{"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/a-generalization-of-transformer-networks-to","title":"A Generalization of Transformer Networks to Graphs","arxiv_id":"2012.09699","date":"2020-12-17","proceeding":null,"authors":["Vijay Prakash Dwivedi","Xavier Bresson"],"abstract":"We propose a generalization of transformer neural network architecture for arbitrary graphs. The original transformer was designed for Natural Language Processing (NLP), which operates on fully connected graphs representing all connections between the words in a sequence. Such architecture does not leverage the graph connectivity inductive bias, and can perform poorly when the graph topology is important and has not been encoded into the node features. We introduce a graph transformer with four new properties compared to the standard model. First, the attention mechanism is a function of the neighborhood connectivity for each node in the graph. Second, the positional encoding is represented by the Laplacian eigenvectors, which naturally generalize the sinusoidal positional encodings often used in NLP. Third, the layer normalization is replaced by a batch normalization layer, which provides faster training and better generalization performance. Finally, the architecture is extended to edge feature representation, which can be critical to tasks s.a. chemistry (bond type) or link prediction (entity relationship in knowledge graphs). Numerical experiments on a graph benchmark demonstrate the performance of the proposed graph transformer architecture. This work closes the gap between the original transformer, which was designed for the limited case of line graphs, and graph neural networks, that can work with arbitrary graphs. As our architecture is simple and generic, we believe it can be used as a black box for future applications that wish to consider transformer and graphs.","url_abs":"https://arxiv.org/abs/2012.09699v2","url_pdf":"https://arxiv.org/pdf/2012.09699v2.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":"a-generalization-of-transformer-networks-to","repo_url":"https://github.com/graphdeeplearning/graphtransformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-generalization-of-transformer-networks-to","repo_url":"https://github.com/asarigun/DrugGEN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-generalization-of-transformer-networks-to","repo_url":"https://github.com/hubiodatalab/druggen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"}],"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":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"graph-transformer","method_name":"Graph Transformer"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"lapeigen","method_name":"LapEigen"},{"method_slug":"laplacian-pe","method_name":"Laplacian PE"},{"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.09699","atlas_url":"https://app.syntology.ai/?focus=2012.09699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.09699"}},"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/graphdeeplearning/graphtransformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asarigun/DrugGEN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hubiodatalab/druggen","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"654acacaf00954fb","entry":"scaled_exp","repo":"graphdeeplearning/graphtransformer","repo_kind":"official","path":"layers/graph_transformer_layer.py","file_url":"https://github.com/graphdeeplearning/graphtransformer/blob/HEAD/layers/graph_transformer_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"654acacaf00954fb"}},{"code_sha256_prefix":"23fba400cff6fafa","entry":"src_dot_dst","repo":"graphdeeplearning/graphtransformer","repo_kind":"official","path":"layers/graph_transformer_layer.py","file_url":"https://github.com/graphdeeplearning/graphtransformer/blob/HEAD/layers/graph_transformer_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23fba400cff6fafa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}