{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:46Z","timestamp":1784138926557,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809684","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"1812-1822","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1205-9492","authenticated-orcid":false,"given":"Junting","family":"Wang","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1629-8268","authenticated-orcid":false,"given":"Chenghuan","family":"Guo","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6390-2517","authenticated-orcid":false,"given":"Yang","family":"Jiao","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9908-3795","authenticated-orcid":false,"given":"Yanhui","family":"Guo","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3315-6055","authenticated-orcid":false,"given":"Hari","family":"Sundaram","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8012-1392","authenticated-orcid":false,"given":"Yan","family":"Gao","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944937"},{"key":"e_1_3_2_1_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_3_1","volume-title":"Representation Learning for Attributed Multiplex Heterogeneous Network. CoRR","author":"Cen Yukuo","year":"2019","unstructured":"Yukuo Cen, Xu Zou, Jianwei Zhang, Hongxia Yang, Jingren Zhou, and Jie Tang. 2019. Representation Learning for Attributed Multiplex Heterogeneous Network. CoRR, Vol. abs\/1905.01669 (2019). arXiv:1905.01669 http:\/\/arxiv.org\/abs\/1905.01669"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25532"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401042"},{"key":"e_1_3_2_1_6_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Alex Castro-Ros Marie Pellat Kevin Robinson Dasha Valter Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. arXiv:2210.11416 [cs.LG] https:\/\/arxiv.org\/abs\/2210.11416"},{"key":"e_1_3_2_1_7_1","unstructured":"Djork-Arn\u00e9 Clevert Thomas Unterthiner and Sepp Hochreiter. 2016. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). arXiv:1511.07289 [cs.LG] https:\/\/arxiv.org\/abs\/1511.07289"},{"key":"e_1_3_2_1_8_1","volume-title":"Toutanova","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina N. Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research","volume":"304","author":"Gutmann Michael","year":"2010","unstructured":"Michael Gutmann and Aapo Hyv\u00e4rinen. 2010. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 9), Yee Whye Teh and Mike Titterington (Eds.). PMLR, Chia Laguna Resort, Sardinia, Italy, 297-304. https:\/\/proceedings.mlr.press\/v9\/gutmann10a.html"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412732"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.361"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3774904.3792294"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645626"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615039"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651552"},{"key":"e_1_3_2_1_16_1","unstructured":"Diederik P Kingma and Max Welling. 2022. Auto-Encoding Variational Bayes. arXiv:1312.6114 [stat.ML] https:\/\/arxiv.org\/abs\/1312.6114"},{"key":"e_1_3_2_1_17_1","unstructured":"Junnan Li Dongxu Li Silvio Savarese and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv:2301.12597 [cs.CV] https:\/\/arxiv.org\/abs\/2301.12597"},{"key":"e_1_3_2_1_18_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arXiv:2201.12086 [cs.CV] https:\/\/arxiv.org\/abs\/2201.12086","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arXiv:2201.12086 [cs.CV] https:\/\/arxiv.org\/abs\/2201.12086"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3705328.3748077"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709267"},{"key":"e_1_3_2_1_21_1","unstructured":"Qidong Liu Jiaxi Hu Yutian Xiao Xiangyu Zhao Jingtong Gao Wanyu Wang Qing Li and Jiliang Tang. 2024. Multimodal Recommender Systems: A Survey. arXiv:2302.03883 [cs.IR] https:\/\/arxiv.org\/abs\/2302.03883"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412695"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783381"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_1_25_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arXiv:2103.00020 [cs.CV] https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290963"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290963"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474268"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM59182.2024.00050"},{"key":"e_1_3_2_1_30_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_31_1","unstructured":"Petar Veli\u00c4kovi\u011e Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph Attention Networks. arXiv:1710.10903 [stat.ML] https:\/\/arxiv.org\/abs\/1710.10903"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688145"},{"key":"e_1_3_2_1_33_1","unstructured":"Xiao Wang Houye Ji Chuan Shi Bai Wang Peng Cui P. Yu and Yanfang Ye. 2021. Heterogeneous Graph Attention Network. arXiv:1903.07293 [cs.SI] https:\/\/arxiv.org\/abs\/1903.07293"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709280"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462862"},{"key":"e_1_3_2_1_36_1","unstructured":"Bing Xu Naiyan Wang Tianqi Chen and Mu Li. 2015. Empirical Evaluation of Rectified Activations in Convolutional Network. arXiv:1505.00853 [cs.LG] https:\/\/arxiv.org\/abs\/1505.00853"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524222"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591847"},{"key":"e_1_3_2_1_39_1","unstructured":"Liyuan Zheng ZUO Zhen Wenbo Wang Chaosheng Dong Michinari Momma and Yi Sun. 2021. Heterogeneous graph neural networks with neighbor-SIM attention mechanism for substitute product recommendation. (2021)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557281"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:30:54Z","timestamp":1784136654000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":40,"alternative-id":["10.1145\/3805712.3809684","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809684","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}