Debiasing graph transfer learning via item semantic clustering for cross-domain recommendations

Z Li, D Amagata, Y Zhang, T Hara… - … Conference on Big …, 2022 - ieeexplore.ieee.org
Deep learning-based recommender systems may lead to over-fitting when lacking training
interaction data. This over-fitting significantly degrades recommendation performances. To …

[PDF][PDF] Trends-enhanced attention & memory networks for ecommerce recommendation

Z Li, D Amagata, T Maekawa… - SIGIR Workshop on …, 2022 - sigir-ecom.github.io
How to capture both users' static and dynamic interests is a general problem for
recommender systems (RSs) in e-commerce. Researchers have recently introduced neural …

Concept drift detection with denoising autoencoder in incomplete data

J Murao, K Yonekawa, M Kurokawa, D Amagata… - … Conference on Mobile …, 2021 - Springer
Recent e-commerce and location-based services provide personalized recommendations
based on machine-learning models that take into account purchase and visiting histories …

[PDF][PDF] Research on Improving Online Recommendations

**智 - 2024 - ir.library.osaka-u.ac.jp
With the explosive growth of the number of online services and the items (ie, products) they
provide, it becomes extremely time-consuming for users to explore their interested products …