Deployable and Continuable Meta-learning-Based Recommender System with Fast User-Incremental Updates
Lists
Only you see this
Abstract
User cold-start is a major challenge in building personalized recommender systems. Due to the lack of sufficient interactions, it is difficult to effectively model new users. One of the main solutions is to obtain an initial model through meta-learning (mainly gradient-based methods) and adapt it to new users with a few steps of gradient descent. Although these methods have achieved remarkable performance, they are still far from being usable in real-world applications due to their high-demand data processing, heavy computational burden, and inability to perform effective user-incremental update. In this paper, we propose a d eployable and c ontinuable m eta-learning-based r ecommendation (DCMR) approach, which can achieve fast user-incremental updating with task replay and first-order gradient descent. Specifically, we introduce a dual-constrained task sampler, distillation-based loss functions, and an adaptive controller in this framework to balance the trade-off between stability and plasticity in updating. In summary, DCMR can be updated while serving new users; in other words, it learns continuously and rapidly from a sequential user stream and is able to make recommendations at any time. The extensive experiments conducted on three benchmark datasets illustrate the superiority of our model.
BibTeX
@inproceedings{guan2022deployable,
author = {Renchu Guan and Haoyu Pang and Fausto Giunchiglia and Ximing Li and Xuefeng Yang and Xiaoyue Feng},
title = {{Deployable and Continuable Meta-learning-Based Recommender System with Fast User-Incremental Updates}},
booktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},
year = {2022},
doi = {10.1145/3477495.3531964},
}Loading related content...