Learning Robust Recommenders Through Cross-Model Agreement

Wang, Y., Xin, X., Meng, Z. , Jose, J. M. , Feng, F. and He, X. (2022) Learning Robust Recommenders Through Cross-Model Agreement. In: ACM Web Conference 2022, Lyon, France, 25-29 April 2022, pp. 2015-2025. ISBN 9781450390965 (doi: 10.1145/3485447.3512202)

[img] Text
265372.pdf - Accepted Version



Learning from implicit feedback is one of the most common cases in the application of recommender systems. Generally speaking, interacted examples are considered as positive while negative examples are sampled from uninteracted ones. However, noisy examples are prevalent in real-world implicit feedback. A noisy positive example could be interacted but it actually leads to negative user preference. A noisy negative example which is uninteracted because of user unawareness could also denote potential positive user preference. Conventional training methods overlook these noisy examples, leading to sub-optimal recommendations. In this work, we propose a general framework to learn robust recommenders from implicit feedback. Through an empirical study, we find that different models make relatively similar predictions on clean examples which denote the real user preference, while the predictions on noisy examples vary much more across different models. Motivated by this observation, we propose denoising with cross-model agreement (DeCA) which minimizes the KL-divergence between the real user preference distributions parameterized by two recommendation models while maximizing the likelihood of data observation. We instantiate DeCA on four representative recommendation models, empirically demonstrating its superiority over normal training and existing denoising methods. Codes are available at https://github.com/wangyu-ustc/DeCA.

Item Type:Conference Proceedings
Additional Information:This work is supported by the National Key Research and Development Program of China (2020AAA0106000).
Glasgow Author(s) Enlighten ID:Jose, Professor Joemon and Meng, Dr Zaiqiao and Xin, Xin
Authors: Wang, Y., Xin, X., Meng, Z., Jose, J. M., Feng, F., and He, X.
College/School:College of Science and Engineering > School of Computing Science
Copyright Holders:Copyright © 2022 Association for Computing Machinery
First Published:First published in ACM Web Conference 2022: 2015-2025
Publisher Policy:Reproduced in accordance with the publisher copyright policy
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record