ABSTRACT
In recent times, deep learning methods have supplanted conventional collaborative filtering approaches as the backbone of modern recommender systems. However, their gains are skewed towards popular items with a drastic performance drop for the vast collection of long-tail items with sparse interactions. Moreover, we empirically show that prior neural recommenders lack the resolution power to accurately rank relevant items within the long-tail.
In this paper, we formulate long-tail item recommendations as a few-shot learning problem of learning-to-recommend few-shot items with very few interactions. We propose a novel meta-learning framework ProtoCF that learns-to-compose robust prototype representations for few-shot items. ProtoCF utilizes episodic few-shot learning to extract meta-knowledge across a collection of diverse meta-training tasks designed to mimic item ranking within the tail. To further enhance discriminative power, we propose a novel architecture-agnostic technique based on knowledge distillation to extract, relate, and transfer knowledge from neural base recommenders. Our experimental results demonstrate that ProtoCF consistently outperforms state-of-art approaches on overall recommendation (by 5% Recall@50) while achieving significant gains (of 60-80% Recall@50) for tail items with less than 20 interactions.
Supplemental Material
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In ICLR.Google Scholar
- Alex Beutel, Kenton Murray, Christos Faloutsos, and Alexander J Smola. 2014. Cobafi: collaborative bayesian filtering. In WWW. 97–108.Google Scholar
- Rodrigo Borges and Kostas Stefanidis. 2020. On Measuring Popularity Bias in Collaborative Filtering Data. In EDBT/ICDT Workshops.Google Scholar
- Da Cao, Liqiang Nie, Xiangnan He, Xiaochi Wei, Shunzhi Zhu, and Tat-Seng Chua. 2017. Embedding factorization models for jointly recommending items and user generated lists. In SIGIR. 585–594.Google Scholar
- Dong-Kyu Chae, Jin-Soo Kang, Sang-Wook Kim, and Jaeho Choi. 2019. Rating augmentation with generative adversarial networks towards accurate collaborative filtering. In WWW. 2616–2622.Google Scholar
- Dong-Kyu Chae, Jihoo Kim, Duen Horng Chau, and Sang-Wook Kim. 2020. AR-CF: Augmenting Virtual Users and Items in Collaborative Filtering for Addressing Cold-Start Problems. In SIGIR. 1251–1260.Google Scholar
- Zhihong Chen, Rong Xiao, Chenliang Li, Gangfeng Ye, Haochuan Sun, and Hongbo Deng. 2020. ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance. In SIGIR. 579–588.Google ScholarDigital Library
- Manqing Dong, Feng Yuan, Lina Yao, Xiwei Xu, and Liming Zhu. 2020. Mamo: Memory-augmented meta-optimization for cold-start recommendation. In 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 KDD. 2895–2904.Google Scholar
- Miao Fan, Yeqi Bai, Mingming Sun, and Ping Li. 2019. Large margin prototypical network for few-shot relation classification with fine-grained features. In CIKM.Google Scholar
- Spyros Gidaris and Nikos Komodakis. 2018. Dynamic few-shot visual learning without forgetting. In CVPR. 4367–4375.Google Scholar
- Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative filtering. In WWW. 173–182.Google Scholar
- Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531(2015).Google Scholar
- Andre Holzapfel, Bob Sturm, and Mark Coeckelbergh. 2018. Ethical dimensions of music information retrieval technology. TISMIR 1, 1 (2018), 44–55.Google Scholar
- Daeryong Kim and Bongwon Suh. 2019. Enhancing VAEs for collaborative filtering: flexible priors & gating mechanisms. In RecSys. 403–407.Google Scholar
- Yehuda Koren, Robert Bell, and Chris Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009), 30–37.Google ScholarDigital Library
- Adit Krishnan, Hari Cheruvu, Cheng Tao, and Hari Sundaram. 2019. A modular adversarial approach to social recommendation. In CIKM. 1753–1762.Google Scholar
- Adit Krishnan, Mahashweta Das, Mangesh Bendre, Hao Yang, and Hari Sundaram. 2020. Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation. In SIGIR. 1081–1090.Google Scholar
- Adit Krishnan, Ashish Sharma, Aravind Sankar, and Hari Sundaram. 2018. An adversarial approach to improve long-tail performance in neural collaborative filtering. In CIKM. 1491–1494.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 KDD. 1073–1082.Google Scholar
- Aoxue Li, Tiange Luo, Zhiwu Lu, Tao Xiang, and Liwei Wang. 2019. Large-scale few-shot learning: Knowledge transfer with class hierarchy. In CVPR. 7212–7220.Google Scholar
- Xiaopeng Li and James She. 2017. Collaborative variational autoencoder for recommender systems. In KDD. 305–314.Google Scholar
- Dawen Liang, Jaan Altosaar, Laurent Charlin, and David M Blei. 2016. Factorization meets the item embedding: Regularizing matrix factorization with item co-occurrence. In RecSys. 59–66.Google Scholar
- Dawen Liang, Rahul G Krishnan, Matthew D Hoffman, and Tony Jebara. 2018. Variational autoencoders for collaborative filtering. In WWW. 689–698.Google Scholar
- Yong Liu, Wei Wei, Aixin Sun, and Chunyan Miao. 2014. Exploiting geographical neighborhood characteristics for location recommendation. In CIKM. 739–748.Google Scholar
- Ziwei Liu, Zhongqi Miao, Xiaohang Zhan, Jiayun Wang, Boqing Gong, and Stella X Yu. 2019. Large-scale long-tailed recognition in an open world. In CVPR. 2537–2546.Google Scholar
- Yuanfu Lu, Yuan Fang, and Chuan Shi. 2020. Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation. In KDD. 1563–1573.Google Scholar
- Mi Luo, Fei Chen, Pengxiang Cheng, Zhenhua Dong, Xiuqiang He, Jiashi Feng, and Zhenguo Li. 2020. MetaSelector: meta-learning for recommendation with user-level adaptive model selection. In WWW. 2507–2513.Google Scholar
- Jingwei Ma, Jiahui Wen, Mingyang Zhong, Liangchen Liu, Chaojie Li, Weitong Chen, Yin Yang, Hongkui Tu, and Xue Li. 2019. DBRec: Dual-Bridging Recommendation via Discovering Latent Groups. In CIKM. 1513–1522.Google Scholar
- [30] Bernard Marr.2018. (2018). https://www.forbes.com/sites/bernardmarr/2018/04/18/netflix-used-big-data-to-identify-the-movies-that-are-too-scary-to-finish/Google Scholar
- Wonpyo Park, Dongju Kim, Yan Lu, and Minsu Cho. 2019. Relational knowledge distillation. In CVPR. 3967–3976.Google Scholar
- Yoon-Joo Park. 2012. The adaptive clustering method for the long tail problem of recommender systems. IEEE TKDE 25, 8 (2012), 1904–1915.Google Scholar
- Sachin Ravi and Hugo Larochelle. 2017. Optimization as a Model for Few-Shot Learning. In ICLR. OpenReview.net.Google Scholar
- Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In UAI.Google ScholarDigital Library
- Aravind Sankar, Yozen Liu, Jun Yu, and Neil Shah. 2021. Graph Neural Networks for Friend Ranking in Large-scale Social Platforms. In WWW. 2535–2546.Google Scholar
- Aravind Sankar, Yanhong Wu, Yuhang Wu, Wei Zhang, Hao Yang, and Hari Sundaram. 2020. Groupim: A mutual information maximization framework for neural group recommendation. In SIGIR. 1279–1288.Google ScholarDigital Library
- Aravind Sankar, Xinyang Zhang, Adit Krishnan, and Jiawei Han. 2020. Inf-vae: A variational autoencoder framework to integrate homophily and influence in diffusion prediction. In WSDM. 510–518.Google ScholarDigital Library
- Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In NeurIPS. 4077–4087.Google Scholar
- Rama Syamala Sreepada and Bidyut Kr Patra. 2020. Mitigating long tail effect in recommendations using few shot learning technique. Expert Sys. App. 140(2020).Google Scholar
- Qiuling Suo, Jingyuan Chou, Weida Zhong, and Aidong Zhang. 2020. TAdaNet: Task-Adaptive Network for Graph-Enriched Meta-Learning. In KDD. 1789–1799.Google Scholar
- Duyu Tang, Bing Qin, and Ting Liu. 2015. Document modeling with gated recurrent neural network for sentiment classification. In EMNLP. 1422–1432.Google Scholar
- Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. 2018. Latent relational metric learning via memory-based attention for collaborative ranking. In WWW. 729–739.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 NeurIPS. 6904–6914.Google Scholar
- Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, 2016. Matching networks for one shot learning. In NeurIPS. 3630–3638.Google Scholar
- Maksims Volkovs, Guangwei Yu, and Tomi Poutanen. 2017. Dropoutnet: Addressing cold start in recommender systems. In NeurIPS. 4957–4966.Google Scholar
- Huiwei Wang and Yong Zhao. 2020. ML2E: Meta-Learning Embedding Ensemble for Cold-Start Recommendation. IEEE Access 8(2020), 165757–165768.Google ScholarCross Ref
- Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, and Tat-Seng Chua. 2019. Kgat: Knowledge graph attention network for recommendation. In KDD. 950–958.Google ScholarDigital Library
- Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019. Neural graph collaborative filtering. In SIGIR. 165–174.Google Scholar
- Yu-Xiong Wang, Deva Ramanan, and Martial Hebert. 2017. Learning to model the tail. In NeurIPS. 7029–7039.Google Scholar
- Tianxin Wei, Ziwei Wu, Ruirui Li, Ziniu Hu, Fuli Feng, Xiangnan He, Yizhou Sun, and Wei Wang. 2020. Fast Adaptation for Cold-start Collaborative Filtering with Meta-learning. ICDM.Google Scholar
- Yao Wu, Christopher DuBois, Alice X Zheng, and Martin Ester. 2016. Collaborative denoising auto-encoders for top-n recommender systems. In WSDM. 153–162.Google Scholar
- Yao Wu, Xudong Liu, Min Xie, Martin Ester, and Qing Yang. 2016. CCCF: Improving collaborative filtering via scalable user-item co-clustering. In WSDM.Google ScholarDigital Library
- Gui-Rong Xue, Chenxi Lin, Qiang Yang, WenSi Xi, Hua-Jun Zeng, Yong Yu, and Zheng Chen. 2005. Scalable collaborative filtering using cluster-based smoothing. In SIGIR.Google Scholar
- Hongzhi Yin, Bin Cui, Jing Li, Junjie Yao, and Chen Chen. 2012. Challenging the long tail recommendation. arXiv preprint arXiv:1205.6700(2012).Google Scholar
- Runsheng Yu, Yu Gong, Xu He, Bo An, Yu Zhu, Qingwen Liu, and Wenwu Ou. 2020. Personalized Adaptive Meta Learning for Cold-start User Preference Prediction. AAAI (2020).Google Scholar
- Yin Zhang, Derek Zhiyuan Cheng, Tiansheng Yao, Xinyang Yi, Lichan Hong, and Ed H Chi. 2021. A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation. In WWW. 2220–2231.Google Scholar
- 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 SIGIR. 1121–1130.Google Scholar
Recommendations
A new similarity function for selecting neighbors for each target item in collaborative filtering
As one of the collaborative filtering (CF) techniques, memory-based CF technique which recommends items to users based on rating information of like-minded users (called neighbors) has been widely used and has also proven to be useful in many practices ...
Generating Top-N Items Recommendation Set Using Collaborative, Content Based Filtering and Rating Variance
AbstractThe main purpose of any recommendation system is to recommend items of users’ interest. Mostly content and collaborative filtering are widely used recommendation systems. Matrix factorization technique is also used by many recommendation systems. ...
Typicality-Based Collaborative Filtering Recommendation
Collaborative filtering (CF) is an important and popular technology for recommender systems. However, current CF methods suffer from such problems as data sparsity, recommendation inaccuracy, and big-error in predictions. In this paper, we borrow ideas ...
Comments