most citedExplainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

30 citations · 38 across the 4 of their papers we have counts for

collaborators

6 papers

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.LG20205 cited

Defending against adversarial attacks on medical imaging AI system, classification or detection?

Xin Li, Deng Pan, Dongxiao Zhu

Medical imaging AI systems such as disease classification and segmentation are increasingly inspired and transformed from computer vision based AI systems. Although an array of adv…

cs.CL2020

Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

Yao Qiang, Xin Li, Dongxiao Zhu

Existing aspect based sentiment analysis (ABSA) approaches leverage various neural network models to extract the aspect sentiments via learning aspect-specific feature representati…

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…

cs.CV2019

Vispi: Automatic Visual Perception and Interpretation of Chest X-rays

Xin Li, Rui Cao, Dongxiao Zhu

Medical imaging contains the essential information for rendering diagnostic and treatment decisions. Inspecting (visual perception) and interpreting image to generate a report are…