{"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/end-to-end-structure-aware-convolutional","title":"End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion","arxiv_id":"1811.04441","date":"2018-11-11","proceeding":null,"authors":["Chao Shang","Yun Tang","Jing Huang","Jinbo Bi","Xiaodong He","Bo-Wen Zhou"],"abstract":"Knowledge graph embedding has been an active research topic for knowledge\nbase completion, with progressive improvement from the initial TransE, TransH,\nDistMult et al to the current state-of-the-art ConvE. ConvE uses 2D convolution\nover embeddings and multiple layers of nonlinear features to model knowledge\ngraphs. The model can be efficiently trained and scalable to large knowledge\ngraphs. However, there is no structure enforcement in the embedding space of\nConvE. The recent graph convolutional network (GCN) provides another way of\nlearning graph node embedding by successfully utilizing graph connectivity\nstructure. In this work, we propose a novel end-to-end Structure-Aware\nConvolutional Network (SACN) that takes the benefit of GCN and ConvE together.\nSACN consists of an encoder of a weighted graph convolutional network (WGCN),\nand a decoder of a convolutional network called Conv-TransE. WGCN utilizes\nknowledge graph node structure, node attributes and edge relation types. It has\nlearnable weights that adapt the amount of information from neighbors used in\nlocal aggregation, leading to more accurate embeddings of graph nodes. Node\nattributes in the graph are represented as additional nodes in the WGCN. The\ndecoder Conv-TransE enables the state-of-the-art ConvE to be translational\nbetween entities and relations while keeps the same link prediction performance\nas ConvE. We demonstrate the effectiveness of the proposed SACN on standard\nFB15k-237 and WN18RR datasets, and it gives about 10% relative improvement over\nthe state-of-the-art ConvE in terms of HITS@1, HITS@3 and HITS@10.","url_abs":"http://arxiv.org/abs/1811.04441v2","url_pdf":"http://arxiv.org/pdf/1811.04441v2.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":"end-to-end-structure-aware-convolutional","repo_url":"https://github.com/JD-AI-Research-Silicon-Valley/SACN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-base-completion","task_name":"Knowledge Base Completion"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"transe","method_name":"TransE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"Structure-Aware Convolutional Networks","rank_in_archive_order":30,"of":75,"metrics":{"Hits@1":"0.26","Hits@10":"0.54","Hits@3":"0.39","MRR":"0.35"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"Structure-Aware Convolutional Networks","rank_in_archive_order":56,"of":75,"metrics":{"Hits@1":"0.43","Hits@10":"0.54","Hits@3":"0.48","MRR":"0.47"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.04441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04441"}},"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/JD-AI-Research-Silicon-Valley/SACN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"24ef53c5c5b147a5","entry":"check_for_reversible_relations","repo":"JD-AI-Research-Silicon-Valley/SACN","repo_kind":"official","path":"inverse_model.py","file_url":"https://github.com/JD-AI-Research-Silicon-Valley/SACN/blob/HEAD/inverse_model.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":"24ef53c5c5b147a5"}},{"code_sha256_prefix":"35195ac220d2639d","entry":"get_list_of_torch_modules","repo":"JD-AI-Research-Silicon-Valley/SACN","repo_kind":"official","path":"src/spodernet/spodernet/backends/torchbackend.py","file_url":"https://github.com/JD-AI-Research-Silicon-Valley/SACN/blob/HEAD/src/spodernet/spodernet/backends/torchbackend.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":"35195ac220d2639d"}},{"code_sha256_prefix":"bcbee6026f554da1","entry":"predictor","repo":"JD-AI-Research-Silicon-Valley/SACN","repo_kind":"official","path":"src/spodernet/spodernet/backends/tfmodels.py","file_url":"https://github.com/JD-AI-Research-Silicon-Valley/SACN/blob/HEAD/src/spodernet/spodernet/backends/tfmodels.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":"bcbee6026f554da1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}