{"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/graph-propagation-transformer-for-graph","title":"Graph Propagation Transformer for Graph Representation Learning","arxiv_id":"2305.11424","date":"2023-05-19","proceeding":null,"authors":["Zhe Chen","Hao Tan","Tao Wang","Tianrun Shen","Tong Lu","Qiuying Peng","Cheng Cheng","Yue Qi"],"abstract":"This paper presents a novel transformer architecture for graph representation learning. The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer blocks. Specifically, we propose a new attention mechanism called Graph Propagation Attention (GPA). It explicitly passes the information among nodes and edges in three ways, i.e. node-to-node, node-to-edge, and edge-to-node, which is essential for learning graph-structured data. On this basis, we design an effective transformer architecture named Graph Propagation Transformer (GPTrans) to further help learn graph data. We verify the performance of GPTrans in a wide range of graph learning experiments on several benchmark datasets. These results show that our method outperforms many state-of-the-art transformer-based graph models with better performance. The code will be released at https://github.com/czczup/GPTrans.","url_abs":"https://arxiv.org/abs/2305.11424v3","url_pdf":"https://arxiv.org/pdf/2305.11424v3.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":"graph-propagation-transformer-for-graph","repo_url":"https://github.com/czczup/gptrans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"graph-property-prediction","task_name":"Graph Property Prediction"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"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":"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/graph-property-prediction-on-ogbg-molhiv","task":"Graph Property Prediction","dataset":"ogbg-molhiv","model":"GPTrans-B","rank_in_archive_order":9,"of":43,"metrics":{"Ext. data":"Yes","Test ROC-AUC":"0.8126 ± 0.0032"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-pcqm4m-lsc","task":"Graph Regression","dataset":"PCQM4M-LSC","model":"GPTrans-L","rank_in_archive_order":8,"of":11,"metrics":{"Validation MAE":"0.1151"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-pcqm4mv2-lsc","task":"Graph Regression","dataset":"PCQM4Mv2-LSC","model":"GPTrans-L","rank_in_archive_order":6,"of":20,"metrics":{"Test MAE":"0.0821","Validation MAE":"0.0809"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-pcqm4mv2-lsc","task":"Graph Regression","dataset":"PCQM4Mv2-LSC","model":"GPTrans-T","rank_in_archive_order":8,"of":20,"metrics":{"Test MAE":"0.0842","Validation MAE":"0.0833"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-500k","task":"Graph Regression","dataset":"ZINC-500k","model":"GPTrans-Nano","rank_in_archive_order":14,"of":36,"metrics":{"MAE":"0.077"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cluster","task":"Node Classification","dataset":"CLUSTER","model":"GPTrans-Nano","rank_in_archive_order":7,"of":12,"metrics":{"Accuracy":"78.07"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pattern","task":"Node Classification","dataset":"PATTERN","model":"GPTrans-Nano","rank_in_archive_order":8,"of":11,"metrics":{"Accuracy":"86.734±0.008"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.11424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11424"}},"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/czczup/gptrans","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/czczup/GPTrans","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"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":8,"samples":[{"code_sha256_prefix":"fb8d3bae800de83f","entry":"FFN","repo":"czczup/GPTrans","repo_kind":"official","path":"models/gptrans.py","file_url":"https://github.com/czczup/GPTrans/blob/HEAD/models/gptrans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb8d3bae800de83f"}},{"code_sha256_prefix":"d7655599f8ece8e5","entry":"GraphEdgeFeature","repo":"czczup/GPTrans","repo_kind":"official","path":"models/gptrans.py","file_url":"https://github.com/czczup/GPTrans/blob/HEAD/models/gptrans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7655599f8ece8e5"}},{"code_sha256_prefix":"ec865a2d4baccda8","entry":"GraphNodeFeature","repo":"czczup/GPTrans","repo_kind":"official","path":"models/gptrans.py","file_url":"https://github.com/czczup/GPTrans/blob/HEAD/models/gptrans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ec865a2d4baccda8"}},{"code_sha256_prefix":"1c592dd49f570330","entry":"GraphPropagationAttention","repo":"czczup/GPTrans","repo_kind":"official","path":"models/gptrans.py","file_url":"https://github.com/czczup/GPTrans/blob/HEAD/models/gptrans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c592dd49f570330"}},{"code_sha256_prefix":"78aeb0947a918bbb","entry":"GPTrans","repo":"czczup/GPTrans","repo_kind":"official","path":"models/gptrans.py","file_url":"https://github.com/czczup/GPTrans/blob/HEAD/models/gptrans.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"78aeb0947a918bbb"}},{"code_sha256_prefix":"6486fc9951e132a2","entry":"GPTransBlock","repo":"czczup/GPTrans","repo_kind":"official","path":"models/gptrans.py","file_url":"https://github.com/czczup/GPTrans/blob/HEAD/models/gptrans.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6486fc9951e132a2"}},{"code_sha256_prefix":"65e6a8898955628f","entry":"GraphEmbedding","repo":"czczup/GPTrans","repo_kind":"official","path":"models/gptrans.py","file_url":"https://github.com/czczup/GPTrans/blob/HEAD/models/gptrans.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"65e6a8898955628f"}},{"code_sha256_prefix":"387e440741d605b1","entry":"init_params","repo":"czczup/GPTrans","repo_kind":"official","path":"models/gptrans.py","file_url":"https://github.com/czczup/GPTrans/blob/HEAD/models/gptrans.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"387e440741d605b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}