{"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/unsupervised-universal-self-attention-network","title":"Universal Graph Transformer Self-Attention Networks","arxiv_id":"1909.11855","date":"2019-09-26","proceeding":null,"authors":["Dai Quoc Nguyen","Tu Dinh Nguyen","Dinh Phung"],"abstract":"The transformer self-attention network has been extensively used in research domains such as computer vision, image processing, and natural language processing. But it has not been actively used in graph neural networks (GNNs) where constructing an advanced aggregation function is essential. To this end, we present U2GNN, an effective GNN model leveraging a transformer self-attention mechanism followed by a recurrent transition, to induce a powerful aggregation function to learn graph representations. Experimental results show that the proposed U2GNN achieves state-of-the-art accuracies on well-known benchmark datasets for graph classification. Our code is available at: https://github.com/daiquocnguyen/Graph-Transformer","url_abs":"https://arxiv.org/abs/1909.11855v9","url_pdf":"https://arxiv.org/pdf/1909.11855v9.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":"unsupervised-universal-self-attention-network","repo_url":"https://github.com/daiquocnguyen/Graph-Transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"graph-representation-learning","task_name":"Graph 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":"relu","method_name":"ReLU"},{"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-classification-on-collab","task":"Graph Classification","dataset":"COLLAB","model":"U2GNN (Unsupervised)","rank_in_archive_order":1,"of":39,"metrics":{"Accuracy":"95.62%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-collab","task":"Graph Classification","dataset":"COLLAB","model":"U2GNN","rank_in_archive_order":20,"of":39,"metrics":{"Accuracy":"77.84%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"U2GNN (Unsupervised)","rank_in_archive_order":1,"of":53,"metrics":{"Accuracy":"95.67%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"U2GNN","rank_in_archive_order":14,"of":53,"metrics":{"Accuracy":"80.23%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"U2GNN (Unsupervised)","rank_in_archive_order":1,"of":51,"metrics":{"Accuracy":"96.41%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"U2GNN","rank_in_archive_order":17,"of":51,"metrics":{"Accuracy":"77.04%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-m","task":"Graph Classification","dataset":"IMDb-M","model":"U2GNN (Unsupervised)","rank_in_archive_order":1,"of":36,"metrics":{"Accuracy":"89.2%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-m","task":"Graph Classification","dataset":"IMDb-M","model":"U2GNN","rank_in_archive_order":9,"of":36,"metrics":{"Accuracy":"53.60%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"U2GNN","rank_in_archive_order":25,"of":74,"metrics":{"Accuracy":"89.97%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"U2GNN (Unsupervised)","rank_in_archive_order":37,"of":74,"metrics":{"Accuracy":"88.47%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"U2GNN (Unsupervised)","rank_in_archive_order":12,"of":103,"metrics":{"Accuracy":"80.01%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"U2GNN","rank_in_archive_order":18,"of":103,"metrics":{"Accuracy":"78.53%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-ptc","task":"Graph Classification","dataset":"PTC","model":"U2GNN (Unsupervised)","rank_in_archive_order":1,"of":37,"metrics":{"Accuracy":"91.81%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-ptc","task":"Graph Classification","dataset":"PTC","model":"U2GNN","rank_in_archive_order":13,"of":37,"metrics":{"Accuracy":"69.63%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.11855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11855"}},"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/daiquocnguyen/Graph-Transformer","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"339e9f8214d3d974","entry":"cross_entropy","repo":"daiquocnguyen/Graph-Transformer","repo_kind":"official","path":"UGformerV2_PyTorch/train_UGformerV2.py","file_url":"https://github.com/daiquocnguyen/Graph-Transformer/blob/HEAD/UGformerV2_PyTorch/train_UGformerV2.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"339e9f8214d3d974"}},{"code_sha256_prefix":"4df9c8952f3c7ef8","entry":"get_Adj_matrix","repo":"daiquocnguyen/Graph-Transformer","repo_kind":"official","path":"UGformerV1_PyTorch/train_UGformerV1_Sup.py","file_url":"https://github.com/daiquocnguyen/Graph-Transformer/blob/HEAD/UGformerV1_PyTorch/train_UGformerV1_Sup.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4df9c8952f3c7ef8"}},{"code_sha256_prefix":"6fa85bb11337eaf8","entry":"get_Adj_matrix","repo":"daiquocnguyen/Graph-Transformer","repo_kind":"official","path":"UGformerV2_PyTorch/train_UGformerV2.py","file_url":"https://github.com/daiquocnguyen/Graph-Transformer/blob/HEAD/UGformerV2_PyTorch/train_UGformerV2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6fa85bb11337eaf8"}},{"code_sha256_prefix":"4cae232bef92f0a0","entry":"get_graphpool","repo":"daiquocnguyen/Graph-Transformer","repo_kind":"official","path":"UGformerV1_PyTorch/train_UGformerV1_Sup.py","file_url":"https://github.com/daiquocnguyen/Graph-Transformer/blob/HEAD/UGformerV1_PyTorch/train_UGformerV1_Sup.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4cae232bef92f0a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}