{"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/attention-based-graph-neural-network-for-semi","title":"Attention-based Graph Neural Network for Semi-supervised Learning","arxiv_id":"1803.03735","date":"2018-03-10","proceeding":"ICLR 2018 1","authors":["Kiran K. Thekumparampil","Chong Wang","Sewoong Oh","Li-Jia Li"],"abstract":"Recently popularized graph neural networks achieve the state-of-the-art\naccuracy on a number of standard benchmark datasets for graph-based\nsemi-supervised learning, improving significantly over existing approaches.\nThese architectures alternate between a propagation layer that aggregates the\nhidden states of the local neighborhood and a fully-connected layer. Perhaps\nsurprisingly, we show that a linear model, that removes all the intermediate\nfully-connected layers, is still able to achieve a performance comparable to\nthe state-of-the-art models. This significantly reduces the number of\nparameters, which is critical for semi-supervised learning where number of\nlabeled examples are small. This in turn allows a room for designing more\ninnovative propagation layers. Based on this insight, we propose a novel graph\nneural network that removes all the intermediate fully-connected layers, and\nreplaces the propagation layers with attention mechanisms that respect the\nstructure of the graph. The attention mechanism allows us to learn a dynamic\nand adaptive local summary of the neighborhood to achieve more accurate\npredictions. In a number of experiments on benchmark citation networks\ndatasets, we demonstrate that our approach outperforms competing methods. By\nexamining the attention weights among neighbors, we show that our model\nprovides some interesting insights on how neighbors influence each other.","url_abs":"http://arxiv.org/abs/1803.03735v1","url_pdf":"http://arxiv.org/pdf/1803.03735v1.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":"attention-based-graph-neural-network-for-semi","repo_url":"https://github.com/dawnranger/pytorch-AGNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"graph-regression","task_name":"Graph Regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-regression-on-lipophilicity","task":"Graph Regression","dataset":"Lipophilicity","model":"AGNN","rank_in_archive_order":19,"of":23,"metrics":{"RMSE":"0.963"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.03735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03735"}},"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/dawnranger/pytorch-AGNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"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":"3ab88254add4c192","entry":"encode_onehot","repo":"dawnranger/pytorch-AGNN","repo_kind":"listed","path":"agnn/utils.py","file_url":"https://github.com/dawnranger/pytorch-AGNN/blob/HEAD/agnn/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab88254add4c192"}},{"code_sha256_prefix":"aa9c29936dee40a7","entry":"normalize","repo":"dawnranger/pytorch-AGNN","repo_kind":"listed","path":"agnn/utils.py","file_url":"https://github.com/dawnranger/pytorch-AGNN/blob/HEAD/agnn/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa9c29936dee40a7"}},{"code_sha256_prefix":"12640e00f97f4319","entry":"load_data","repo":"dawnranger/pytorch-AGNN","repo_kind":"listed","path":"agnn/utils.py","file_url":"https://github.com/dawnranger/pytorch-AGNN/blob/HEAD/agnn/utils.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":"12640e00f97f4319"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}