activity
20192022
most citedExplainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

30 citations · 37 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG20203 cited

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…

cs.LG202030 cited

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…

cs.LG20203 cited

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…

cs.LG2020

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…

eess.IV20191 cited

Interpreting Age Effects of Human Fetal Brain from Spontaneous fMRI using Deep 3D Convolutional Neural Networks

Xiangrui Li, Jasmine Hect, Moriah Thomason +1

Understanding human fetal neurodevelopment is of great clinical importance as abnormal development is linked to adverse neuropsychiatric outcomes after birth. Recent advances in fu…

cs.LG2019

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…