{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/kgtn-ens-few-shot-image-classification-with","title":"KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles","arxiv_id":"2211.03199","date":"2022-11-06","proceeding":null,"authors":["Dominik Filipiak","Anna Fensel","Agata Filipowska"],"abstract":"We propose KGTN-ens, a framework extending the recent Knowledge Graph Transfer Network (KGTN) in order to incorporate multiple knowledge graph embeddings at a small cost. We evaluate it with different combinations of embeddings in a few-shot image classification task. We also construct a new knowledge source - Wikidata embeddings - and evaluate it with KGTN and KGTN-ens. Our approach outperforms KGTN in terms of the top-5 accuracy on the ImageNet-FS dataset for the majority of tested settings.","url_abs":"https://arxiv.org/abs/2211.03199v1","url_pdf":"https://arxiv.org/pdf/2211.03199v1.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":"kgtn-ens-few-shot-image-classification-with","repo_url":"https://github.com/DominikFilipiak/KGTN-ens","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-4","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (1-shot, all)","model":"KGTN-ens (ResNet-50, h+g, max)","rank_in_archive_order":1,"of":2,"metrics":{"Top-5 Accuracy (%)":"68.58"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (1-shot, novel)","model":"KGTN-ens (ResNet-50, h+g, max)","rank_in_archive_order":1,"of":7,"metrics":{"Top-5 Accuracy (%)":"62.73"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-7","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (10-shot, all)","model":"KGTN-ens (ResNet-50, h+g, max)","rank_in_archive_order":2,"of":2,"metrics":{"Top-5 Accuracy (%)":"83.46"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-3","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (10-shot, novel)","model":"KGTN-ens (ResNet-50, h+g, max)","rank_in_archive_order":1,"of":2,"metrics":{"Top-5 Accuracy (%)":"82.56"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-5","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (2-shot, all)","model":"KGTN-ens (ResNet-50, h+g, max)","rank_in_archive_order":1,"of":2,"metrics":{"Top-5 Accuracy (%)":"75.45"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-1","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (2-shot, novel)","model":"KGTN-ens (ResNet-50, h+g, max)","rank_in_archive_order":1,"of":8,"metrics":{"Top-5 Accuracy (%)":"71.48"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-6","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (5-shot, all)","model":"KGTN-ens (ResNet-50, h+g, max)","rank_in_archive_order":1,"of":8,"metrics":{"Top-5 Accuracy (%)":"81.12"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-fs-2","task":"Few-Shot Image Classification","dataset":"ImageNet-FS (5-shot, novel)","model":"KGTN-ens (ResNet-50, h+g, mean)","rank_in_archive_order":1,"of":3,"metrics":{"Top-5 Accuracy (%)":"78.90"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"DominikFilipiak/KGTN-ens","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2b9b4acf63bd69cc297021d1de6af6dd0e351c33b88491b9ef2be087eb2f2aff","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}