{"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/scalable-and-adaptive-graph-neural-networks","title":"Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training","arxiv_id":"2104.09376","date":"2021-04-19","proceeding":null,"authors":["Chuxiong Sun","Hongming Gu","Jie Hu"],"abstract":"It is hard to directly implement Graph Neural Networks (GNNs) on large scaled graphs. Besides of existed neighbor sampling techniques, scalable methods decoupling graph convolutions and other learnable transformations into preprocessing and post classifier allow normal minibatch training. By replacing redundant concatenation operation with attention mechanism in SIGN, we propose Scalable and Adaptive Graph Neural Networks (SAGN). SAGN can adaptively gather neighborhood information among different hops. To further improve scalable models on semi-supervised learning tasks, we propose Self-Label-Enhance (SLE) framework combining self-training approach and label propagation in depth. We add base model with a scalable node label module. Then we iteratively train models and enhance train set in several stages. To generate input of node label module, we directly apply label propagation based on one-hot encoded label vectors without inner random masking. We find out that empirically the label leakage has been effectively alleviated after graph convolutions. The hard pseudo labels in enhanced train set participate in label propagation with true labels. Experiments on both inductive and transductive datasets demonstrate that, compared with other sampling-based and sampling-free methods, SAGN achieves better or comparable results and SLE can further improve performance.","url_abs":"https://arxiv.org/abs/2104.09376v3","url_pdf":"https://arxiv.org/pdf/2104.09376v3.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":"scalable-and-adaptive-graph-neural-networks","repo_url":"https://github.com/skepsun/SAGN_with_SLE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-property-prediction-on-ogbn-mag","task":"Node Property Prediction","dataset":"ogbn-mag","model":"NARS_SAGN+SLE","rank_in_archive_order":16,"of":39,"metrics":{"Ext. data":"No","Number of params":"3846330","Test Accuracy":"0.5440 ± 0.0015","Validation Accuracy":"0.5591 ± 0.0017"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-papers100m","task":"Node Property Prediction","dataset":"ogbn-papers100M","model":"SAGN+SLE (4 stages)","rank_in_archive_order":4,"of":20,"metrics":{"Ext. data":"No","Number of params":"8556888","Test Accuracy":"0.6830 ± 0.0008","Validation Accuracy":"0.7163 ± 0.0007"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-papers100m","task":"Node Property Prediction","dataset":"ogbn-papers100M","model":"SAGN+SLE","rank_in_archive_order":9,"of":20,"metrics":{"Ext. data":"No","Number of params":"8556888","Test Accuracy":"0.6800 ± 0.0015","Validation Accuracy":"0.7131 ± 0.0010"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-papers100m","task":"Node Property Prediction","dataset":"ogbn-papers100M","model":"SAGN","rank_in_archive_order":14,"of":20,"metrics":{"Ext. data":"No","Number of params":"6098092","Test Accuracy":"0.6675 ± 0.0084","Validation Accuracy":"0.7034 ± 0.0099"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"SAGN+SLE (4 stages)+C&S","rank_in_archive_order":17,"of":64,"metrics":{"Ext. data":"No","Number of params":"2179678","Test Accuracy":"0.8485 ± 0.0010","Validation Accuracy":"0.9302 ± 0.0003"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"SAGN+SLE (4 stages)","rank_in_archive_order":18,"of":64,"metrics":{"Ext. data":"No","Number of params":"2179678","Test Accuracy":"0.8468 ± 0.0012","Validation Accuracy":"0.9309 ± 0.0007"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"SAGN+SLE","rank_in_archive_order":23,"of":64,"metrics":{"Ext. data":"No","Number of params":"2179678","Test Accuracy":"0.8428 ± 0.0014","Validation Accuracy":"0.9287 ± 0.0003"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"SAGN","rank_in_archive_order":38,"of":64,"metrics":{"Ext. data":"No","Number of params":"2233391","Test Accuracy":"0.8120 ± 0.0007","Validation Accuracy":"0.9309 ± 0.0004"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.09376","atlas_url":"https://app.syntology.ai/?focus=2104.09376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09376"}},"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/skepsun/SAGN_with_SLE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"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":"c6acd3e400fc2676","entry":"get_n_params","repo":"skepsun/SAGN_with_SLE","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/skepsun/SAGN_with_SLE/blob/HEAD/src/utils.py","link_basis":"plan_row","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":"c6acd3e400fc2676"}},{"code_sha256_prefix":"a4d2591506684852","entry":"entropy","repo":"skepsun/SAGN_with_SLE","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/skepsun/SAGN_with_SLE/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","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":"a4d2591506684852"}},{"code_sha256_prefix":"f31615a9e0aa6f97","entry":"generate_preds_path","repo":"skepsun/SAGN_with_SLE","repo_kind":"official","path":"src/post_process.py","file_url":"https://github.com/skepsun/SAGN_with_SLE/blob/HEAD/src/post_process.py","link_basis":"first_harvest_node","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":"f31615a9e0aa6f97"}},{"code_sha256_prefix":"eb1a19a333b59f25","entry":"load_output_files","repo":"skepsun/SAGN_with_SLE","repo_kind":"official","path":"src/post_process.py","file_url":"https://github.com/skepsun/SAGN_with_SLE/blob/HEAD/src/post_process.py","link_basis":"first_harvest_node","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":"eb1a19a333b59f25"}},{"code_sha256_prefix":"8ccc6f05779c9d3f","entry":"test","repo":"skepsun/SAGN_with_SLE","repo_kind":"official","path":"src/train_process.py","file_url":"https://github.com/skepsun/SAGN_with_SLE/blob/HEAD/src/train_process.py","link_basis":"first_harvest_node","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":"8ccc6f05779c9d3f"}},{"code_sha256_prefix":"9301ba207b35bab1","entry":"to_scipy","repo":"skepsun/SAGN_with_SLE","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/skepsun/SAGN_with_SLE/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","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":"9301ba207b35bab1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}