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":"da80a2b9fd449bd2","entry":"index_to_mask","repo":"weiganglu/skipnode","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/weiganglu/skipnode/blob/HEAD/utils/dataset.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da80a2b9fd449bd2"}},{"code_sha256_prefix":"1875a961241944ff","entry":"cal_energy","repo":"weiganglu/skipnode","repo_kind":"official","path":"utils/energy.py","file_url":"https://github.com/weiganglu/skipnode/blob/HEAD/utils/energy.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":"1875a961241944ff"}},{"code_sha256_prefix":"83661fc8bde4fc47","entry":"compute_mad_value","repo":"weiganglu/skipnode","repo_kind":"official","path":"utils/mad_gap.py","file_url":"https://github.com/weiganglu/skipnode/blob/HEAD/utils/mad_gap.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":"83661fc8bde4fc47"}},{"code_sha256_prefix":"91e82cab62fa0b71","entry":"generate_random_graph","repo":"weiganglu/skipnode","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/weiganglu/skipnode/blob/HEAD/utils/dataset.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":"91e82cab62fa0b71"}},{"code_sha256_prefix":"ebae84a1ad7dfa50","entry":"get_dataset","repo":"weiganglu/skipnode","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/weiganglu/skipnode/blob/HEAD/utils/dataset.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":"ebae84a1ad7dfa50"}},{"code_sha256_prefix":"6ff82b43fa43b21c","entry":"get_laplacian_mat","repo":"weiganglu/skipnode","repo_kind":"official","path":"utils/energy.py","file_url":"https://github.com/weiganglu/skipnode/blob/HEAD/utils/energy.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":"6ff82b43fa43b21c"}},{"code_sha256_prefix":"254aa250e6c6fd5e","entry":"tonp","repo":"weiganglu/skipnode","repo_kind":"official","path":"utils/energy.py","file_url":"https://github.com/weiganglu/skipnode/blob/HEAD/utils/energy.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":"254aa250e6c6fd5e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}