{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T03:46:15Z","timestamp":1772336775872,"version":"3.50.1"},"reference-count":33,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"content-version":"vor","delay-in-days":247,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In the task of Knowledge Graph Completion (KGC), the existing datasets and their inherent subtasks carry a wealth of shared knowledge that can be utilized to enhance the representation of knowledge triplets and overall performance. However, no current studies specifically address the shared knowledge within KGC. To bridge this gap, we introduce a multi-level Shared Knowledge Guided learning method (SKG) that operates at both the dataset and task levels. On the dataset level, SKG-KGC broadens the original dataset by identifying shared features within entity sets via text summarization. On the task level, for the three typical KGC subtasks\u2014head entity prediction, relation prediction, and tail entity prediction\u2014we present an innovative multi-task learning architecture with dynamically adjusted loss weights. This approach allows the model to focus on more challenging and underperforming tasks, effectively mitigating the imbalance of knowledge sharing among subtasks. Experimental results demonstrate that SKG-KGC outperforms existing text-based methods significantly on three well-known datasets, with the most notable improvement on WN18RR (MRR: 66.6%\u2192 72.2%, Hit@1: 58.7%\u219267.0%).<\/jats:p>","DOI":"10.1162\/tacl_a_00686","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T13:34:31Z","timestamp":1725456871000},"page":"1027-1042","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion"],"prefix":"10.1162","volume":"12","author":[{"given":"Yongxue","family":"Shan","sequence":"first","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China. shanyongxue001@nudt.edu.cn"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China. jiezhou@nudt.edu.cn"}]},{"given":"Jie","family":"Peng","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China. pengjie@nudt.edu.cn"}]},{"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China. zhouxin.130@nudt.edu.cn"}]},{"given":"Jiaqian","family":"Yin","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China. yinjiaqian@nudt.edu.cn"}]},{"given":"Xiaodong","family":"Wang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China. xdwang@nudt.edu.cn"}]}],"member":"281","published-online":{"date-parts":[[2024,9,4]]},"reference":[{"key":"2024090413342185600_bib1","doi-asserted-by":"publisher","first-page":"5185","DOI":"10.18653\/v1\/D19-1522","article-title":"TuckER: Tensor factorization for knowledge graph completion","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Balazevic","year":"2019"},{"key":"2024090413342185600_bib2","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1145\/1376616.1376746","article-title":"Freebase: A collaboratively created graph database for structuring human knowledge","volume-title":"Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data","author":"Bollacker","year":"2008"},{"key":"2024090413342185600_bib3","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2","author":"Bordes","year":"2013"},{"issue":"6","key":"2024090413342185600_bib4","doi-asserted-by":"publisher","first-page":"102124","DOI":"10.1016\/j.ipm.2019.102124","article-title":"Building a morpho-semantic knowledge graph for Arabic information retrieval","volume":"57","author":"Bounhas","year":"2020","journal-title":"Information Processing & Management"},{"key":"2024090413342185600_bib5","doi-asserted-by":"publisher","first-page":"11489","DOI":"10.18653\/v1\/2023.findings-acl.729","article-title":"Dipping PLMs sauce: Bridging structure and text for effective knowledge graph completion via conditional soft prompting","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Chen","year":"2023"},{"key":"2024090413342185600_bib6","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1145\/3442381.3450141","article-title":"Inductive entity representations from text via link prediction","volume-title":"Proceedings of the Web Conference 2021","author":"Daza","year":"2021"},{"key":"2024090413342185600_bib7","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.1609\/aaai.v32i1.11573","article-title":"Convolutional 2D knowledge graph embeddings","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence","author":"Dettmers","year":"2018"},{"key":"2024090413342185600_bib8","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/978-3-030-73194-6_17","article-title":"A novel embedding model for knowledge graph completion based on multi-task learning","volume-title":"Database Systems for Advanced Applications: 26th International Conference, DASFAA 2021","author":"Dou","year":"2021"},{"issue":"10","key":"2024090413342185600_bib9","doi-asserted-by":"publisher","first-page":"10281","DOI":"10.1109\/TKDE.2023.3251897","article-title":"Enhanced multi-task learning and knowledge graph-based recommender system","volume":"35","author":"Gao","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2024090413342185600_bib10","doi-asserted-by":"publisher","first-page":"2600","DOI":"10.1145\/3543507.3583358","article-title":"Link prediction with attention applied on multiple knowledge graph embedding models","volume-title":"Proceedings of the ACM Web Conference 2023","author":"Gregucci","year":"2023"},{"key":"2024090413342185600_bib11","article-title":"Knowledge base completion: Baseline strikes back (again)","author":"Jain","year":"2020","journal-title":"CoRR"},{"key":"2024090413342185600_bib12","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.18653\/v1\/2020.coling-main.153","article-title":"Multi-task learning for knowledge graph completion with pre-trained language models","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics","author":"Kim","year":"2020"},{"key":"2024090413342185600_bib13","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Lan","year":"2020"},{"issue":"11","key":"2024090413342185600_bib14","doi-asserted-by":"publisher","DOI":"10.1145\/3627704","article-title":"Multi-task pre-training language model for semantic network completion","volume":"22","author":"Da","year":"2023","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing"},{"issue":"2","key":"2024090413342185600_bib15","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2024090413342185600_bib16","doi-asserted-by":"publisher","first-page":"3570","DOI":"10.18653\/v1\/2022.findings-acl.282","article-title":"Do pre-trained models benefit knowledge graph completion? A reliable evaluation and a reasonable approach","volume-title":"Findings of the Association for Computational Linguistics: ACL 2022","author":"Lv","year":"2022"},{"key":"2024090413342185600_bib17","first-page":"404","article-title":"TextRank: Bringing order into text","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing","author":"Mihalcea","year":"2004"},{"issue":"11","key":"2024090413342185600_bib18","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","article-title":"WordNet: A lexical database for english","volume":"38","author":"Miller","year":"1995","journal-title":"Communications of the ACM"},{"key":"2024090413342185600_bib19","doi-asserted-by":"publisher","first-page":"103866","DOI":"10.1016\/j.compbiomed.2020.103866","article-title":"Electrocardiogram heartbeat classification based on a deep convolutional neural network and focal loss","volume":"123","author":"Romdhane","year":"2020","journal-title":"Computers in Biology and Medicine"},{"key":"2024090413342185600_bib20","doi-asserted-by":"publisher","first-page":"2814","DOI":"10.18653\/v1\/2022.acl-long.201","article-title":"Sequence-to-sequence knowledge graph completion and question answering","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Saxena","year":"2022"},{"key":"2024090413342185600_bib21","doi-asserted-by":"publisher","first-page":"4498","DOI":"10.18653\/v1\/2020.acl-main.412","article-title":"Improving multi-hop question answering over knowledge graphs using knowledge base embeddings","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Saxena","year":"2020"},{"key":"2024090413342185600_bib22","article-title":"RotatE: Knowledge graph embedding by relational rotation in complex space","volume-title":"7th International Conference on Learning Representations","author":"Sun","year":"2019"},{"issue":"10","key":"2024090413342185600_bib23","doi-asserted-by":"publisher","first-page":"1495","DOI":"10.3390\/e24101495","article-title":"Multi-task learning and improved TextRank for knowledge graph completion","volume":"24","author":"Tian","year":"2022","journal-title":"Entropy"},{"key":"2024090413342185600_bib24","doi-asserted-by":"publisher","first-page":"57","DOI":"10.18653\/v1\/W15-4007","article-title":"Observed versus latent features for knowledge base and text inference","volume-title":"Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality","author":"Toutanova","year":"2015"},{"key":"2024090413342185600_bib25","first-page":"2071","article-title":"Complex embeddings for simple link prediction","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning","author":"Trouillon","year":"2016"},{"key":"2024090413342185600_bib26","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.1145\/3442381.3450043","article-title":"Structure-augmented text representation learning for efficient knowledge graph completion","volume-title":"Proceedings of the Web Conference 2021","author":"Bo","year":"2021"},{"key":"2024090413342185600_bib27","doi-asserted-by":"publisher","first-page":"4281","DOI":"10.18653\/v1\/2022.acl-long.295","article-title":"SimKGC: Simple contrastive knowledge graph completion with pre-trained language models","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Wang","year":"2022"},{"key":"2024090413342185600_bib28","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1162\/tacl_a_00360","article-title":"KEPLER: A unified model for knowledge embedding and pre-trained language representation","volume":"9","author":"Wang","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2024090413342185600_bib29","doi-asserted-by":"publisher","first-page":"2659","DOI":"10.1609\/aaai.v30i1.10329","article-title":"Representation learning of knowledge graphs with entity descriptions","volume-title":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","author":"Xie","year":"2016"},{"key":"2024090413342185600_bib30","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1145\/3487553.3524238","article-title":"From discrimination to generation: Knowledge graph completion with generative transformer","volume-title":"Companion Proceedings of the Web Conference 2022","author":"Xie","year":"2022"},{"key":"2024090413342185600_bib31","doi-asserted-by":"publisher","first-page":"5370","DOI":"10.24963\/ijcai.2019\/746","article-title":"Improving multilingual sentence embedding using bi-directional dual encoder with additive margin softmax","volume-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19","author":"Yang","year":"2019"},{"key":"2024090413342185600_bib32","article-title":"KG-BERT: BERT for knowledge graph completion","author":"Yao","year":"2019","journal-title":"CoRR"},{"key":"2024090413342185600_bib33","article-title":"Exploring large language models for knowledge graph completion","author":"Yao","year":"2024","journal-title":"CoRR"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00686\/2468646\/tacl_a_00686.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00686\/2468646\/tacl_a_00686.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T13:34:40Z","timestamp":1725456880000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00686\/124257\/Multi-level-Shared-Knowledge-Guided-Learning-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00686","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}