{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T03:01:31Z","timestamp":1792724491749,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272250, U22B2048, 62077031"],"award-info":[{"award-number":["62272250, U22B2048, 62077031"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Natural Science Foundation of Tianjin City","doi-asserted-by":"publisher","award":["22JCJQJC00150, 22JCQNJC01580"],"award-info":[{"award-number":["22JCJQJC00150, 22JCQNJC01580"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657838","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"102-111","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Contrast then Memorize: Semantic Neighbor Retrieval-Enhanced Inductive Multimodal Knowledge Graph Completion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0326-7152","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer Science, VCIP, TMCC, TBI Center, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8473-1326","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science, VCIP, TMCC, TBI Center, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7577-6204","authenticated-orcid":false,"given":"Baohang","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer Science, VCIP, TMCC, TBI Center, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8299-8275","authenticated-orcid":false,"given":"Xinying","family":"Qian","sequence":"additional","affiliation":[{"name":"College of Computer Science, VCIP, TMCC, TBI Center, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9694-6359","authenticated-orcid":false,"given":"Kehui","family":"Song","sequence":"additional","affiliation":[{"name":"School of Software, Tiangong University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5039-0922","authenticated-orcid":false,"given":"Xiangrui","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Computer Science, VCIP, TMCC, TBI Center, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Translating embeddings for modeling multi-relational data. Advances in neural information processing systems","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_2_1","first-page":"39090","article-title":"Otkge: Multi-modal knowledge graph embeddings via optimal transport","volume":"35","author":"Cao Zongsheng","year":"2022","unstructured":"Zongsheng Cao, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, and Qingming Huang. 2022. Otkge: Multi-modal knowledge graph embeddings via optimal transport. Advances in Neural Information Processing Systems, Vol. 35 (2022), 39090--39102.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531746"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"e_1_3_2_1_5_1","volume-title":"Inductively representing out-of-knowledge-graph entities by optimal estimation under translational assumptions. arXiv preprint arXiv:2009.12765","author":"Dai Damai","year":"2020","unstructured":"Damai Dai, Hua Zheng, Fuli Luo, Pengcheng Yang, Baobao Chang, and Zhifang Sui. 2020. Inductively representing out-of-knowledge-graph entities by optimal estimation under translational assumptions. arXiv preprint arXiv:2009.12765 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450141"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 1263--1272","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. In International conference on machine learning. PMLR, 1263--1272."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Learning Representations.","author":"Khandelwal Urvashi","year":"2019","unstructured":"Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2019. Generalization through Memorization: Nearest Neighbor Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","unstructured":"Timoth\u00e9e Lacroix Nicolas Usunier and Guillaume Obozinski. 2018. Canonical tensor decomposition for knowledge base completion. In ICML. PMLR 2863--2872."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583554"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.601"},{"key":"e_1_3_2_1_18_1","volume-title":"Reasoning over different types of knowledge graphs: Static, temporal and multi-modal. arXiv preprint arXiv:2212.05767","author":"Liang Ke","year":"2022","unstructured":"Ke Liang, Lingyuan Meng, Meng Liu, Yue Liu, Wenxuan Tu, Siwei Wang, Sihang Zhou, Xinwang Liu, and Fuchun Sun. 2022. Reasoning over different types of knowledge graphs: Static, temporal and multi-modal. arXiv preprint arXiv:2212.05767 (2022)."},{"key":"e_1_3_2_1_19_1","volume-title":"Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning. arXiv preprint arXiv:2307.03591","author":"Liang Ke","year":"2023","unstructured":"Ke Liang, Sihang Zhou, Yue Liu, Lingyuan Meng, Meng Liu, and Xinwang Liu. 2023. Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning. arXiv preprint arXiv:2307.03591 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.234"},{"key":"e_1_3_2_1_21_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"Ok-vqa: A visual question answering benchmark requiring external knowledge. In CVPR. 3195--3204.","author":"Marino Kenneth","year":"2019","unstructured":"Kenneth Marino, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. 2019. Ok-vqa: A visual question answering benchmark requiring external knowledge. In CVPR. 3195--3204."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.46"},{"key":"e_1_3_2_1_24_1","volume-title":"Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734","author":"Mokady Ron","year":"2021","unstructured":"Ron Mokady, Amir Hertz, and Amit H Bermano. 2021. Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Pouya Pezeshkpour Liyan Chen and Sameer Singh. 2018. Embedding Multimodal Relational Data for Knowledge Base Completion. In EMNLP. 3208--3218.","DOI":"10.18653\/v1\/D18-1359"},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Rui Sun Xuezhi Cao Yan Zhao Junchen Wan Kun Zhou Fuzheng Zhang Zhongyuan Wang and Kai Zheng. 2020. Multi-modal knowledge graphs for recommender systems. In CIKM. 1405--1414.","DOI":"10.1145\/3340531.3411947"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583412"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Kristina Toutanova Danqi Chen Patrick Pantel Hoifung Poon Pallavi Choudhury and Michael Gamon. 2015. Representing text for joint embedding of text and knowledge bases. In EMNLP. 1499--1509.","DOI":"10.18653\/v1\/D15-1174"},{"key":"e_1_3_2_1_31_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450043"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475470"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017152"},{"key":"e_1_3_2_1_35_1","volume-title":"k NN-NER: Named Entity Recognition with Nearest Neighbor Search. arXiv preprint arXiv:2203.17103","author":"Wang Shuhe","year":"2022","unstructured":"Shuhe Wang, Xiaoya Li, Yuxian Meng, Tianwei Zhang, Rongbin Ouyang, Jiwei Li, and Guoyin Wang. 2022. k NN-NER: Named Entity Recognition with Nearest Neighbor Search. arXiv preprint arXiv:2203.17103 (2022)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852079"},{"key":"e_1_3_2_1_37_1","volume-title":"Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush.","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In EMNLP. 38--45."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10329"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Ruobing Xie Zhiyuan Liu Huanbo Luan and Maosong Sun. 2017. Image-embodied knowledge representation learning. In IJCAI. 3140--3146.","DOI":"10.24963\/ijcai.2017\/438"},{"key":"e_1_3_2_1_40_1","volume-title":"KG-BERT: BERT for knowledge graph completion. arXiv preprint arXiv:1909.03193","author":"Yao Liang","year":"2019","unstructured":"Liang Yao, Chengsheng Mao, and Yuan Luo. 2019. KG-BERT: BERT for knowledge graph completion. arXiv preprint arXiv:1909.03193 (2019)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591763"},{"key":"e_1_3_2_1_42_1","volume-title":"Reasoning through memorization: Nearest neighbor knowledge graph embeddings. arXiv preprint arXiv:2201.05575","author":"Zhang Ningyu","year":"2022","unstructured":"Ningyu Zhang, Xin Xie, Xiang Chen, Yongheng Wang, Xu Cheng, and Huajun Chen. 2022. Reasoning through memorization: Nearest neighbor knowledge graph embeddings. arXiv preprint arXiv:2201.05575 (2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.719"},{"key":"e_1_3_2_1_44_1","volume-title":"Multi-Modal Knowledge Graph Construction and Application: A Survey. arXiv preprint arXiv:2202.05786","author":"Zhu Xiangru","year":"2022","unstructured":"Xiangru Zhu, Zhixu Li, Xiaodan Wang, Xueyao Jiang, Penglei Sun, Xuwu Wang, Yanghua Xiao, and Nicholas Jing Yuan. 2022. Multi-Modal Knowledge Graph Construction and Application: A Survey. arXiv preprint arXiv:2202.05786 (2022)."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657838","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:40:19Z","timestamp":1755841219000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":44,"alternative-id":["10.1145\/3626772.3657838","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657838","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}