• Publications
  • Influence
LINE: Large-scale Information Network Embedding
TLDR
This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Expand
  • 2,514
  • 724
  • PDF
Pfp: parallel fp-growth for query recommendation
TLDR
We propose to parallelize the FP-Growth algorithm (we call our parallel algorithm PFP) on distributed machines. Expand
  • 429
  • 67
  • PDF
Comparisons of channel assignment strategies in cellular mobile telephone systems
  • M. Zhang, T. Yum
  • Computer Science
  • IEEE International Conference on Communications…
  • 11 June 1989
Two new channel assignment strategies are proposed. They are the locally optimized dynamic assignment (LODA) strategy and the borrowing with directional channel locking (BDCL) strategy. TheirExpand
  • 241
  • 31
Topic sentiment analysis in twitter: a graph-based hashtag sentiment classification approach
Twitter is one of the biggest platforms where massive instant messages (i.e. tweets) are published every day. Users tend to express their real feelings freely in Twitter, which makes it an idealExpand
  • 375
  • 30
  • PDF
Visualizing Large-scale and High-dimensional Data
TLDR
We study the problem of visualizing large-scale and high-dimensional data in a low-dimensional (typically 2D or 3D) space with the structure preserved. Expand
  • 166
  • 23
  • PDF
An Attention-based Collaboration Framework for Multi-View Network Representation Learning
TLDR
This paper studies learning node representations for networks with multiple views, which aims to infer robust node representations across different views. Expand
  • 77
  • 16
  • PDF
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
TLDR
We propose an effective and efficient method called the AutoInt to automatically learn the high-order feature interactions of input features. Expand
  • 73
  • 15
  • PDF
Understanding the Limiting Factors of Topic Modeling via Posterior Contraction Analysis
TLDR
We present theorems elucidating the posterior contraction rates of the topics as the amount of data increases, and a thorough supporting empirical study using synthetic and real data sets, including news and web-based articles and tweet messages. Expand
  • 168
  • 14
  • PDF
Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction
TLDR
In this paper, we develop a novel approach to aspect term extraction based on unsupervised learning of distributed representations of words and dependency paths. Expand
  • 98
  • 14
  • PDF
Towards Automated ICD Coding Using Deep Learning
TLDR
We use character-aware neural language models to generate hidden representations of written diagnosis descriptions and ICD codes, and design an attention mechanism to address the mismatch between the numbers of descriptions and corresponding codes. Expand
  • 57
  • 13
  • PDF