Discrete Listwise Content-aware Recommendation
Authors: 
Fangyuan Luo, Jun Wu, and Tao WangAuthors Info & Claims
Fangyuan Luo, Jun Wu, and Tao WangAuthors Info & ClaimsArticle No.: 7, Pages 1 - 20
Abstract
To perform online inference efficiently, hashing techniques, devoted to encoding model parameters as binary codes, play a key role in reducing the computational cost of content-aware recommendation (CAR), particularly on devices with limited computation resource. However, current hashing methods for CAR fail to align their learning objectives (e.g., squared loss) with the ranking-based metrics (e.g., Normalized Discounted Cumulative Gain (NDCG)), resulting in suboptimal recommendation accuracy. In this article, we propose a novel ranking-based CAR hashing method based on Factorization Machine (FM), called Discrete Listwise FM (DLFM), for fast and accurate recommendation. Concretely, our DLFM is to optimize NDCG in the Hamming space for preserving the listwise user-item relationships. We devise an efficient algorithm to resolve the challenging DLFM problem, which can directly learn binary parameters in a relaxed continuous solution space, without additional quantization. Particularly, our theoretical analysis shows that the optimal solution to the relaxed continuous optimization problem is approximately the same as that of the original discrete optimization problem. Through extensive experiments on two real-world datasets, we show that DLFM consistently outperforms state-of-the-art hashing-based recommendation techniques.
References
[1]
Chris J. C. Burges. 2010. From RankNet to LambdaRank to LambdaMART: An Overview. Technical Report.
[2]
Christopher J. C. Burges, Robert Ragno, and Quoc Viet Le. 2006. Learning to rank with nonsmooth cost functions. In Proceedings of the NIPS. 193–200.
[3]
Yankai Chen, Yixiang Fang, Yifei Zhang, and Irwin King. 2023. Bipartite graph convolutional hashing for effective and efficient top-n search in hamming space. In Proceedings of the WWW. ACM.
[4]
Yankai Chen, Huifeng Guo, Yingxue Zhang, Chen Ma, Ruiming Tang, Jingjie Li, and Irwin King. 2022. Learning binarized graph representations with multi-faceted quantization reinforcement for top-k recommendation. In Proceedings of the SIGKDD.
[5]
Yankai Chen, Quoc-Tuan Truong, Xin Shen, Ming Wang, Jin Li, Jim Chan, and Irwin King. 2023. Topological representation learning for e-commerce shopping behaviors. In Proceedings of the MLG.
[6]
Yankai Chen, Yifei Zhang, Menglin Yang, Zixing Song, Chen Ma, and Irwin King. 2023. WSFE: Wasserstein sub-graph feature encoder for effective user segmentation in collaborative filtering. In Proceedings of the SIGIR (2023).
[7]
Paolo Cremonesi, Yehuda Koren, and Roberto Turrin. 2010. Performance of recommender algorithms on top-n recommendation tasks. In Proceedings of the RecSys. 39–46.
[8]
Bolin Gao and Lacra Pavel. 2017. On the properties of the softmax function with application in game theory and reinforcement learning. Retrieved from https://arxiv.org/abs/1704.00805
[9]
Chen Gao, Yu Zheng, Nian Li, Yinfeng Li, Yingrong Qin, Jinghua Piao, Yuhan Quan, Jianxin Chang, Depeng Jin, Xiangnan He, and Yong Li. 2021. Graph neural networks for recommender systems: Challenges, methods, and directions. Retrieved from https://arxiv.org/abs/2109.12843
[10]
Aditya Grover, Eric Wang, Aaron Zweig, and Stefano Ermon. 2019. Stochastic optimization of sorting networks via continuous relaxations. In Proceedings of the ICLR.
[11]
Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. 2017. DeepFM: A factorization-machine based neural network for CTR prediction. In Proceedings of the IJCAI. 1725–1731.
[12]
Casper Hansen, Christian Hansen, Jakob Grue Simonsen, Stephen Alstrup, and Christina Lioma. 2020. Content-aware neural hashing for cold-start recommendation. In Proceedings of the SIGIR. 971–980.
[13]
Christian Hansen, Casper Hansen, Jakob Grue Simonsen, and Christina Lioma. 2021. Projected hamming dissimilarity for bit-level importance coding in collaborative filtering. In Proceedings of the WWW. 261–269.
[14]
Johan Håstad. 2001. Some optimal inapproximability results. J. ACM 48, 4 (2001), 798–859.
[15]
Martin Jaggi. 2011. Sparse convex optimization methods for machine learning. (2011). Retrieved from https://hdl.handle.net/20.500.11850/72811
[16]
Wang-Cheng Kang and Julian John McAuley. 2019. Candidate generation with binary codes for large-scale top-n recommendation. In Proceedings of the CIKM. 1523–1532.
[17]
Jaana Kekäläinen. 2005. Binary and graded relevance in IR evaluations–comparison of the effects on ranking of IR systems. Info. Process. Manag. 41, 5 (2005), 1019–1033.
[18]
Guang-He Lee and Shou-De Lin. 2015. LambdaMF: Learning nonsmooth ranking functions in matrix factorization using lambda. In Proceedings of the ICDM. 823–828.
[19]
Roger Zhe Li, Julián Urbano, and Alan Hanjalic. 2021. New insights into metric optimization for ranking-based recommendation. In Proceedings of the SIGIR. 932–941.
[20]
Defu Lian, Rui Liu, Yong Ge, Kai Zheng, Xing Xie, and Longbing Cao. 2017. Discrete content-aware matrix factorization. In Proceedings of the SIGKDD. 325–334.
[21]
Defu Lian, Xing Xie, and Enhong Chen. 2021. Discrete matrix factorization and extension for fast item recommendation. IEEE Trans. Knowl. Data Eng. 33, 5 (2021), 1919–1933.
[22]
Jianxun Lian, Xiaohuan Zhou, Fuzheng Zhang, Zhongxia Chen, Xing Xie, and Guangzhong Sun. 2018. xDeepFM: Combining explicit and implicit feature interactions for recommender systems. In Proceedings of the SIGKDD. 1754–1763.
[23]
Weizhe Lin, Linjun Shou, Ming Gong, Jian Pei, Zhilin Wang, Bill Byrne, and Daxin Jiang. 2022. Transformer-empowered content-aware collaborative filtering. In Proceedings of the KaRS@RecSys(CEUR Workshop Proceedings, Vol. 3294). 53–64.
[24]
Chenghao Liu, Tao Lu, Zhiyong Cheng, Xin Wang, Jianling Sun, and Steven C. H. Hoi. 2021. Discrete listwise collaborative filtering for fast recommendation. In Proceedings of the SDM. 46–54.
[25]
Chenghao Liu, Xin Wang, Tao Lu, Wenwu Zhu, Jianling Sun, and Steven Hoi. 2019. Discrete social recommendation. In Proceedings of the AAAI.
[26]
Han Liu, Xiangnan He, Fuli Feng, Liqiang Nie, Rui Liu, and Hanwang Zhang. 2018. Discrete factorization machines for fast feature-based recommendation. In Proceedings of the IJCAI. 3449–3455.
[27]
Tie-Yan Liu. 2011. Learning to Rank for Information Retrieval. Springer.
[28]
Zhiyong Liu and Hong Qiao. 2014. GNCCP—Graduated NonConvexity and graduated concavity procedure. IEEE Trans. Pattern Anal. Mach. Intell. 36, 6 (2014), 1258–1267.
[29]
Fangyuan Luo, Jun Wu, and Tao Wang. 2022. Discrete listwise personalized ranking for fast top-n recommendation with implicit feedback. In Proceedings of the IJCAI. 2159–2165.
[30]
Chen Ma, Peng Kang, Bin Wu, Qinglong Wang, and Xue Liu. 2019. Gated attentive-autoencoder for content-aware recommendation. In Proceedings of the WSDM. 519–527.
[31]
Philip Wolfe Marguerite Frank. 1956. An algorithm for quadratic programming. Naval Res. Logist. Quart. 3 (1956), 95–110.
[32]
Wlodzimierz Ogryczak and Arie Tamir. 2003. Minimizing the sum of the k largest functions in linear time. Info. Process. Lett. 85, 3 (2003), 117–122.
[33]
Rabeh Ravanifard, Abdolreza Mirzaei, Wray L. Buntine, and Mehran Safayani. 2021. Content-aware listwise collaborative filtering. Neurocomputing 461 (2021), 479–493.
[34]
Steffen Rendle. 2010. Factorization machines. In Proceedings of the ICDM. 995–1000.
[35]
R. T. Rockafellar. 1997. Convex Analysis. Princeton University Press.
[36]
Fumin Shen, Chunhua Shen, Wei Liu, and Heng Tao Shen. 2015. Supervised discrete hashing. In Proceedings of the CVPR. 37–45.
[37]
Yue Shi, Alexandros Karatzoglou, Linas Baltrunas, Martha A. Larson, and Alan Hanjalic. 2013. xCLiMF: Optimizing expected reciprocal rank for data with multiple levels of relevance. In Proceedings of the RecSys. 431–434.
[38]
Yue Shi, Martha Larson, and Alan Hanjalic. 2014. Collaborative filtering beyond the user-item matrix: A survey of the state of the art and future challenges. ACM Comput. Surv. 47, 1 (2014), 1–45.
[39]
Qiaoyu Tan, Ninghao Liu, Xing Zhao, Hongxia Yang, Jingren Zhou, and Xia Hu. 2020. Learning to hash with graph neural networks for recommender systems. In Proceedings of the WWW. 1988–1998.
[40]
J. Wang, W. Liu, S. Kumar, and S. Chang. 2016. Learning to hash for indexing big data—A survey. Proc. IEEE 104, 1 (2016), 34–57.
[41]
Jingdong Wang, Ting Zhang, Jingkuan Song, Nicu Sebe, and Heng Tao Shen. 2018. A survey on learning to hash. IEEE T. Pattern Anal. 40, 4 (2018), 769–790.
[42]
Ke Wang, Yanmin Zhu, Haobing Liu, Tianzi Zang, and Chunyang Wang. 2023. Learning aspect-aware high-order representations from ratings and reviews for recommendation. ACM Trans. Knowl. Discov. Data 17, 1 (2023), 22 pages.
[43]
Zihan Wang, Ziheng Jiang, Zhaochun Ren, Jiliang Tang, and Dawei Yin. 2018. A path-constrained framework for discriminating substitutable and complementary products in e-commerce. In Proceedings of the WSDM. 619–627.
[44]
Markus Weimer, Alexandros Karatzoglou, Quoc V. Le, and Alexander J. Smola. 2007. COFI RANK - maximum margin matrix factorization for collaborative ranking. In Proceedings of the NIPS. 1593–1600.
[45]
Jun Wu, Fangyuan Luo, Yujia Zhang, and Haishuai Wang. 2020. Semi-discrete matrix factorization. IEEE Intell. Syst. 35, 5 (2020), 73–83.
[46]
Yang Xu, Lei Zhu, Zhiyong Cheng, Jingjing Li, Zheng Zhang, and Huaxiang Zhang. 2023. Multi-modal discrete collaborative filtering for efficient cold-start recommendation. IEEE Trans. Knowl. Data Eng. 35, 1 (2023), 741–755.
[47]
Fajie Yuan, Guibing Guo, Joemon M. Jose, Long Chen, Haitao Yu, and Weinan Zhang. 2016. LambdaFM: Learning optimal ranking with factorization machines using lambda surrogates. In Proceedings of the CIKM. 227–236.
[48]
Mikhail Zaslavskiy, Francis R. Bach, and Jean-Philippe Vert. 2009. A path following algorithm for the graph matching problem. IEEE Trans. Pattern Anal. Mach. Intell. 31, 12 (2009), 2227–2242.
[49]
Hanwang Zhang, Fumin Shen, Wei Liu, Xiangnan He, Huanbo Luan, and Tat Seng Chua. 2016. Discrete collaborative filtering. In Proceedings of the SIGIR. 325–334.
[50]
Shuai Zhang, Lina Yao, Aixin Sun, and Yi Tay. 2019. Deep learning based recommender system: A survey and new perspectives. ACM Comput. Surv. 52, 1 (2019), 5:1–5:38.
[51]
Xinni Zhang, Yankai Chen, Cuiyun Gao, Qing Liao, Shenglin Zhao, and Irwin King. 2022. Knowledge-aware neural networks with personalized feature referencing for cold-start recommendation. Retrieved from https://arXiv:2209.13973
[52]
Yan Zhang, Defu Lian, and Guowu Yang. 2017. Discrete personalized ranking for fast collaborative filtering from implicit feedback. In Proceedings of the AAAI. 1669–1675.
[53]
Yan Zhang, Ivor W. Tsang, Hongzhi Yin, Guowu Yang, Defu Lian, and Jingjing Li. 2022. Deep pairwise hashing for cold-start recommendation. IEEE Trans. Knowl. Data Eng. 34, 7 (2022), 3169–3181.
[54]
Yan Zhang, Haoyu Wang, Defu Lian, Ivor W. Tsang, Hongzhi Yin, and Guowu Yang. 2018. Discrete ranking-based matrix factorization with self-paced learning. In Proceedings of the SIGKDD. 2758–2767.
[55]
Yan Zhang, Hongzhi Yin, Zi Huang, Xingzhong Du, Guowu Yang, and Defu Lian. 2018. Discrete deep learning for fast content-aware recommendation. In Proceedings of the WSDM. 717–726.
[56]
Zhiwei Zhang, Qifan Wang, Lingyun Ruan, and Luo Si. 2014. Preference preserving hashing for efficient recommendation. In Proceedings of the SIGIR. 183–192.
[57]
Ke Zhou and Hongyuan Zha. 2012. Learning binary codes for collaborative filtering. In Proceedings of the SIGKDD. 498–506.
[58]
Lei Zhu, Yang Xu, Jingjing Li, Weili Guan, and Zhiyong Cheng. 2022. Explainable discrete collaborative filtering. IEEE Trans. Knowl. Data Eng. 35, 7 (2022), 1–14.
Index Terms
- Discrete Listwise Content-aware Recommendation
Recommendations
Content-Aware Listwise Collaborative Filtering
Graphical abstractDisplay Omitted
Highlights- A probabilistic model is proposed that integrates content information about items, represented as bag-of-words, with ranking-oriented collaborative ...
AbstractRecently, listwise collaborative filtering (CF) algorithms are attracting increasing interest due to their efficiency and prediction quality. Different from rating-oriented (pointwise) CF, they recommend a preference ranking of items ...
Listwise Collaborative Filtering
SIGIR '15: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information RetrievalRecently, ranking-oriented collaborative filtering (CF) algorithms have achieved great success in recommender systems. They obtained state-of-the-art performances by estimating a preference ranking of items for each user rather than estimating the ...
Content-Independent Task-Focused Recommendation
Recommender systems, also known as collaborative filtering systems, predict a user's current interest in unseen items based on ratings or recommendations from other people. Users are typically asked to rate items (such as movies) that they have already ...
Comments
Information & Contributors
Information
Published In
January 2024
854 pages
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 10 August 2023
Online AM: 14 July 2023
Accepted: 05 July 2023
Revised: 26 June 2023
Received: 29 November 2022
Published in TKDD Volume 18, Issue 1
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Fundamental Research Funds for the Central Universities
- Open Research Fund from the Guangdong Provincial Key Laboratory of Big Data Computing
- Chinese University of Hong Kong, Shenzhen
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 334Total Downloads
- Downloads (Last 12 months)334
- Downloads (Last 6 weeks)23
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in