i-Razor: A Neural Input Razor for Feature Selection and Dimension Search in Large-Scale Recommender Systems

Posted by klaurent Peking

Kavli Affiliate: Ke Wang | First 5 Authors: Yao Yao, Bin Liu, Haoxun He, Dakui Sheng, Ke Wang | Summary: Input features play a crucial role in the predictive performance of DNN-based industrial recommender systems with thousands of categorical and continuous fields from users, items, contexts, and their interactions. Noisy features and inappropriate embedding dimension […]


Continue.. i-Razor: A Neural Input Razor for Feature Selection and Dimension Search in Large-Scale Recommender Systems

An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection

Posted by klaurent Tokyo

Kavli Affiliate: Jia Liu | First 5 Authors: Jia Liu, Wenjie Xuan, Yuhang Gan, Juhua Liu, Bo Du | Summary: Existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations, but ignore the universal domain shift induced by time-varying land cover changes, including luminance fluctuations and season changes […]


Continue.. An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection