Meta-Learning Helps Personalized Product Search
WWW 2022 - Proceedings of the ACM Web Conference 2022
Personalized product search that provides users with customized search services is an important task for e-commerce platforms. This task remains a challenge when inferring users' preferences from few records or even no records, which is also known as the few-shot or zero-shot learning problem. In this paper, we propose a Bayesian Online Meta-Learning Model (BOML), which transfers meta-knowledge, from the inference for other users' preferences, to help to infer the current user's interest behind her/his few or even no historical records. To extract meta-knowledge from various inference patterns, our model constructs a mixture of meta-knowledge and transfers the corresponding meta-knowledge to the specific user according to her/his records. Based on the meta-knowledge learned from other similar inferences, our proposed model searches a ranked list of products to meet users' personalized query intents for those with few search records (i.e., few-shot learning problem) or even no search records (i.e., zero-shot learning problem). Under the records arriving sequentially setting, we propose an online variational inference algorithm to update meta-knowledge over time. Experimental results demonstrate that our proposed BOML outperforms state-of-the-art algorithms. © 2022 ACM.
E-learning, Knowledge management, Learning systems, Bayesian, Learning problem, Meta-knowledge, Meta-learning models, Metalearning, Online learning, Personalized products, Product search, Search services, User's preferences, Inference engines
B. Wu, Z. Meng, Q. Zhang, and S. Liang, "Meta-Learning Helps Personalized Product Search", in 31st ACM World Wide Web Conference, WWW 2022, April 25-29, 2022 [Online]. DOI:10.1145/3485447.3512036