Existing research efforts for multi-interest candidate matching in recommender systems mainly focus on improving model architecture or incorporating additional information …
Sequential recommendation is one of the most important tasks in recommender systems, which aims to recommend the next interacted item with historical behaviors as input …
Z Si, Z Sun, J Chen, G Chen, X Zang, K Zheng… - arXiv preprint arXiv …, 2023 - arxiv.org
The retrieval phase is a vital component in recommendation systems, requiring the model to be effective and efficient. Recently, generative retrieval has become an emerging paradigm …
The pre-training paradigm, ie, learning universal knowledge across a wide spectrum of domains, has increasingly become a new de-facto practice in many fields, especially for …
Z Zhu, S Li, Y Liu, X Zhang, Z Feng, Y Hou - World Wide Web, 2024 - Springer
The sequential recommendation task based on the multi-interest framework aims to model multiple interests of users from different aspects to predict their future interactions. However …
M Li, X Chen, J Xiang, Q Zhang, C Ma, C Dai… - Proceedings of the 17th …, 2024 - dl.acm.org
Text matching systems have become a fundamental service in most Searching platforms. For instance, they are responsible for matching user queries to relevant candidate items, or …
Q Liu, Z Liu, Z Zhu, S Wu, L Wang - arXiv preprint arXiv:2304.05615, 2023 - arxiv.org
Recently, multi-interest models, which extract interests of a user as multiple representation vectors, have shown promising performances for sequential recommendation. However …
Y Liu, X Zhang, M Zou, Z Feng - … of the 17th ACM Conference on …, 2023 - dl.acm.org
Multi-interest recommendation methods extract multiple interest vectors to represent the user comprehensively. Despite their success in the matching stage, previous works overlook the …
Personalized recommender systems aim to predict users' preferences for items. It has become an indispensable part of online services. Online social platforms enable users to …