{"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/few-shot-learning-with-graph-neural-networks","title":"Few-Shot Learning with Graph Neural Networks","arxiv_id":"1711.04043","date":"2017-11-10","proceeding":null,"authors":["Victor Garcia","Joan Bruna"],"abstract":"We propose to study the problem of few-shot learning with the prism of\ninference on a partially observed graphical model, constructed from a\ncollection of input images whose label can be either observed or not. By\nassimilating generic message-passing inference algorithms with their\nneural-network counterparts, we define a graph neural network architecture that\ngeneralizes several of the recently proposed few-shot learning models. Besides\nproviding improved numerical performance, our framework is easily extended to\nvariants of few-shot learning, such as semi-supervised or active learning,\ndemonstrating the ability of graph-based models to operate well on 'relational'\ntasks.","url_abs":"http://arxiv.org/abs/1711.04043v3","url_pdf":"http://arxiv.org/pdf/1711.04043v3.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":"few-shot-learning-with-graph-neural-networks","repo_url":"https://github.com/vgsatorras/few-shot-gnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"few-shot-learning-with-graph-neural-networks","repo_url":"https://github.com/HoganZhang/few-shot-gnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"few-shot-learning-with-graph-neural-networks","repo_url":"https://github.com/Lieberk/Paddle-FSL-GNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"few-shot-learning-with-graph-neural-networks","repo_url":"https://github.com/louis2889184/gnn_few_shot_cifar100","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"few-shot-learning-with-graph-neural-networks","repo_url":"https://github.com/suvarna-kadam/Oct2018_Demo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"few-shot-learning-with-graph-neural-networks","repo_url":"https://github.com/xxxnhb/few-shot-gnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"cross-domain-few-shot","task_name":"Cross-Domain Few-Shot"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-few-shot-on-chestx","task":"Cross-Domain Few-Shot","dataset":"ChestX","model":"GNN","rank_in_archive_order":6,"of":11,"metrics":{"5 shot":"25.27"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-on-eurosat","task":"Cross-Domain Few-Shot","dataset":"EuroSAT","model":"GNN","rank_in_archive_order":7,"of":11,"metrics":{"5 shot":"83.64"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-on-isic2018","task":"Cross-Domain Few-Shot","dataset":"ISIC2018","model":"GNN","rank_in_archive_order":10,"of":11,"metrics":{"5 shot":"43.94"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-2","task":"Few-Shot Image Classification","dataset":"Stanford Cars 5-way (1-shot)","model":"GNN++","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"55.85"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-3","task":"Few-Shot Image Classification","dataset":"Stanford Cars 5-way (5-shot)","model":"GNN++","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"71.25"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-1","task":"Few-Shot Image Classification","dataset":"Stanford Dogs 5-way (5-shot)","model":"GNN++","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"62.27"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.04043","atlas_url":"https://app.syntology.ai/?focus=1711.04043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.04043"}},"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/HoganZhang/few-shot-gnn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/suvarna-kadam/Oct2018_Demo","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vgsatorras/few-shot-gnn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xxxnhb/few-shot-gnn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Lieberk/Paddle-FSL-GNN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/louis2889184/gnn_few_shot_cifar100","reach":{"status":"ok"}}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"346e55cd35e8bf35","entry":"gmul","repo":"HoganZhang/few-shot-gnn","repo_kind":"listed","path":"models/gnn_iclr.py","file_url":"https://github.com/HoganZhang/few-shot-gnn/blob/HEAD/models/gnn_iclr.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"346e55cd35e8bf35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}