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

Zhen Liu, Xiaodong Feng, Yecheng Wang, Wenbo Zuo

Abstract: 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.