Preventing Overfitting via Sample Reweighting for Recommender System Incremental Update (Student Abstract)

Authors

  • Danni Peng Nanyang Technological University Alibaba-NTU Singapore Joint Research Institute
  • Xiaobo Hu Alibaba Group
  • Anxiang Zeng Nanyang Technological University
  • Jie Zhang Nanyang Technological University

Keywords:

Recommender System, Incremental Update, Sample Reweighting

Abstract

Incremental update of recommender system models using only newly arrived data may easily cause the model to overfit to the current data. To address this issue without relying on historical data, we propose a sample reweighting method based on prediction performance of previous model on current data. The proposed method effectively alleviates the problem of overfitting and improves the performance of incremental update.

Downloads

Published

2021-05-18

How to Cite

Peng, D., Hu, X., Zeng, A., & Zhang, J. (2021). Preventing Overfitting via Sample Reweighting for Recommender System Incremental Update (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15863-15864. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17928

Issue

Section

AAAI Student Abstract and Poster Program