-
Article
Learning structured communication for multi-agent reinforcement learning
This work explores the large-scale multi-agent communication mechanism for multi-agent reinforcement learning (MARL). We summarize the general topology categories for communication structures, which are often ...
-
Chapter and Conference Paper
A Particle-Evolving Method for Approximating the Optimal Transport Plan
We propose an innovative algorithm that iteratively evolves a particle system to approximate the sample-wised Optimal Transport plan for given continuous probability densities. Our algorithm is proposed via th...
-
Chapter and Conference Paper
AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning
This paper proposes new ways of sample mixing by thinking of the process as generation of barycenter in a metric space for data augmentation. First, we present an optimal-transport-based mixup technique to gen...
-
Chapter and Conference Paper
Sequential Multi-fusion Network for Multi-channel Video CTR Prediction
In this work, we study video click-through rate (CTR) prediction, crucial for the refinement of video recommendation and the revenue of video advertising. Existing studies have verified the importance of model...
-
Chapter and Conference Paper
Parametric Fokker-Planck Equation
We derive the Fokker-Planck equation on the parametric space. It is...
-
Chapter and Conference Paper
Personalized Prescription for Comorbidity
Personalized medicine (PM) aiming at tailoring medical treatment to individual patient is critical in guiding precision prescription. An important challenge for PM is comorbidity due to the complex interrelati...
-
Chapter and Conference Paper
Parallel Randomized Block Coordinate Descent for Neural Probabilistic Language Model with High-Dimensional Output Targets
Training a large probabilistic neural network language model, with typical high-dimensional output is excessively time-consuming, which is one of the main reasons that more simplified models such as n-gram is oft...
-
Chapter and Conference Paper
Graduated Consistency-Regularized Optimization for Multi-graph Matching
Graph matching has a wide spectrum of computer vision applications such as finding feature point correspondences across images. The problem of graph matching is generally NP-hard, so most existing work pursues...
-
Chapter and Conference Paper
Learning the Hotness of Information Diffusions with Multi-dimensional Hawkes Processes
Modeling the information cascading process over networks has attracted a lot of research attention due to its wide applications in viral marketing, epidemiology and recommendation systems. In particular, infor...
-
Chapter and Conference Paper
On the Convergence of Graph Matching: Graduated Assignment Revisited
We focus on the problem of graph matching that is fundamental in computer vision and machine learning. Many state-of-the-arts frequently formulate it as integer quadratic programming, which incorporates both u...
-
Chapter
Dimensionality Reduction and Topic Modeling: From Latent Semantic Indexing to Latent Dirichlet Allocation and Beyond
The bag-of-words representation commonly used in text analysis can be analyzed very efficiently and retains a great deal of useful information, but it is also troublesome because the same thought can be expres...
-
Article
Simple and effective variational optimization of surface and volume triangulations
Optimizing surface and volume triangulations is critical for many advanced numerical simulation applications. We present a variational approach for smoothing triangulated surface and volume meshes to improve t...
-
Chapter and Conference Paper
Metric Learning for Regression Problems and Human Age Estimation
The estimation of human age from face images has great potential in real-world applications. However, how to discover the intrinsic aging trend is still a challenging problem. In this work, we proposed a gener...
-
Chapter and Conference Paper
Variational Graph Embedding for Globally and Locally Consistent Feature Extraction
Existing feature extraction methods explore either global statistical or local geometric information underlying the data. In this paper, we propose a general framework to learn features that account for both t...
-
Chapter and Conference Paper
Simple and Effective Variational Optimization of Surface and Volume Triangulations
Optimizing surface and volume triangulations is critical for advanced numerical simulations. We present a simple and effective variational approach for optimizing triangulated surface and volume meshes. Our me...
-
Article
Analysis of an alignment algorithm for nonlinear dimensionality reduction
The goal of dimensionality reduction or manifold learning for a given set of high-dimensional data points, is to find a low-dimensional parametrization for them. Usually it is easy to carry out this parametriz...
-
Chapter and Conference Paper
Optimizing Surface Triangulation Via Near Isometry with Reference Meshes
Optimization of the mesh quality of surface triangulation is critical for advanced numerical simulations and is challenging under the constraints of error minimization and density control. We derive a new meth...
-
Chapter and Conference Paper
IKNN: Informative K-Nearest Neighbor Pattern Classification
The K-nearest neighbor (KNN) decision rule has been a ubiquitous classification tool with good scalability. Past experience has shown that the optimal choice of K depends upon the data, making it laborious to tun...
-
Article
Open AccessTowards Inferring Protein Interactions: Challenges and Solutions
Discovering interacting proteins has been an essential part of functional genomics. However, existing experimental techniques only uncover a small portion of any interactome. Furthermore, these data often have...
-
Article
Linear low-rank approximation and nonlinear dimensionality reduction
We present our recent work on both linear and nonlinear data reduction methods and algorithms: for the linear case we discuss results on structure analysis of SVD of columnpartitioned matrices and sparse low-r...
