{"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/zero-shot-learning-with-common-sense","title":"Zero-Shot Learning with Common Sense Knowledge Graphs","arxiv_id":"2006.10713","date":"2020-06-18","proceeding":null,"authors":["Nihal V. Nayak","Stephen H. Bach"],"abstract":"Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples. We propose to learn class representations by embedding nodes from common sense knowledge graphs in a vector space. Common sense knowledge graphs are an untapped source of explicit high-level knowledge that requires little human effort to apply to a range of tasks. To capture the knowledge in the graph, we introduce ZSL-KG, a general-purpose framework with a novel transformer graph convolutional network (TrGCN) for generating class representations. Our proposed TrGCN architecture computes non-linear combinations of node neighbourhoods. Our results show that ZSL-KG improves over existing WordNet-based methods on five out of six zero-shot benchmark datasets in language and vision.","url_abs":"https://arxiv.org/abs/2006.10713v4","url_pdf":"https://arxiv.org/pdf/2006.10713v4.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":"zero-shot-learning-with-common-sense","repo_url":"https://github.com/BatsResearch/nayak-arxiv20-code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zero-shot-learning-with-common-sense","repo_url":"https://github.com/BatsResearch/zsl-kg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zero-shot-learning-with-common-sense","repo_url":"https://github.com/batsresearch/nayak-tmlr22-code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"generalized-zero-shot-learning","task_name":"Generalized Zero-Shot Learning"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-zero-shot-learning-on-awa2","task":"Generalized Zero-Shot Learning","dataset":"AwA2","model":"ZSL-KG","rank_in_archive_order":2,"of":4,"metrics":{"Harmonic mean":"74.58"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-bbn-pronoun","task":"Generalized Zero-Shot Learning","dataset":"BBN Pronoun Coreference and Entity Type Corpus","model":"ZSL-KG","rank_in_archive_order":1,"of":1,"metrics":{"F1":"26.69"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-ontonotes","task":"Generalized Zero-Shot Learning","dataset":"OntoNotes","model":"ZSL-KG","rank_in_archive_order":1,"of":1,"metrics":{"F1":"45.21"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-apy-0-shot","task":"Generalized Zero-Shot Learning","dataset":"aPY - 0-Shot","model":"ZSL-KG","rank_in_archive_order":1,"of":1,"metrics":{"Harmonic mean":"61.57"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-awa2","task":"Zero-Shot Learning","dataset":"AwA2","model":"ZSL-KG","rank_in_archive_order":2,"of":4,"metrics":{"average top-1 classification accuracy":"78.08"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-snips","task":"Zero-Shot Learning","dataset":"SNIPS","model":"ZSL-KG","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"88.98"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-apy-0-shot","task":"Zero-Shot Learning","dataset":"aPY - 0-Shot","model":"ZSL-KG","rank_in_archive_order":1,"of":1,"metrics":{"Top-1":"60.54"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.10713","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}