{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T01:58:27Z","timestamp":1783648707012,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T00:00:00Z","timestamp":1595635200000},"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":[[2020,7,25]]},"DOI":"10.1145\/3397271.3401156","type":"proceedings-article","created":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T07:50:08Z","timestamp":1595663408000},"page":"1469-1478","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":127,"title":["Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation"],"prefix":"10.1145","author":[{"given":"Fajie","family":"Yuan","sequence":"first","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Karatzoglou","sequence":"additional","affiliation":[{"name":"Google, London, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liguang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,7,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Superbloom: Bloom filter meets Transformer. arXiv preprint arXiv:2002.04723","author":"Anderson John","year":"2020","unstructured":"John Anderson , Qingqing Huang , Walid Krichene , Steffen Rendle , and Li Zhang . 2020 . Superbloom: Bloom filter meets Transformer. arXiv preprint arXiv:2002.04723 (2020). John Anderson, Qingqing Huang, Walid Krichene, Steffen Rendle, and Li Zhang. 2020. Superbloom: Bloom filter meets Transformer. arXiv preprint arXiv:2002.04723 (2020)."},{"key":"e_1_3_2_1_2_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_3_1","unstructured":"Yoshua Bengio and Samy Bengio. 2000. Modeling high-dimensional discrete data with multi-layer neural networks. In Advances in Neural Information Processing Systems. 400--406.  Yoshua Bengio and Samy Bengio. 2000. Modeling high-dimensional discrete data with multi-layer neural networks. In Advances in Neural Information Processing Systems. 400--406."},{"key":"e_1_3_2_1_4_1","volume-title":"Jack Valmadre, Philip Torr, and Andrea Vedaldi.","author":"Bertinetto Luca","year":"2016","unstructured":"Luca Bertinetto , Jo ao F Henriques , Jack Valmadre, Philip Torr, and Andrea Vedaldi. 2016 . Learning feed-forward one-shot learners. In Advances in Neural Information Processing Systems . 523--531. Luca Bertinetto, Jo ao F Henriques, Jack Valmadre, Philip Torr, and Andrea Vedaldi. 2016. Learning feed-forward one-shot learners. In Advances in Neural Information Processing Systems. 523--531."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Chong Chen Min Zhang Chenyang Wang Weizhi Ma Minming Li Yiqun Liu and Shaoping Ma. 2019. An Efficient Adaptive Transfer Neural Network for Social-aware Recommendation. (2019).  Chong Chen Min Zhang Chenyang Wang Weizhi Ma Minming Li Yiqun Liu and Shaoping Ma. 2019. An Efficient Adaptive Transfer Neural Network for Social-aware Recommendation. (2019).","DOI":"10.1145\/3331184.3331192"},{"key":"e_1_3_2_1_6_1","unstructured":"Misha Denil Babak Shakibi Laurent Dinh Marc'Aurelio Ranzato and Nando De Freitas. 2013. Predicting parameters in deep learning. In Advances in neural information processing systems. 2148--2156.  Misha Denil Babak Shakibi Laurent Dinh Marc'Aurelio Ranzato and Nando De Freitas. 2013. Predicting parameters in deep learning. In Advances in neural information processing systems. 2148--2156."},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/190"},{"key":"e_1_3_2_1_9_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017).  Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_10_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080777"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_14_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi , Alexandros Karatzoglou , Linas Baltrunas , and Domonkos Tikk . 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 ( 2015 ). Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_1_15_1","volume-title":"Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly.","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby , Andrei Giurgiu , Stanislaw Jastrzebski , Bruna Morrone , Quentin De Laroussilhe , Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019 . Parameter-Efficient Transfer Learning for NLP. arXiv preprint arXiv:1902.00751 (2019). Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. arXiv preprint arXiv:1902.00751 (2019)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271684"},{"key":"e_1_3_2_1_17_1","unstructured":"Guangneng Hu Yu Zhang and Qiang Yang. 2018b. MTNet: a neural approach for cross-domain recommendation with unstructured text.  Guangneng Hu Yu Zhang and Qiang Yang. 2018b. MTNet: a neural approach for cross-domain recommendation with unstructured text."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_19_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371769"},{"key":"e_1_3_2_1_21_1","volume-title":"K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning. arXiv preprint arXiv:1810.10703","author":"Mudrakarta Pramod Kaushik","year":"2018","unstructured":"Pramod Kaushik Mudrakarta , Mark Sandler , Andrey Zhmoginov , and Andrew Howard . 2018. K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning. arXiv preprint arXiv:1810.10703 ( 2018 ). Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, and Andrew Howard. 2018. K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning. arXiv preprint arXiv:1810.10703 (2018)."},{"key":"e_1_3_2_1_22_1","unstructured":"Vinod Nair and Geoffrey E Hinton. 2010. Rectified linear units improve restricted boltzmann machines. In ICML. 807--814.  Vinod Nair and Geoffrey E Hinton. 2010. Rectified linear units improve restricted boltzmann machines. In ICML. 807--814."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219828"},{"key":"e_1_3_2_1_24_1","volume-title":"CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network. arXiv preprint arXiv:2004.13401","author":"Qu Shilin","year":"2020","unstructured":"Shilin Qu , Fajie Yuan , Guibing Guo , Liguang Zhang , and Wei Wei . 2020. CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network. arXiv preprint arXiv:2004.13401 ( 2020 ). Shilin Qu, Fajie Yuan, Guibing Guo, Liguang Zhang, and Wei Wei. 2020. CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network. arXiv preprint arXiv:2004.13401 (2020)."},{"key":"e_1_3_2_1_25_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. [n.d.]. Improving language understanding by generative pre-training. ([n. d.]).  Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. [n.d.]. Improving language understanding by generative pre-training. ([n. d.])."},{"key":"e_1_3_2_1_26_1","unstructured":"Sylvestre-Alvise Rebuffi Hakan Bilen and Andrea Vedaldi. 2017. Learning multiple visual domains with residual adapters. In Advances in Neural Information Processing Systems. 506--516.  Sylvestre-Alvise Rebuffi Hakan Bilen and Andrea Vedaldi. 2017. Learning multiple visual domains with residual adapters. In Advances in Neural Information Processing Systems. 506--516."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00847"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. AUAI Press, 452--461","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle , Christoph Freudenthaler , Zeno Gantner , and Lars Schmidt-Thieme . 2009 . BPR: Bayesian personalized ranking from implicit feedback . In Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. AUAI Press, 452--461 . Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. AUAI Press, 452--461."},{"key":"e_1_3_2_1_29_1","volume-title":"Neural Collaborative Filtering vs. Matrix Factorization Revisited. arXiv preprint arXiv:2005.09683","author":"Rendle Steffen","year":"2020","unstructured":"Steffen Rendle , Walid Krichene , Li Zhang , and John Anderson . 2020. Neural Collaborative Filtering vs. Matrix Factorization Revisited. arXiv preprint arXiv:2005.09683 ( 2020 ). Steffen Rendle, Walid Krichene, Li Zhang, and John Anderson. 2020. Neural Collaborative Filtering vs. Matrix Factorization Revisited. arXiv preprint arXiv:2005.09683 (2020)."},{"key":"e_1_3_2_1_30_1","volume-title":"Incremental learning through deep adaptation","author":"Rosenfeld Amir","year":"2018","unstructured":"Amir Rosenfeld and John K Tsotsos . 2018. Incremental learning through deep adaptation . IEEE transactions on pattern analysis and machine intelligence ( 2018 ). Amir Rosenfeld and John K Tsotsos. 2018. Incremental learning through deep adaptation. IEEE transactions on pattern analysis and machine intelligence (2018)."},{"key":"e_1_3_2_1_31_1","volume-title":"BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning. arXiv preprint arXiv:1902.02671","author":"Stickland Asa Cooper","year":"2019","unstructured":"Asa Cooper Stickland and Iain Murray . 2019. BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning. arXiv preprint arXiv:1902.02671 ( 2019 ). Asa Cooper Stickland and Iain Murray. 2019. BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning. arXiv preprint arXiv:1902.02671 (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530","author":"Su Weijie","year":"2019","unstructured":"Weijie Su , Xizhou Zhu , Yue Cao , Bin Li , Lewei Lu , Furu Wei , and Jifeng Dai . 2019 . Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019). Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2019. Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401125"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357887"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_37_1","unstructured":"Jason Yosinski Jeff Clune Yoshua Bengio and Hod Lipson. 2014. How transferable are features in deep neural networks?. In Advances in neural information processing systems. 3320--3328.  Jason Yosinski Jeff Clune Yoshua Bengio and Hod Lipson. 2014. How transferable are features in deep neural networks?. In Advances in neural information processing systems. 3320--3328."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983758"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380116"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_41_1","unstructured":"Fajie Yuan Xin Xin Xiangnan He Guibing Guo Weinan Zhang Chua Tat-Seng and Joemon M Jose. 2018. fBGD: Learning embeddings from positive unlabeled data with BGD. (2018).  Fajie Yuan Xin Xin Xiangnan He Guibing Guo Weinan Zhang Chua Tat-Seng and Joemon M Jose. 2018. fBGD: Learning embeddings from positive unlabeled data with BGD. (2018)."},{"key":"e_1_3_2_1_42_1","volume-title":"2019 b. DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns. arXiv preprint arXiv:1905.10760","author":"Yuan Feng","year":"2019","unstructured":"Feng Yuan , Lina Yao , and Boualem Benatallah . 2019 b. DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns. arXiv preprint arXiv:1905.10760 ( 2019 ). Feng Yuan, Lina Yao, and Boualem Benatallah. 2019 b. DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns. arXiv preprint arXiv:1905.10760 (2019)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219855"}],"event":{"name":"SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval","location":"Virtual Event China","acronym":"SIGIR '20","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401156","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3397271.3401156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:43Z","timestamp":1750200103000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,25]]},"references-count":43,"alternative-id":["10.1145\/3397271.3401156","10.1145\/3397271"],"URL":"https:\/\/doi.org\/10.1145\/3397271.3401156","relation":{},"subject":[],"published":{"date-parts":[[2020,7,25]]},"assertion":[{"value":"2020-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}