36 citations · 94 across the 6 of their papers we have counts for
6 papers
CROLoss: Towards a Customizable Loss for Retrieval Models in Recommender Systems
Yongxiang Tang, Wentao Bai, Guilin Li +2
In large-scale recommender systems, retrieving top N relevant candidates accurately with resource constrain is crucial. To evaluate the performance of such retrieval models, Recall…
DropNAS: Grouped Operation Dropout for Differentiable Architecture Search
Weijun Hong, Guilin Li, Weinan Zhang +4
Neural architecture search (NAS) has shown encouraging results in automating the architecture design. Recently, DARTS relaxes the search process with a differentiable formulation t…
Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation
Qijun Luo, Zhili Liu, Lanqing Hong +7
Semi-supervised domain adaptation (SSDA), which aims to learn models in a partially labeled target domain with the assistance of the fully labeled source domain, attracts increasin…
AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction
Bin Liu, Chenxu Zhu, Guilin Li +6
Learning feature interactions is crucial for click-through rate (CTR) prediction in recommender systems. In most existing deep learning models, feature interactions are either manu…
Hierarchical Neural Architecture Search via Operator Clustering
Guilin Li, Xing Zhang, Zitong Wang +4
Recently, the efficiency of automatic neural architecture design has been significantly improved by gradient-based search methods such as DARTS. However, recent literature has brou…
Revisiting Knowledge Distillation via Label Smoothing Regularization
Li Yuan, Francis E. H. Tay, Guilin Li +2
Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged info…