Yang Zhang
Xiangnan He
Meng Wang
ABSTRACT
Practical recommender systems need be periodically retrained to refresh the model with new interaction data. To pursue high model fidelity, it is usually desirable to retrain the model on both historical and new data, since it can account for both long-term and short-term user preference. However, a full model retraining could be very time-consuming and memory-costly, especially when the scale of historical data is large. In this work, we study the model retraining mechanism for recommender systems, a topic of high practical values but has been relatively little explored in the research community.
Our first belief is that retraining the model on historical data is unnecessary, since the model has been trained on it before. Nevertheless, normal training on new data only may easily cause overfitting and forgetting issues, since the new data is of a smaller scale and contains fewer information on long-term user preference. To address this dilemma, we propose a new training method, aiming to abandon the historical data during retraining through learning to transfer the past training experience.Specifically, we design a neural network-based transfer component, which transforms the old model to a new model that is tailored for future recommendations. To learn the transfer component well, we optimize the "future performance'' -- i.e., the recommendation accuracy evaluated in the next time period. Our Sequential Meta-Learning(SML) method offers a general training paradigm that is applicable to any differentiable model. We demonstrate SML on matrix factorization and conduct experiments on two real-world datasets. Empirical results show that SML not only achieves significant speed-up, but also outperforms the full model retraining in recommendation accuracy, validating the effectiveness of our proposals. We release our codes at: https://github.com/zyang1580/SML.
- Alex Beutel, Paul Covington, Sagar Jain, Can Xu, Jia Li, Vince Gatto, and Ed H Chi. 2018. Latent cross: Making use of context in recurrent recommender systems. In WSDM. 46--54.Google Scholar
- Homanga Bharadhwaj. 2019. Meta-Learning for User Cold-Start Recommendation. In IJCNN. 1--8.Google Scholar
- Shiyu Chang, Yang Zhang, Jiliang Tang, Dawei Yin, Yi Chang, Mark A Hasegawa-Johnson, and Thomas S Huang. 2017. Streaming recommender systems. In WWW. 525--534.Google Scholar
- Yihong Chen, Bei Chen, Xiangnan He, Chen Gao, Yong Li, Jian-Guang Lou, and Yue Wang. 2019. (łambda)Opt: Learn to Regularize Recommender Models in Finer Levels. In SIGKDD. 978--986.Google Scholar
- Robin Devooght, Nicolas Kourtellis, and Amin Mantrach. 2015. Dynamic matrix factorization with priors on unknown values. In SIGKDD. 189--198.Google Scholar
- Ernesto Diaz-Aviles, Lucas Drumond, Lars Schmidt-Thieme, and Wolfgang Nejdl. 2012. Real-time top-n recommendation in social streams. In RecSys. 59--66.Google Scholar
- Xiaoyu Du, Xiangnan He, Fajie Yuan, Jinhui Tang, Zhiguang Qin, and Tat-Seng Chua. 2019 a. Modeling Embedding Dimension Correlations via Convolutional Neural Collaborative Filtering. TOIS, Vol. 37, 4 (2019), 47:1--47:22.Google ScholarDigital Library
- Zhengxiao Du, Xiaowei Wang, Hongxia Yang, Jingren Zhou, and Jie Tang. 2019 b. Sequential Scenario-Specific Meta Learner for Online Recommendation. In SIGKDD. 2895--2904.Google Scholar
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML, Vol. 70. 1126--1135.Google Scholar
- Luca Franceschi, Paolo Frasconi, Saverio Salzo, Riccardo Grazzi, and Massimiliano Pontil. 2018. Bilevel Programming for Hyperparameter Optimization and Meta-Learning. In ICML, Vol. 80. 1563--1572.Google Scholar
- Jon Atle Gulla, Lemei Zhang, Peng Liu, Özlem Özgöbek, and Xiaomeng Su. 2017. The Adressa dataset for news recommendation. In WI. 1042--1048.Google Scholar
- Ruining He, Wang-Cheng Kang, and Julian McAuley. 2017a. Translation-based recommendation. In RecSys. 161--169.Google Scholar
- Xiangnan He and Tat-Seng Chua. 2017. Neural factorization machines for sparse predictive analytics. In SIGIR. 355--364.Google Scholar
- Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, and Meng Wang. 2020. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. In SIGIR.Google Scholar
- Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017b. Neural collaborative filtering. In WWW. 173--182.Google Scholar
- Xiangnan He, Hanwang Zhang, Min-Yen Kan, and Tat-Seng Chua. 2016. Fast Matrix Factorization for Online Recommendation with Implicit Feedback. In SIGIR. 549--558.Google Scholar
- Dan Hendrycks and Kevin Gimpel. 2016. Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units. CoRR, Vol. abs/1606.08415 (2016).Google Scholar
- Balá zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2016. Session-based Recommendations with Recurrent Neural Networks. In ICLR.Google Scholar
- Kurt Hornik. 1991. Approximation capabilities of multilayer feedforward networks. Neural networks, Vol. 4, 2 (1991), 251--257.Google Scholar
- Haoji Hu, Xiangnan He, Jinyang Gao, and Zhi-Li Zhang. 2020. Modeling Personalized Item Frequency Information for Next-basket Recommendation. In SIGIR.Google Scholar
- Muhammad Abdullah Jamal and Guo-Jun Qi. 2019. Task Agnostic Meta-Learning for Few-Shot Learning. In CVPR. 11719--11727.Google Scholar
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR.Google Scholar
- James Kirkpatrick, Razvan Pascanu, Neil C Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabskabarwinska, et almbox. 2017. Overcoming catastrophic forgetting in neural networks. PNAS, Vol. 114, 13 (2017), 3521--3526.Google ScholarCross Ref
- Hoyeop Lee, Jinbae Im, Seongwon Jang, Hyunsouk Cho, and Sehee Chung. 2019. MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation. In SIGKDD. 1073--1082.Google Scholar
- Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, and Tat-Seng Chua. 2020. Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems. In WSDM. 304--312.Google Scholar
- 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 SIGKDD. 1754--1763.Google Scholar
- David Lopez-Paz and Marc'Aurelio Ranzato. 2017. Gradient Episodic Memory for Continual Learning. In NeurlPS 2017. 6467--6476.Google Scholar
- Feiyang Pan, Shuokai Li, Xiang Ao, Pingzhong Tang, and Qing He. 2019. Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings. In SIGIR. 695--704.Google Scholar
- Massimo Quadrana, Paolo Cremonesi, and Dietmar Jannach. 2018. Sequence-aware recommender systems. ACM Computing Surveys (CSUR), Vol. 51, 4 (2018), 66:1--66:36.Google ScholarDigital Library
- Sachin Ravi and Hugo Larochelle. 2017. Optimization as a Model for Few-Shot Learning. In ICLR.Google Scholar
- Yi Ren, Cuirong Chi, and Zhang Jintao. 2019. A Survey of Personalized Recommendation Algorithm Selection Based on Meta-learning. In CSIA. 1383--1388.Google Scholar
- Steffen Rendle. 2010. Factorization Machines. In ICDM. 995--1000.Google Scholar
- Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In UAI. 452--461.Google ScholarDigital Library
- Steffen Rendle, Christoph Freudenthaler, and Lars Schmidt-Thieme. 2010. Factorizing personalized markov chains for next-basket recommendation. In WWW. 811--820.Google Scholar
- Steffen Rendle and Lars Schmidt-Thieme. 2008. Online-updating regularized kernel matrix factorization models for large-scale recommender systems. In RecSys. 251--258.Google Scholar
- David Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-Francois Crespo, and Dan Dennison. 2015. Hidden technical debt in machine learning systems. In NeurlPS. 2503--2511.Google Scholar
- Karthik Subbian, Charu Aggarwal, and Kshiteesh Hegde. 2016. Recommendations for streaming data. In CIKM. 2185--2190.Google Scholar
- Jiaxi Tang and Ke Wang. 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In WSDM. 565--573.Google Scholar
- Manasi Vartak, Arvind Thiagarajan, Conrado Miranda, Jeshua Bratman, and Hugo Larochelle. 2017. A meta-learning perspective on cold-start recommendations for items. In NeurlPS. 6904--6914.Google Scholar
- Jeffrey S Vitter. 1985. Random sampling with a reservoir. TOMS, Vol. 11, 1, 37--57.Google ScholarDigital Library
- Qinyong Wang, Hongzhi Yin, Zhiting Hu, Defu Lian, Hao Wang, and Zi Huang. 2018a. Neural memory streaming recommender networks with adversarial training. In SIGKDD. 2467--2475.Google Scholar
- Weiqing Wang, Hongzhi Yin, Zi Huang, Qinyong Wang, Xingzhong Du, and Quoc Viet Hung Nguyen. 2018b. Streaming ranking based recommender systems. In SIGIR. 525--534.Google Scholar
- Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, and Tat-Seng Chua. 2019 a. KGAT: Knowledge Graph Attention Network for Recommendation. In SIGKDD. 950--958.Google Scholar
- Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019 b. Neural Graph Collaborative Filtering. In SIGIR. 165--174.Google Scholar
- Bin Wu, Xiangnan He, Zhongchuan Sun, Liang Chen, and Yangdong Ye. 2019. ATM: An Attentive Translation Model for Next-Item Recommendation. IEEE Transactions on Industrial Informatics, Vol. 16, 3 (2019), 1448--1459.Google ScholarCross Ref
- Fajie Yuan, Xiangnan He, Haochuan Jiang, Guibing Guo, Jian Xiong, Zhezhao Xu, and Yilin Xiong. 2020. Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation. In WWW. 303--313.Google Scholar
- Fajie Yuan, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M Jose, and Xiangnan He. 2019. A Simple Convolutional Generative Network for Next Item Recommendation. In WSDM. 582--590.Google Scholar
Index Terms
- How to Retrain Recommender System?: A Sequential Meta-Learning Method
Recommendations
Self-Supervised Learning for Recommender System
SIGIR '22: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information RetrievalRecommender systems have become key components for a wide spectrum of web applications (e.g., E-commerce sites, video sharing platforms, lifestyle applications, etc), so as to alleviate the information overload and suggest items for users. However, most ...
Addressing cold start in recommender systems: a semi-supervised co-training algorithm
SIGIR '14: Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrievalCold start is one of the most challenging problems in recommender systems. In this paper we tackle the cold-start problem by proposing a context-aware semi-supervised co-training method named CSEL. Specifically, we use a factorization model to capture ...
How Important is Periodic Model update in Recommender System?
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalIn real-world recommender model deployments, the models are typically retrained and deployed repeatedly. It is the rule-of-thumb to periodically retrain recommender models to capture up-to-date user behavior and item trends. However, the harm caused by ...
Comments