34 citations · 71 across the 8 of their papers we have counts for
7 papers · 1 filter
Learning Compact Features via In-Training Representation Alignment
Xin Li, Xiangrui Li, Deng Pan +2
Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of the feature extractor (i.e., last hidden layer) and a linear classifier (i.e., output layer) that…
Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints
Xin Li, Xiangrui Li, Deng Pan +1
Convolutional neural networks (CNNs) have achieved state-of-the-art performance on various tasks in computer vision. However, recent studies demonstrate that these models are vulne…
Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability
Deng Pan, Xiangrui Li, Xin Li +1
Latent factor collaborative filtering (CF) has been a widely used technique for recommender system by learning the semantic representations of users and items. Recently, explainabl…
On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks
Xiangrui Li, Xin Li, Deng Pan +1
Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made significant advancement in visual recognition tasks in computer vision. When training d…
Improve SGD Training via Aligning Mini-batches
Xiangrui Li, Deng Pan, Xin Li +1
Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is…
CRCEN: A Generalized Cost-sensitive Neural Network Approach for Imbalanced Classification
Xiangrui Li, Dongxiao Zhu
Classification on imbalanced datasets is a challenging task in real-world applications. Training conventional classification algorithms directly by minimizing classification error…
SAFS: A Deep Feature Selection Approach for Precision Medicine
Milad Zafar Nezhad, Dongxiao Zhu, Xiangrui Li +2
In this paper, we propose a new deep feature selection method based on deep architecture. Our method uses stacked auto-encoders for feature representation in higher-level abstracti…