{"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/non-backtracking-graph-neural-networks","title":"Non-backtracking Graph Neural Networks","arxiv_id":"2310.07430","date":"2023-10-11","proceeding":null,"authors":["Seonghyun Park","Narae Ryu","Gahee Kim","Dongyeop Woo","Se-Young Yun","Sungsoo Ahn"],"abstract":"The celebrated message-passing updates for graph neural networks allow representing large-scale graphs with local and computationally tractable updates. However, the updates suffer from backtracking, i.e., a message flowing through the same edge twice and revisiting the previously visited node. Since the number of message flows increases exponentially with the number of updates, the redundancy in local updates prevents the graph neural network from accurately recognizing a particular message flow relevant for downstream tasks. In this work, we propose to resolve such a redundancy issue via the non-backtracking graph neural network (NBA-GNN) that updates a message without incorporating the message from the previously visited node. We theoretically investigate how NBA-GNN alleviates the over-squashing of GNNs, and establish a connection between NBA-GNN and the impressive performance of non-backtracking updates for stochastic block model recovery. Furthermore, we empirically verify the effectiveness of our NBA-GNN on the long-range graph benchmark and transductive node classification problems.","url_abs":"https://arxiv.org/abs/2310.07430v2","url_pdf":"https://arxiv.org/pdf/2310.07430v2.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":"non-backtracking-graph-neural-networks","repo_url":"https://github.com/seonghyun26/nba-gnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"stochastic-block-model","task_name":"Stochastic Block Model"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.07430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07430"}},"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/seonghyun26/nba-gnn","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"1bb331bf70a78136","entry":"get_final_pretrained_ckpt","repo":"seonghyun26/nba-gnn","repo_kind":"official","path":"lrgb/graphgps/finetuning.py","file_url":"https://github.com/seonghyun26/nba-gnn/blob/HEAD/lrgb/graphgps/finetuning.py","link_basis":"harvester_set","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":"1bb331bf70a78136"}},{"code_sha256_prefix":"8653a762bb268420","entry":"init_model_from_pretrained","repo":"seonghyun26/nba-gnn","repo_kind":"official","path":"lrgb/graphgps/finetuning.py","file_url":"https://github.com/seonghyun26/nba-gnn/blob/HEAD/lrgb/graphgps/finetuning.py","link_basis":"harvester_set","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":"8653a762bb268420"}},{"code_sha256_prefix":"affe04943f6ee017","entry":"join_list","repo":"seonghyun26/nba-gnn","repo_kind":"official","path":"lrgb/aggr_results/agg_runs.py","file_url":"https://github.com/seonghyun26/nba-gnn/blob/HEAD/lrgb/aggr_results/agg_runs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"affe04943f6ee017"}},{"code_sha256_prefix":"ae56bcfaae96da3c","entry":"apply_chunking_to_forward","repo":"seonghyun26/nba-gnn","repo_kind":"official","path":"lrgb/graphgps/layer/bigbird_layer.py","file_url":"https://github.com/seonghyun26/nba-gnn/blob/HEAD/lrgb/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae56bcfaae96da3c"}},{"code_sha256_prefix":"995500eb98f90144","entry":"load_pretrained_model_cfg","repo":"seonghyun26/nba-gnn","repo_kind":"official","path":"lrgb/graphgps/finetuning.py","file_url":"https://github.com/seonghyun26/nba-gnn/blob/HEAD/lrgb/graphgps/finetuning.py","link_basis":"harvester_set","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":"995500eb98f90144"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}