{"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/rethinking-knowledge-graph-propagation-for","title":"Rethinking Knowledge Graph Propagation for Zero-Shot Learning","arxiv_id":"1805.11724","date":"2018-05-29","proceeding":"CVPR 2019 6","authors":["Michael Kampffmeyer","Yinbo Chen","Xiaodan Liang","Hao Wang","Yu-jia Zhang","Eric P. Xing"],"abstract":"Graph convolutional neural networks have recently shown great potential for\nthe task of zero-shot learning. These models are highly sample efficient as\nrelated concepts in the graph structure share statistical strength allowing\ngeneralization to new classes when faced with a lack of data. However,\nmulti-layer architectures, which are required to propagate knowledge to distant\nnodes in the graph, dilute the knowledge by performing extensive Laplacian\nsmoothing at each layer and thereby consequently decrease performance. In order\nto still enjoy the benefit brought by the graph structure while preventing\ndilution of knowledge from distant nodes, we propose a Dense Graph Propagation\n(DGP) module with carefully designed direct links among distant nodes. DGP\nallows us to exploit the hierarchical graph structure of the knowledge graph\nthrough additional connections. These connections are added based on a node's\nrelationship to its ancestors and descendants. A weighting scheme is further\nused to weigh their contribution depending on the distance to the node to\nimprove information propagation in the graph. Combined with finetuning of the\nrepresentations in a two-stage training approach our method outperforms\nstate-of-the-art zero-shot learning approaches.","url_abs":"http://arxiv.org/abs/1805.11724v3","url_pdf":"http://arxiv.org/pdf/1805.11724v3.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":"rethinking-knowledge-graph-propagation-for","repo_url":"https://github.com/cyvius96/adgpm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"rethinking-knowledge-graph-propagation-for","repo_url":"https://github.com/cyvius96/DGP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"rethinking-knowledge-graph-propagation-for","repo_url":"https://github.com/yinboc/dgp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.11724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.11724"}},"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/cyvius96/DGP","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yinboc/dgp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cyvius96/adgpm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"listed":{"samples":1,"ran":0,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"cyvius96/adgpm","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/cyvius96/adgpm/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"6cf4f1c5a5508f6d","entry":"make_resnet_base","repo":"cyvius96/adgpm","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/cyvius96/adgpm/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","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":"6cf4f1c5a5508f6d"}},{"code_sha256_prefix":"2f5f8a535d807f12","entry":"test_on_subset","repo":"yinboc/dgp","repo_kind":"listed","path":"evaluate_imagenet.py","file_url":"https://github.com/yinboc/dgp/blob/HEAD/evaluate_imagenet.py","link_basis":"first_harvest_node","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":"2f5f8a535d807f12"}},{"code_sha256_prefix":"63253360ac13e718","entry":"test_on_subset","repo":"cyvius96/adgpm","repo_kind":"official","path":"evaluate_awa2.py","file_url":"https://github.com/cyvius96/adgpm/blob/HEAD/evaluate_awa2.py","link_basis":"first_harvest_node","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":"63253360ac13e718"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}