{"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/masked-label-prediction-unified-massage","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","arxiv_id":"2009.03509","date":"2020-09-08","proceeding":null,"authors":["Yunsheng Shi","Zhengjie Huang","Shikun Feng","Hui Zhong","Wenjin Wang","Yu Sun"],"abstract":"Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. GNN performs feature propagation by a neural network to make predictions, while LPA uses label propagation across graph adjacency matrix to get results. However, there is still no effective way to directly combine these two kinds of algorithms. To address this issue, we propose a novel Unified Message Passaging Model (UniMP) that can incorporate feature and label propagation at both training and inference time. First, UniMP adopts a Graph Transformer network, taking feature embedding and label embedding as input information for propagation. Second, to train the network without overfitting in self-loop input label information, UniMP introduces a masked label prediction strategy, in which some percentage of input label information are masked at random, and then predicted. UniMP conceptually unifies feature propagation and label propagation and is empirically powerful. It obtains new state-of-the-art semi-supervised classification results in Open Graph Benchmark (OGB).","url_abs":"https://arxiv.org/abs/2009.03509v5","url_pdf":"https://arxiv.org/pdf/2009.03509v5.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":"masked-label-prediction-unified-massage","repo_url":"https://github.com/PaddlePaddle/PGL/tree/main/ogb_examples/nodeproppred/unimp","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"masked-label-prediction-unified-massage","repo_url":"https://github.com/lucidrains/graph-transformer-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"masked-label-prediction-unified-massage","repo_url":"https://github.com/willyfh/graph-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"UniMP_v2","rank_in_archive_order":32,"of":86,"metrics":{"Ext. data":"No","Number of params":"687377","Test Accuracy":"0.7397 ± 0.0015","Validation Accuracy":"0.7506 ± 0.0009"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"UniMP_large","rank_in_archive_order":36,"of":86,"metrics":{"Ext. data":"No","Number of params":"1162515","Test Accuracy":"0.7379 ± 0.0014","Validation Accuracy":"0.7475 ± 0.0008"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"UniMP","rank_in_archive_order":48,"of":86,"metrics":{"Ext. data":"No","Number of params":"473489","Test Accuracy":"0.7311 ± 0.0020","Validation Accuracy":"0.7450 ± 0.0005"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-papers100m","task":"Node Property Prediction","dataset":"ogbn-papers100M","model":"TransformerConv","rank_in_archive_order":11,"of":20,"metrics":{"Ext. data":"No","Number of params":"883378","Test Accuracy":"0.6736 ± 0.0010","Validation Accuracy":"0.7172 ± 0.0005"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"UniMP","rank_in_archive_order":32,"of":64,"metrics":{"Ext. data":"No","Number of params":"1475605","Test Accuracy":"0.8256 ± 0.0031","Validation Accuracy":"0.9308 ± 0.0017"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"UniMP+CrossEdgeFeat","rank_in_archive_order":10,"of":26,"metrics":{"Ext. data":"No","Number of params":"1959984","Test ROC-AUC":"0.8691 ± 0.0018","Validation ROC-AUC":"0.9258 ± 0.0009"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"UniMP","rank_in_archive_order":12,"of":26,"metrics":{"Ext. data":"No","Number of params":"1909104","Test ROC-AUC":"0.8642 ± 0.0008","Validation ROC-AUC":"0.9175 ± 0.0006"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.03509","atlas_url":"https://app.syntology.ai/?focus=2009.03509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.03509"}},"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/PaddlePaddle/PGL/tree/main/ogb_examples/nodeproppred/unimp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/willyfh/graph-transformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/graph-transformer-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_violates":2,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1},"listed":{"samples":4,"ran":4,"repositories":2}},"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":"e094fdc0df86ec02","entry":"FeedForward","repo":"lucidrains/graph-transformer-pytorch","repo_kind":"listed","path":"graph_transformer_pytorch/graph_transformer_pytorch.py","file_url":"https://github.com/lucidrains/graph-transformer-pytorch/blob/HEAD/graph_transformer_pytorch/graph_transformer_pytorch.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":"e094fdc0df86ec02"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":"lucidrains/graph-transformer-pytorch","repo_kind":"listed","path":"graph_transformer_pytorch/graph_transformer_pytorch.py","file_url":"https://github.com/lucidrains/graph-transformer-pytorch/blob/HEAD/graph_transformer_pytorch/graph_transformer_pytorch.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"lucidrains/graph-transformer-pytorch","repo_kind":"listed","path":"graph_transformer_pytorch/graph_transformer_pytorch.py","file_url":"https://github.com/lucidrains/graph-transformer-pytorch/blob/HEAD/graph_transformer_pytorch/graph_transformer_pytorch.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"2f6500993366c0f7","entry":"softmax","repo":"willyfh/graph-transformer","repo_kind":"listed","path":"graph_transformer/graph_transformer_model.py","file_url":"https://github.com/willyfh/graph-transformer/blob/HEAD/graph_transformer/graph_transformer_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f6500993366c0f7"}},{"code_sha256_prefix":"7de5d45120be5bcd","entry":"get_default_data_dir","repo":"PaddlePaddle/PGL","repo_kind":"official","path":"pgl/dataset.py","file_url":"https://github.com/PaddlePaddle/PGL/blob/HEAD/pgl/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7de5d45120be5bcd"}},{"code_sha256_prefix":"e97bbf7d7b1c2f61","entry":"is_all","repo":"PaddlePaddle/PGL","repo_kind":"official","path":"legacy/pgl/heter_graph_wrapper.py","file_url":"https://github.com/PaddlePaddle/PGL/blob/HEAD/legacy/pgl/heter_graph_wrapper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e97bbf7d7b1c2f61"}},{"code_sha256_prefix":"75f339abee8ab5cf","entry":"random_partition","repo":"PaddlePaddle/PGL","repo_kind":"official","path":"pgl/partition.py","file_url":"https://github.com/PaddlePaddle/PGL/blob/HEAD/pgl/partition.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"75f339abee8ab5cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}