{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:57:12Z","timestamp":1771613832847,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671733","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"1956-1967","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Probabilistic Attention for Sequential Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8268-6792","authenticated-orcid":false,"given":"Yuli","family":"Liu","sequence":"first","affiliation":[{"name":"Qinghai University & Qinghai Provincial Key Laboratory of Media Integration Technology and Communication, Xining, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2411-3523","authenticated-orcid":false,"given":"Christian","family":"Walder","sequence":"additional","affiliation":[{"name":"Google Research, Brain Team, Montreal, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8319-0118","authenticated-orcid":false,"given":"Lexing","family":"Xie","sequence":"additional","affiliation":[{"name":"Australian National University & Data61 CSIRO, Canberra, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-4512","authenticated-orcid":false,"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University & Zhongguancun Laboratory, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928","author":"Abnar Samira","year":"2020","unstructured":"Samira Abnar and Willem Zuidema. 2020. Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928 (2020)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313568"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159727"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462832"},{"key":"e_1_3_2_2_5_1","volume-title":"Fast greedy map inference for determinantal point process to improve recommendation diversity. Advances in Neural Information Processing Systems 31","author":"Chen Laming","year":"2018","unstructured":"Laming Chen, Guoxin Zhang, and Eric Zhou. 2018. Fast greedy map inference for determinantal point process to improve recommendation diversity. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555350"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403170"},{"key":"e_1_3_2_2_8_1","unstructured":"Chen Cheng Haiqin Yang Michael R Lyu and Irwin King. 2013. Where you like to go next: Successive point-of-interest recommendation. In Twenty-Third international joint conference on Artificial Intelligence."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052585"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591689"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512077"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401213"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298483.3298517"},{"key":"e_1_3_2_2_14_1","volume-title":"Lectures on linear algebra","author":"Gelfand Izrail Moiseevich","unstructured":"Izrail Moiseevich Gelfand. 1989. Lectures on linear algebra. Courier Corporation."},{"key":"e_1_3_2_2_15_1","volume-title":"Expectation-maximization for learning determinantal point processes. Advances in Neural Information Processing Systems 27","author":"Gillenwater Jennifer A","year":"2014","unstructured":"Jennifer A Gillenwater, Alex Kulesza, Emily Fox, and Ben Taskar. 2014. Expectation-maximization for learning determinantal point processes. Advances in Neural Information Processing Systems 27 (2014)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6290"},{"key":"e_1_3_2_2_17_1","volume-title":"International Conference on Machine Learning. PMLR, 1384--1393","author":"Han Insu","year":"2017","unstructured":"Insu Han, Prabhanjan Kambadur, Kyoungsoo Park, and Jinwoo Shin. 2017. Faster greedy MAP inference for determinantal point processes. In International Conference on Machine Learning. PMLR, 1384--1393."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3250463"},{"key":"e_1_3_2_2_19_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis) 5, 4","author":"Maxwell Harper F","year":"2015","unstructured":"F Maxwell Harper and Joseph A Konstan. 2015. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis) 5, 4 (2015), 1--19."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0030"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449957"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240609"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5854"},{"key":"e_1_3_2_2_25_1","volume-title":"Yingtao Luo, Kai Zhang, and Sunghun Kim.","author":"Jiang Juyong","year":"2022","unstructured":"Juyong Jiang, Jae Boum Kim, Yingtao Luo, Kai Zhang, and Sunghun Kim. 2022. AdaMCT: adaptive mixture of CNN-transformer for sequential recommendation. arXiv preprint arXiv:2205.08776 (2022)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Alex Kulesza and Ben Taskar. 2011. k-DPPs: Fixed-size determinantal point processes. In ICML.","DOI":"10.1561\/9781601986290"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Alex Kulesza Ben Taskar et al. 2012. Determinantal point processes for machine learning. Foundations and Trends\u00ae in Machine Learning 5 2--3 (2012) 123--286.","DOI":"10.1561\/2200000044"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608779"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371786"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531732"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482448"},{"key":"e_1_3_2_2_33_1","volume-title":"Edge-enhanced global disentangled graph neural network for sequential recommendation. ACM Transactions on Knowledge Discovery from Data 17, 6","author":"Li Yunyi","year":"2023","unstructured":"Yunyi Li, Yongjing Hao, Pengpeng Zhao, Guanfeng Liu, Yanchi Liu, Victor S Sheng, and Xiaofang Zhou. 2023. Edge-enhanced global disentangled graph neural network for sequential recommendation. ACM Transactions on Knowledge Discovery from Data 17, 6 (2023), 1--22."},{"key":"e_1_3_2_2_34_1","volume-title":"Recommending accurate and diverse items using bilateral branch network. arXiv preprint arXiv:2101.00781","author":"Liang Yile","year":"2021","unstructured":"Yile Liang and Tieyun Qian. 2021. Recommending accurate and diverse items using bilateral branch network. arXiv preprint arXiv:2101.00781 (2021)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503181.3503203"},{"key":"e_1_3_2_2_36_1","volume-title":"Determinantal Point Process Likelihoods for Sequential Recommendation. arXiv preprint arXiv:2204.11562","author":"Liu Yuli","year":"2022","unstructured":"Yuli Liu, Christian Walder, and Lexing Xie. 2022. Determinantal Point Process Likelihoods for Sequential Recommendation. arXiv preprint arXiv:2204.11562 (2022)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411994"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959149"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498433"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313567"},{"key":"e_1_3_2_2_41_1","volume-title":"Self-attention with relative position representations. arXiv preprint arXiv:1803.02155","author":"Shaw Peter","year":"2018","unstructured":"Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. 2018. Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)."},{"key":"e_1_3_2_2_42_1","volume-title":"Reinforced self-attention network: a hybrid of hard and soft attention for sequence modeling. arXiv preprint arXiv:1801.10296","author":"Shen Tao","year":"2018","unstructured":"Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, SenWang, and Chengqi Zhang. 2018. Reinforced self-attention network: a hybrid of hard and soft attention for sequence modeling. arXiv preprint arXiv:1801.10296 (2018)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_2_45_1","volume-title":"Attention Mixtures for Time-Aware Sequential Recommendation. arXiv preprint arXiv:2304.08158","author":"Tran Viet-Anh","year":"2023","unstructured":"Viet-Anh Tran, Guillaume Salha-Galvan, Bruno Sguerra, and Romain Hennequin. 2023. Attention Mixtures for Time-Aware Sequential Recommendation. arXiv preprint arXiv:2304.08158 (2023)."},{"key":"e_1_3_2_2_46_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","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 30 (2017)."},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1605--1615","author":"Mary J\u00e9r\u00e9mie","year":"2019","unstructured":"RomainWarlop, J\u00e9r\u00e9mie Mary, and Mike Gartrell. 2019. Tensorized determinantal point processes for recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1605--1615."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380285"},{"key":"e_1_3_2_2_49_1","first-page":"3870","article-title":"PD-GAN: Adversarial Learning for Personalized Diversity-Promoting Recommendation","volume":"19","author":"Wu Qiong","year":"2019","unstructured":"Qiong Wu, Yong Liu, Chunyan Miao, Binqiang Zhao, Yin Zhao, and Lu Guan. 2019. PD-GAN: Adversarial Learning for Personalized Diversity-Promoting Recommendation.. In IJCAI, Vol. 19. 3870--3876.","journal-title":"IJCAI"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449946"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISKE.2017.8258747"},{"key":"e_1_3_2_2_52_1","volume-title":"Sharing attention weights for fast transformer. arXiv preprint arXiv:1906.11024","author":"Xiao Tong","year":"2019","unstructured":"Tong Xiao, Yinqiao Li, Jingbo Zhu, Zhengtao Yu, and Tongran Liu. 2019. Sharing attention weights for fast transformer. arXiv preprint arXiv:1906.11024 (2019)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00099"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.066"},{"key":"e_1_3_2_2_55_1","first-page":"3940","article-title":"Graph contextualized selfattention network for session-based recommendation","volume":"19","author":"Xu Chengfeng","year":"2019","unstructured":"Chengfeng Xu, Pengpeng Zhao, Yanchi Liu, Victor S Sheng, Jiajie Xu, Fuzhen Zhuang, Junhua Fang, and Xiaofang Zhou. 2019. Graph contextualized selfattention network for session-based recommendation.. In IJCAI, Vol. 19. 3940--3946.","journal-title":"IJCAI"},{"key":"e_1_3_2_2_56_1","volume-title":"Zhiming Cui, Xiaofang Zhou, and Hui Xiong.","author":"Xu Chengfeng","year":"2019","unstructured":"Chengfeng Xu, Pengpeng Zhao, Yanchi Liu, Jiajie Xu, Victor S Sheng S. Sheng, Zhiming Cui, Xiaofang Zhou, and Hui Xiong. 2019. Recurrent convolutional neural network for sequential recommendation. In The world wide web conference. 3398--3404."},{"key":"e_1_3_2_2_57_1","volume-title":"International conference on machine learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning. PMLR, 2048--2057."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358113"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.009"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583361"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539342"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015709"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2943140"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454008.1454030"},{"key":"e_1_3_2_2_65_1","volume-title":"Next item recommendation with self-attention. arXiv preprint arXiv:1808.06414","author":"Zhang Shuai","year":"2018","unstructured":"Shuai Zhang, Yi Tay, Lina Yao, and Aixin Sun. 2018. Next item recommendation with self-attention. arXiv preprint arXiv:1808.06414 (2018)."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"crossref","unstructured":"Tingting Zhang Pengpeng Zhao Yanchi Liu Victor S Sheng Jiajie Xu Deqing Wang Guanfeng Liu Xiaofang Zhou et al. 2019. Feature-level Deeper Self-Attention Network for Sequential Recommendation.. In IJCAI. 4320--4326.","DOI":"10.24963\/ijcai.2019\/600"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411954"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671733","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:01Z","timestamp":1750291561000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671733"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":67,"alternative-id":["10.1145\/3637528.3671733","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671733","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}