• Publications
  • Influence
Nonlinear Dimension Reduction via Local Tangent Space Alignment
TLDR
We present a new algorithm for manifold learning and nonlinear dimension reduction using tangent spaces learned by fitting an affine subspace in a neighborhood of each data point. Expand
R1-PCA: rotational invariant L1-norm principal component analysis for robust subspace factorization
TLDR
We propose a rotational invariant L1-norm PCA (R1-PCA) for the objective functions of PCA. Expand
A min-max cut algorithm for graph partitioning and data clustering
TLDR
An important application of graph partitioning is data clustering using a graph model - the pairwise similarities between all data objects form a weighted graph adjacency matrix that contains all necessary information for clustering. Expand
Learning Social Infectivity in Sparse Low-rank Networks Using Multi-dimensional Hawkes Processes
TLDR
We propose a convex optimization approach to discover the hidden network of social influence by modeling the recurrent events at different individuals as multidimensional Hawkes processes, emphasizing the mutual-excitation nature of the dynamics of event occurrence. Expand
Spectral Relaxation for K-means Clustering
TLDR
The popular K-means clustering partitions a data set by minimizing a sum-of-squares cost function. Expand
Scalable Influence Estimation in Continuous-Time Diffusion Networks
TLDR
We propose a randomized algorithm for influence estimation in continuous-time diffusion networks. Expand
On Updating Problems in Latent Semantic Indexing
TLDR
We develop new SVD-updating algorithms for three types of updating problems arising from latent semantic indexing for information retrieval to deal with rapidly changing document collections. Expand
Like like alike: joint friendship and interest propagation in social networks
TLDR
We propose a framework that exploits homophily to establish an integrated network linking a user to interested services and connecting different users with common interests, upon which both friendship and interests could be efficiently propagated. Expand
Name disambiguation in author citations using a K-way spectral clustering method
TLDR
We propose an unsupervised learning approach using K-way spectral clustering that disambiguates authors in citations. Expand
Automatic document metadata extraction using support vector machines
TLDR
We describe a support vector machine classification based method for metadata extraction from header part of research papers and show that it outperforms other machine learning methods on the same task. Expand
...
1
2
3
4
5
...