{"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/attending-to-graph-transformers","title":"Attending to Graph Transformers","arxiv_id":"2302.04181","date":"2023-02-08","proceeding":null,"authors":["Luis Müller","Mikhail Galkin","Christopher Morris","Ladislav Rampášek"],"abstract":"Recently, transformer architectures for graphs emerged as an alternative to established techniques for machine learning with graphs, such as (message-passing) graph neural networks. So far, they have shown promising empirical results, e.g., on molecular prediction datasets, often attributed to their ability to circumvent graph neural networks' shortcomings, such as over-smoothing and over-squashing. Here, we derive a taxonomy of graph transformer architectures, bringing some order to this emerging field. We overview their theoretical properties, survey structural and positional encodings, and discuss extensions for important graph classes, e.g., 3D molecular graphs. Empirically, we probe how well graph transformers can recover various graph properties, how well they can deal with heterophilic graphs, and to what extent they prevent over-squashing. Further, we outline open challenges and research direction to stimulate future work. Our code is available at https://github.com/luis-mueller/probing-graph-transformers.","url_abs":"https://arxiv.org/abs/2302.04181v3","url_pdf":"https://arxiv.org/pdf/2302.04181v3.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":"attending-to-graph-transformers","repo_url":"https://github.com/luis-mueller/probing-graph-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"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":"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":{"atlas_url":"https://app.syntology.ai/?focus=2302.04181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04181"}},"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/luis-mueller/probing-graph-transformers","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":6},"by_repo_kind":{"official":{"samples":8,"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":"1bb331bf70a78136","entry":"get_final_pretrained_ckpt","repo":"luis-mueller/probing-graph-transformers","repo_kind":"official","path":"graphgps/finetuning.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/finetuning.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":"1bb331bf70a78136"}},{"code_sha256_prefix":"55e0e3e0c19f368e","entry":"graph_token_pooling","repo":"luis-mueller/probing-graph-transformers","repo_kind":"official","path":"graphgps/pooling/graph_token.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/pooling/graph_token.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":"55e0e3e0c19f368e"}},{"code_sha256_prefix":"ae56bcfaae96da3c","entry":"apply_chunking_to_forward","repo":"luis-mueller/probing-graph-transformers","repo_kind":"official","path":"graphgps/layer/bigbird_layer.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/layer/bigbird_layer.py","link_basis":"harvester_set","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":"ae56bcfaae96da3c"}},{"code_sha256_prefix":"3db4474abe13fdee","entry":"init_model_from_pretrained","repo":"luis-mueller/probing-graph-transformers","repo_kind":"official","path":"graphgps/finetuning.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/finetuning.py","link_basis":"harvester_set","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":"3db4474abe13fdee"}},{"code_sha256_prefix":"c98a702be0660ac9","entry":"is_seed","repo":"luis-mueller/probing-graph-transformers","repo_kind":"official","path":"graphgps/agg_runs.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/agg_runs.py","link_basis":"harvester_set","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":"c98a702be0660ac9"}},{"code_sha256_prefix":"438635c08adfe2aa","entry":"is_split","repo":"luis-mueller/probing-graph-transformers","repo_kind":"official","path":"graphgps/agg_runs.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/agg_runs.py","link_basis":"harvester_set","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":"438635c08adfe2aa"}},{"code_sha256_prefix":"40e98e1ecbf39f34","entry":"join_list","repo":"luis-mueller/probing-graph-transformers","repo_kind":"official","path":"graphgps/agg_runs.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/agg_runs.py","link_basis":"harvester_set","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":"40e98e1ecbf39f34"}},{"code_sha256_prefix":"d796cdea5889c847","entry":"load_pretrained_model_cfg","repo":"luis-mueller/probing-graph-transformers","repo_kind":"official","path":"graphgps/finetuning.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/finetuning.py","link_basis":"harvester_set","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":"d796cdea5889c847"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}