Self-paced learning enhanced neural matrix factorization for noise-aware recommendation

作者：

Highlights：

• We propose a novel neural matrix factorization for noise-aware recommendation.

• We introduce a bounded self-paced learning schema to improve the robustness.

• The new method can determine noisy instances from clean ones well.

• Proposed method can perform better for recommendation task on real datasets.

摘要

•We propose a novel neural matrix factorization for noise-aware recommendation.•We introduce a bounded self-paced learning schema to improve the robustness.•The new method can determine noisy instances from clean ones well.•Proposed method can perform better for recommendation task on real datasets.

论文关键词：Recommendation,Deep learning,Noisy and outlier corruption,Instance weighting,Self-paced learning

论文评审过程：Received 30 March 2020, Revised 6 December 2020, Accepted 7 December 2020, Available online 13 December 2020, Version of Record 28 December 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106660