• Publications
  • Influence
ANRL: Attributed Network Representation Learning via Deep Neural Networks
TLDR
We propose a novel framework, named ANRL, to incorporate both the network structure and node attribute information in a principled way to learn robust representations in AINs. Expand
  • 79
  • 17
  • PDF
Cognitive Graph for Multi-Hop Reading Comprehension at Scale
TLDR
We propose a new CogQA framework for multi-hop question answering in web-scale documents. Expand
  • 73
  • 16
  • PDF
Representation Learning for Attributed Multiplex Heterogeneous Network
TLDR
We formalize the problem of embedding learning for the Attributed Multiplex Heterogeneous Network and propose a unified framework to address this problem. Expand
  • 72
  • 14
  • PDF
Association of glycemic variability and the presence and severity of coronary artery disease in patients with type 2 diabetes
BackgroundGlucose variability is one of components of the dysglycemia in diabetes and may play an important role in development of diabetic vascular complications. The objective of this study was toExpand
  • 175
  • 12
  • PDF
Towards Knowledge-Based Recommender Dialog System
TLDR
In this paper, we propose a novel end-to-end framework called KBRD, which stands for Knowledge-Based Recommender Dialog System. Expand
  • 20
  • 7
  • PDF
AliGraph: A Comprehensive Graph Neural Network Platform
TLDR
An increasing number of machine learning tasks require dealing with large graph datasets, which capture rich and complex relation- ship among potentially billions of elements. Expand
  • 34
  • 6
  • PDF
Dependent Hierarchical Beta Process for Image Interpolation and Denoising
TLDR
A dependent hierarchical beta process (dHBP) is developed as a prior for data that may be represented in terms of a sparse set of latent features, with covariate-dependent feature usage. Expand
  • 69
  • 3
  • PDF
Learning Disentangled Representations for Recommendation
TLDR
We present the MACRo-mIcro Disentangled Variational Auto-Encoder (MacridVAE) for learning disentangled representations from user behavior, which can bring enhanced robustness, interpretability, and controllability. Expand
  • 33
  • 3
  • PDF
Adversarial Detection with Model Interpretation
TLDR
We develop a novel adversary-resistant detection framework by utilizing the interpretation of ML models. Expand
  • 23
  • 3
  • PDF
PRRE: Personalized Relation Ranking Embedding for Attributed Networks
TLDR
We propose the Personalized Relation Ranking Embedding (PRRE) method for attributed networks which is capable of exploiting the partial correlation between node topology and attributes. Expand
  • 13
  • 3
  • PDF