ABSTRACT
The issue of user cold-start poses a long-standing challenge to recommendation systems, due to the scarce interactions of new users. Recently, meta-learning based studies treat each cold-start user as a user-specific few-shot task and then derive meta-knowledge about fast model adaptation across training users. However, existing solutions mostly do not clearly distinguish the concept of new users and the concept of novel preferences, leading to over-reliance on meta-learning based adaptability to novel patterns. In addition, we also argue that the existing meta-training task construction inherently suffers from the memorization overfitting issue, which inevitably hinders meta-generalization to new users. In response to the aforementioned issues, we propose a preference learning decoupling framework, which is enhanced with meta-augmentation (PDMA), for user cold-start recommendation. To rescue the meta-learning from unnecessary adaptation to common patterns, our framework decouples preference learning for a cold-start user into two complementary aspects: common preference transfer, and novel preference adaptation. To handle the memorization overfitting issue, we further propose to augment meta-training users by injecting attribute-based noises, to achieve mutually-exclusive tasks. Extensive experiments on benchmark datasets demonstrate that our framework achieves superior performance improvements against state-of-the-art methods. We also show that our proposed framework is effective in alleviating memorization overfitting.
- Homanga Bharadhwaj. 2019. Meta-learning for user cold-start recommendation. In Proceedings of IJCNN. IEEE, 1--8.Google ScholarCross Ref
- Manqing Dong, Feng Yuan, Lina Yao, Xiwei Xu, and Liming Zhu. 2020. Mamo: Memory-augmented meta-optimization for cold-start recommendation. In Proceedings of KDD. 688--697.Google ScholarDigital Library
- Zhengxiao Du, Xiaowei Wang, Hongxia Yang, Jingren Zhou, and Jie Tang. 2019. Sequential scenario-specific meta learner for online recommendation. In Proceedings of KDD. 2895--2904.Google ScholarDigital Library
- Xidong Feng, Chen Chen, Dong Li, Mengchen Zhao, Jianye Hao, and Jun Wang. 2021. CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation. In Proceedings of CIKM. 484--493.Google ScholarDigital Library
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of ICML. PMLR, 1126--1135.Google Scholar
- Zeno Gantner, Lucas Drumond, Christoph Freudenthaler, Steffen Rendle, and Lars Schmidt-Thieme. 2010. Learning attribute-to-feature mappings for cold-start recommendations. In Proceedings of ICDM. IEEE, 176--185.Google ScholarDigital Library
- Li Gao, Hong Yang, Jia Wu, Chuan Zhou, Weixue Lu, and Yue Hu. 2018. Recommendation with multi-source heterogeneous information. In Proceedings of IJCAI.Google ScholarCross Ref
- Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative filtering. In Proceedings of WWW. 173--182.Google ScholarDigital Library
- Timothy Hospedales, Antreas Antoniou, Paul Micaelli, and Amos Storkey. 2021. Meta-learning in neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 9 (2021), 5149--5169.Google Scholar
- Guangneng Hu, Yu Zhang, and Qiang Yang. 2018. Conet: Collaborative cross networks for cross-domain recommendation. In Proceedings of CIKM. 667--676.Google ScholarDigital Library
- Wang-Cheng Kang and Julian McAuley. 2018. Self-attentive sequential recommendation. In Proceedings of ICDM. IEEE, 197--206.Google ScholarCross Ref
- Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR.Google Scholar
- Hoyeop Lee, Jinbae Im, Seongwon Jang, Hyunsouk Cho, and Sehee Chung. 2019. Melu: Meta-learned user preference estimator for cold-start recommendation. In Proceedings of KDD. 1073--1082.Google ScholarDigital Library
- Jingjing Li, Ke Lu, Zi Huang, and Heng Tao Shen. 2019. On both cold-start and long-tail recommendation with social data. IEEE Transactions on Knowledge and Data Engineering (TKDE), Vol. 33, 1 (2019), 194--208.Google ScholarDigital Library
- Pan Li and Alexander Tuzhilin. 2020. Ddtcdr: Deep dual transfer cross domain recommendation. In Proceedings of WSDM. 331--339.Google ScholarDigital Library
- Xixun Lin, Jia Wu, Chuan Zhou, Shirui Pan, Yanan Cao, and Bin Wang. 2021. Task-adaptive Neural Process for User Cold-Start Recommendation. In Proceedings of WWW. 1306--1316.Google ScholarDigital Library
- Siwei Liu, Iadh Ounis, Craig Macdonald, and Zaiqiao Meng. 2020b. A heterogeneous graph neural model for cold-start recommendation. In Proceedings of SIGIR. 2029--2032.Google ScholarDigital Library
- Zhaoyang Liu, Haokun Chen, Fei Sun, Xu Xie, Jinyang Gao, Bolin Ding, and Yanyan Shen. 2020a. Intent Preference Decoupling for User Representation on Online Recommender System.. In Proceedings of IJCAI. 2575--2582.Google ScholarCross Ref
- Yuanfu Lu, Yuan Fang, and Chuan Shi. 2020. Meta-learning on heterogeneous information networks for cold-start recommendation. In Proceedings of KDD. 1563--1573.Google ScholarDigital Library
- Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. 2018. A Simple Neural Attentive Meta-Learner. In Proceedings of ICLR.Google Scholar
- Tsendsuren Munkhdalai and Hong Yu. 2017. Meta networks. In Proceedings of ICML. PMLR, 2554--2563.Google Scholar
- Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong, and Tom Goldstein. 2021. Data augmentation for meta-learning. In Proceedings of ICML. PMLR, 8152--8161.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 Proceedings of SIGIR. 695--704.Google ScholarDigital Library
- Haoyu Pang, Fausto Giunchiglia, Ximing Li, Renchu Guan, and Xiaoyue Feng. 2022. Pnmta: A pretrained network modulation and task adaptation approach for user cold-start recommendation. In Proceedings of the ACM Web Conference 2022. 348--359.Google ScholarDigital Library
- Sujoy Roy and Sharath Chandra Guntuku. 2016. Latent factor representations for cold-start video recommendation. In Proceedings of RecSys. 99--106.Google ScholarDigital Library
- Suvash Sedhain, Aditya Krishna Menon, Scott Sanner, and Lexing Xie. 2015. Autorec: Autoencoders meet collaborative filtering. In Proceedings of WWW. 111--112.Google ScholarDigital Library
- Suvash Sedhain, Scott Sanner, Darius Braziunas, Lexing Xie, and Jordan Christensen. 2014. Social collaborative filtering for cold-start recommendations. In Proceedings of Recsys. 345--348.Google ScholarDigital Library
- Chuan Shi, Binbin Hu, Wayne Xin Zhao, and S Yu Philip. 2018. Heterogeneous information network embedding for recommendation. IEEE Transactions on Knowledge and Data Engineering (TKDE), Vol. 31, 2 (2018), 357--370.Google ScholarDigital Library
- Fei Sun, Jun Liu, Jian Wu, Changhua Pei, Xiao Lin, Wenwu Ou, and Peng Jiang. 2019. BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. In Proceedings of CIKM. 1441--1450.Google ScholarDigital Library
- Xuehan Sun, Tianyao Shi, Xiaofeng Gao, Yanrong Kang, and Guihai Chen. 2021. FORM: Follow the Online Regularized Meta-Leader for Cold-Start Recommendation. In Proceedings of SIGIR. 1177--1186.Google ScholarDigital Library
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In Proceedings of ICLR.Google Scholar
- Maksims Volkovs, Guangwei Yu, and Tomi Poutanen. 2017. Dropoutnet: Addressing cold start in recommender systems. Proceedings of NeurIPS, Vol. 30 (2017).Google Scholar
- Chunyang Wang, Yanmin Zhu, Haobing Liu, Tianzi Zang, Jiadi Yu, and Feilong Tang. 2022. Deep Meta-learning in Recommendation Systems: A Survey. arXiv preprint arXiv:2206.04415 (2022).Google Scholar
- Hongwei Wang, Fuzheng Zhang, Jialin Wang, Miao Zhao, Wenjie Li, Xing Xie, and Minyi Guo. 2018. Ripplenet: Propagating user preferences on the knowledge graph for recommender systems. In Proceedings of CIKM. 417--426.Google ScholarDigital Library
- Hongwei Wang, Fuzheng Zhang, Mengdi Zhang, Jure Leskovec, Miao Zhao, Wenjie Li, and Zhongyuan Wang. 2019c. Knowledge-aware graph neural networks with label smoothness regularization for recommender systems. In Proceedings of KDD. 968--977.Google ScholarDigital Library
- Li Wang, Binbin Jin, Zhenya Huang, Hongke Zhao, Defu Lian, Qi Liu, and Enhong Chen. 2021. Preference-adaptive meta-learning for cold-start recommendation. In Proceedings of IJCAI. 1607--1614.Google ScholarCross Ref
- Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, and Tat-Seng Chua. 2019a. Kgat: Knowledge graph attention network for recommendation. In Proceedings of KDD. 950--958.Google ScholarDigital Library
- Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Yanfang Ye, Peng Cui, and Philip S Yu. 2019b. Heterogeneous graph attention network. In Proceedings of WWW. 2022--2032.Google ScholarDigital Library
- Huaxiu Yao, Long-Kai Huang, Linjun Zhang, Ying Wei, Li Tian, James Zou, Junzhou Huang, et al. 2021. Improving generalization in meta-learning via task augmentation. In Proceedings of ICML. PMLR, 11887--11897.Google Scholar
- Huaxiu Yao, Ying Wei, Junzhou Huang, and Zhenhui Li. 2019a. Hierarchically structured meta-learning. In Proceedings of ICML. PMLR, 7045--7054.Google Scholar
- Huaxiu Yao, Xian Wu, Zhiqiang Tao, Yaliang Li, Bolin Ding, Ruirui Li, and Zhenhui Li. 2019b. Automated Relational Meta-learning. In Proceedings of ICLR.Google Scholar
- Mingzhang Yin, George Tucker, Mingyuan Zhou, Sergey Levine, and Chelsea Finn. [n. d.]. Meta-Learning without Memorization. In Proceedings of ICLR.Google Scholar
- Runsheng Yu, Yu Gong, Xu He, Yu Zhu, Qingwen Liu, Wenwu Ou, and Bo An. 2021. Personalized Adaptive Meta Learning for Cold-start User Preference Prediction. In Proceedings of AAAI, Vol. 35. 10772--10780.Google ScholarCross Ref
- Yan Zhang, Changyu Li, Ivor W Tsang, Hui Xu, Lixin Duan, Hongzhi Yin, Wen Li, and Jie Shao. 2022. Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations. In ICDE. IEEE, 2942--2955.Google Scholar
- Cheng Zhao, Chenliang Li, Rong Xiao, Hongbo Deng, and Aixin Sun. 2020. CATN: Cross-domain recommendation for cold-start users via aspect transfer network. In Proceedings of SIGIR. 229--238.Google ScholarDigital Library
- Yongchun Zhu, Ruobing Xie, Fuzhen Zhuang, Kaikai Ge, Ying Sun, Xu Zhang, Leyu Lin, and Juan Cao. 2021. Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks. In Proceedings of SIGIR. 1167--1176.Google ScholarDigital Library
- Ziwei Zhu, Shahin Sefati, Parsa Saadatpanah, and James Caverlee. 2020. Recommendation for new users and new items via randomized training and mixture-of-experts transformation. In Proceedings of SIGIR. 1121--1130.Google ScholarDigital Library
Index Terms
- A Preference Learning Decoupling Framework for User Cold-Start Recommendation
Recommendations
Semi-supervised discriminative preference elicitation for cold-start recommendation
CIKM '13: Proceedings of the 22nd ACM international conference on Information & Knowledge ManagementRecommendation for cold users is fairly challenging because no prior rating can be used in preference prediction. To tackle this cold-start scenario, rating elicitation is usually employed through an initial interview in which users are queried by some ...
Improving Cold Start Recommendation by Mapping Feature-Based Preferences to Item Comparisons
UMAP '17: Proceedings of the 25th Conference on User Modeling, Adaptation and PersonalizationMany Recommender Systems (RSs) rely on user preference data in the form of ratings or likes for items. Previous research has shown that item comparisons can also be effectively used to model user preferences and build RS. However, users often express ...
An Industrial Framework for Cold-Start Recommendation in Zero-Shot Scenarios
SIGIR '22: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information RetrievalThere exists the cold-start problem in the recommendation systems when observed user-item interactions are insufficient. To alleviate this problem, most existing works aim to learn globally shared prior knowledge across all items and be fast adapted to ...
Comments