• Publications
  • Influence
Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks
TLDR
We introduce a novel framework based on Recurrent Neural Networks (RNN). Expand
  • 220
  • 27
  • PDF
Variational Reasoning for Question Answering with Knowledge Graph
TLDR
We propose a novel and unified deep learning architecture, and an end-to-end variational learning algorithm which can handle noise in questions, and learn multi-hop reasoning simultaneously. Expand
  • 120
  • 12
  • PDF
KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
TLDR
We propose a novel framework for answering science exam questions, which mimics human solving process in an open-book exam. Expand
  • 18
  • 5
  • PDF
Facial Expression Recognition Using Weighted Mixture Deep Neural Network Based on Double-Channel Facial Images
TLDR
A weighted mixture deep neural network is proposed to automatically extract the features that are effective for facial expression recognition tasks. Expand
  • 58
  • 4
Psychological advertising: exploring user psychology for click prediction in sponsored search
TLDR
We propose to systematically model user psychological desire in sponsored search according to Maslow's desire theory in order for a precise prediction on ad clicks. Expand
  • 29
  • 4
  • PDF
Counting challenging crowds robustly using a multi-column multi-task convolutional neural network
TLDR
A multi-column multi-task convolutional neural network is proposed for robust crowd counting, which is achieved through summing up the density map estimated by the proposed network. Expand
  • 16
  • 3
Efficient Probabilistic Logic Reasoning with Graph Neural Networks
TLDR
We propose a GNN variant, named ExpressGNN, which strikes a nice balance between the representation power and the simplicity of the model. Expand
  • 14
  • 1
  • PDF
FLASH: Fast Bayesian Optimization for Data Analytic Pipelines
TLDR
We propose Fast LineAr SearcH (FLASH), an efficient method for tuning analytic pipelines. Expand
  • 18
  • 1
  • PDF
Standalone Systolic Profile Detection of Non-Contact SCG Signal With LSTM Network
TLDR
A single-layer bi-directional long short-term memory (LSTM) network is used to distinguish SP, which is the part of SCG that depicts the phase of systole, including fiducial points such as isovolumic contraction (IM) and aortic valve opening (AO) points. Expand
  • 3
  • 1