• Publications
  • Influence
Personalized Ranking Metric Embedding for Next New POI Recommendation
TLDR
The rapidly growing of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which enables many services, e.g., point-of-interest (POI) recommendation. Expand
  • 226
  • 49
  • PDF
Rank-GeoFM: A Ranking based Geographical Factorization Method for Point of Interest Recommendation
TLDR
We propose a ranking based geographical factorization method, called Rank-GeoFM, for POI recommendation, which addresses the two challenges. Expand
  • 219
  • 31
  • PDF
MultiRank: co-ranking for objects and relations in multi-relational data
TLDR
We propose a framework (MultiRank) to determine the importance of both objects and relations simultaneously based on a probability distribution computed from multi-relational data and develop an efficient iterative algorithm to solve a set of tensor (multivariate polynomial) equations to obtain such distribution. Expand
  • 103
  • 14
  • PDF
Low-Rank Tensor Completion with Total Variation for Visual Data Inpainting
TLDR
We argue that low-rank constraint, albeit useful, is not effective enough to exploit the local smooth and piecewise priors of visual data. Expand
  • 44
  • 11
  • PDF
HAR: Hub, Authority and Relevance Scores in Multi-Relational Data for Query Search
TLDR
We propose a framework HAR to study the hub and authority scores of objects, and the relevance scores of relations in multi-relational data for query search. Expand
  • 61
  • 8
  • PDF
Hyperspectral Image Classification With Deep Learning Models
TLDR
Deep learning has achieved great successes in conventional computer vision tasks. Expand
  • 87
  • 6
A general graph-based model for recommendation in event-based social networks
TLDR
We propose a general graph-based model, called HeteRS, to solve multiple recommendation problems on EBSNs in one framework. Expand
  • 78
  • 5
  • PDF
Heterogeneous Domain Adaptation via Soft Transfer Network
TLDR
We propose a Soft Transfer Network (STN), which jointly learns the domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for addressing the HDA problem. Expand
  • 13
  • 5
  • PDF
Stratified sampling for feature subspace selection in random forests for high dimensional data
TLDR
We propose a stratified sampling method to select the feature subspaces for random forests with high dimensional data. Expand
  • 109
  • 3
  • PDF
A General Recommendation Model for Heterogeneous Networks
TLDR
We propose a graph-based model, called HeteRS, which can solve general recommendation problems on heterogeneous networks, and the learned influence weights help understanding user behaviors. Expand
  • 35
  • 3