向潛在感興趣的用戶推薦物品是一項重要的商業任務，它面臨著兩個主要的挑戰：準確性和可解釋性。傳統協同過濾算法依賴於對用戶和物品之間大規模交互數據的統計計算，可以達到很高的性能，但解釋能力不足。我們提出了UIPC-MF的方法，它是一種基於原型的矩陣分解的演算法，可建構可解釋的協同過濾推薦。在UIPC-MF中，每位用戶和每個項目都與用戶和項目的原型集相關聯，每個原型用於學習數據集中的社交協同屬性。為了提高可解釋性，UIPC-MF學習了反映用戶和項目原型之間關聯的連接權重。在三個真實數據集上，UIPC-MF在命中率和正規化折扣累計增益的指標表現皆優於最先進的基準演算法，同時也提供了更佳的模型透明度。

Recommending items to potential interested users has been an important commercial task that faces with two main challenges the accuracy and explainability. Collaborative filtering relies on statistical computing on a large scale of interaction data between users and items and can achieve high performance but vaguer explanation power. We propose UIPC-MF, a prototype-based matrix factorization method for explainable collaborative filtering recommendation. In UIPC-MF, both users and items are associated with sets of prototypes, capturing general collaborative attributes. To enhance explainability, UIPC-MF learns connection weights that reflect the association relations between user and item prototypes for recommendation. UIPC-MF outperforms state-of-the-art baseline methods in terms of Hit Ratio and Normalized Discounted Cumulative Gain on three datasets while also providing better transparency.

[1] Christoph Molnar. Interpretable Machine Learning. 2 edition, 2022. URL https://christophm.github.io/interpretable-ml-book.
[2] Yu Zhang, Peter Tino, Ale ˇ s Leonardis, and Ke Tang. A survey on neural network interpretability. IEEE Transactions on Emerging Topics in Computational Intelligence, 5(5):726–742, 2021.
[3] Oscar Li, Hao Liu, Chaofan Chen, and Cynthia Rudin. Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018.
[4] Chaofan Chen, Oscar Li, Daniel Tao, Alina Barnett, Cynthia Rudin, and Jonathan KSu. This looks like that: deep learning for interpretable image recognition. Advances in neural information processing systems, 32, 2019.
[5] Meike Nauta, Ron Van Bree, and Christin Seifert. Neural prototype trees for interpretable fine-grained image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14933–14943, 2021.
[6] Monish Keswani, Sriranjani Ramakrishnan, Nishant Reddy, and Vineeth N Balasubramanian. Proto2proto: Can you recognize the car, the way i do? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10233–10243, 2022.
[7] Nava Tintarev and Judith Masthoff. Explaining recommendations: Design and evaluation. Recommender systems handbook, pages 353–382, 2015.
[8] Xu Chen, Yongfeng Zhang, and Ji-Rong Wen. Measuring” why” in recommender systems: a comprehensive survey on the evaluation of explainable recommendation. arXiv preprint arXiv:2202.06466, 2022.
[9] Krisztian Balog and Filip Radlinski. Measuring recommendation explanation quality: The conflicting goals of explanations. In Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, pages 329–338, 2020.
[10] Yehuda Koren, Robert Bell, and Chris Volinsky. Matrix factorization techniques for recommender systems. Computer, 42(8):30–37, 2009.
[11] Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI ’09, page 452–461. AUAI Press, 2009.
[12] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collaborative filtering. In Proceedings of the 26th international conference on world wide web, pages 173–182, 2017.
[13] Dawen Liang, Rahul G Krishnan, Matthew D Hoffman, and Tony Jebara. Variational autoencoders for collaborative filtering. In Proceedings of the 2018 world wide web conference, pages 689–698, 2018.
[14] Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, and Meng Wang. Lightgcn: Simplifying and powering graph convolution network for recommendation. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pages 639–648, 2020.
[15] Yongfeng Zhang, Xu Chen, et al. Explainable recommendation: A survey and new perspectives. Foundations and Trends® in Information Retrieval, 14(1):1–101, 2020.
[16] Jingwu Chen, Fuzhen Zhuang, Xin Hong, Xiang Ao, Xing Xie, and Qing He. Attention-driven factor model for explainable personalized recommendation. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pages 909–912, 2018.
[17] Xiting Wang, Yiru Chen, Jie Yang, Le Wu, Zhengtao Wu, and Xing Xie. A reinforcement learning framework for explainable recommendation. In 2018 IEEE international conference on data mining (ICDM), pages 587–596. IEEE, 2018.
[18] Oren Barkan, Roy Hirsch, Ori Katz, Avi Caciularu, and Noam Koenigstein. Anchorbased collaborative filtering. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pages 2877–2881, 2021.
[19] Alessandro B Melchiorre, Navid Rekabsaz, Christian Ganhor, and Markus Schedl. Protomf: Prototype-based matrix factorization for effective and explainable recommendations. In Proceedings of the 16th ACM Conference on Recommender Systems, pages 246–256, 2022.
[20] Paolo Cremonesi, Yehuda Koren, and Roberto Turrin. Performance of recommender algorithms on top-n recommendation tasks. In Proceedings of the fourth ACM conference on Recommender systems, pages 39–46, 2010.
[21] Zainab Zolaktaf, Reza Babanezhad, and Rachel Pottinger. A generic top-n recommendation framework for trading-off accuracy, novelty, and coverage. In 2018 IEEE 34th International Conference on Data Engineering (ICDE), pages 149–160. IEEE, 2018.
[22] Steffen Rendle. Item recommendation from implicit feedback. In Recommender Systems Handbook, pages 143–171. Springer, 2021.
[23] Jiancan Wu, Xiang Wang, Xingyu Gao, Jiawei Chen, Hongcheng Fu, Tianyu Qiu, and Xiangnan He. On the effectiveness of sampled softmax loss for item recommendation. arXiv preprint arXiv:2201.02327, 2022.
[24] F Maxwell Harper and Joseph A Konstan. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):1–19, 2015.
[25] Julian McAuley, Christopher Targett, Qinfeng Shi, and Anton Van Den Hengel. Image-based recommendations on styles and substitutes. In Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, pages 43–52, 2015.
[26] Marta Moscati, Emilia Parada-Cabaleiro, Yashar Deldjoo, Eva Zangerle, and Markus Schedl. Music4all-onion—a large-scale multi-faceted content-centric music recommendation dataset. In Proceedings of the 31th ACM International Conference on Information & Knowledge Management (CIKM’22), 2022.
[27] Markus Schedl, Stefan Brandl, Oleg Lesota, Emilia Parada-Cabaleiro, David Penz, and Navid Rekabsaz. Lfm-2b: a dataset of enriched music listening events for recommender systems research and fairness analysis. In ACM SIGIR Conference on Human Information Interaction and Retrieval, pages 337–341, 2022.
[28] Benjamin Wang. Ranking evaluation metrics for recommender systems, 2021. URL https://towardsdatascience.com/ranking-evaluationmetrics-for-recommender-systems-263d0a66ef54.
[29] Wikipedia contributors. Discounted cumulative gain — Wikipedia the free encyclopedia. URL https://en.wikipedia.org/wiki/Discounted_cumulative_gain.
[30] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
[31] John Duchi, Elad Hazan, and Yoram Singer. Adaptive subgradient methods for online learning and stochastic optimization. Journal of machine learning research, 12(7), 2011.
[32] James Bergstra, Remi Bardenet, Yoshua Bengio, and Bal ´ azs K ´ egl. Algorithms for ´hyper-parameter optimization. Advances in neural information processing systems, 24, 2011.
[33] Lisha Li, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, and Ameet Talwalkar. Hyperband: A novel bandit-based approach to hyperparameter optimization. The Journal of Machine Learning Research, 18(1):6765–6816, 2017.
[34] Optunity contributors. Tree-structured parzen estimator, . URL https://optunity.readthedocs.io/en/latest/user/solvers/TPE.html.
[35] OpenVINO contributors. Tree-structured parzen estimator (tpe), . URL https://docs.openvino.ai/2021.4/pot_compression_optimization_tpe_README.html.
[36] Will Koehrsen. A conceptual explanation of bayesian hyperparameter optimization for machine learning, 2018. URL https://towardsdatascience.com/a-conceptual-explanation-of-bayesian-model-basedhyperparameter-optimization-for-machine-learningb8172278050f.
[37] James Bergstra, Daniel Yamins, and David Cox. Making a science of model search:Hyperparameter optimization in hundreds of dimensions for vision architectures. In International conference on machine learning, pages 115–123. PMLR, 2013.
[38] Brandon M. Wood. A novice’s guide to hyperparameter optimization at scale, 2020. URL https://wood-b.github.io/post/a-novices-guideto-hyperparameter-optimization-at-scale/.
[39] Himan Abdollahpouri, Masoud Mansoury, Robin Burke, and Bamshad Mobasher. The unfairness of popularity bias in recommendation. arXiv preprint arXiv:1907.13286, 2019.
[40] Aravind Sankar, Junting Wang, Adit Krishnan, and Hari Sundaram. Protocf: Prototypical collaborative filtering for few-shot recommendation. In Proceedings of the 15th ACM Conference on Recommender Systems, pages 166–175, 2021