Scalable Semantic Querying of Text

May 03, 2018

Xiaolan Wang, Aaron Feng, Behzad Golshan, Alon Halevy, George Mihaila, Hidekazu Oiwa, Wang-Chiew Tan

May 03, 2018

Xiaolan Wang, Aaron Feng, Behzad Golshan, Alon Halevy, George Mihaila, Hidekazu Oiwa, Wang-Chiew Tan

**Click to Read Paper**

Learning to Draw Samples with Amortized Stein Variational Gradient Descent

Oct 30, 2017

Yihao Feng, Dilin Wang, Qiang Liu

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient direction (Liu & Wang, 2016) that maximally decreases the KL divergence with the target distribution. Our method works for any target distribution specified by their unnormalized density function, and can train any black-box architectures that are differentiable in terms of the parameters we want to adapt. We demonstrate our method with a number of applications, including variational autoencoder (VAE) with expressive encoders to model complex latent space structures, and hyper-parameter learning of MCMC samplers that allows Bayesian inference to adaptively improve itself when seeing more data.
Oct 30, 2017

Yihao Feng, Dilin Wang, Qiang Liu

* Accepted by UAI 2017

**Click to Read Paper**

Towards Scalable Spectral Clustering via Spectrum-Preserving Sparsification

Oct 11, 2018

Yongyu Wang, Zhuo Feng

The eigendeomposition of nearest-neighbor (NN) graph Laplacian matrices is the main computational bottleneck in spectral clustering. In this work, we introduce a highly-scalable, spectrum-preserving graph sparsification algorithm that enables to build ultra-sparse NN (u-NN) graphs with guaranteed preservation of the original graph spectrums, such as the first few eigenvectors of the original graph Laplacian. Our approach can immediately lead to scalable spectral clustering of large data networks without sacrificing solution quality. The proposed method starts from constructing low-stretch spanning trees (LSSTs) from the original graphs, which is followed by iteratively recovering small portions of "spectrally critical" off-tree edges to the LSSTs by leveraging a spectral off-tree embedding scheme. To determine the suitable amount of off-tree edges to be recovered to the LSSTs, an eigenvalue stability checking scheme is proposed, which enables to robustly preserve the first few Laplacian eigenvectors within the sparsified graph. Additionally, an incremental graph densification scheme is proposed for identifying extra edges that have been missing in the original NN graphs but can still play important roles in spectral clustering tasks. Our experimental results for a variety of well-known data sets show that the proposed method can dramatically reduce the complexity of NN graphs, leading to significant speedups in spectral clustering.
Oct 11, 2018

Yongyu Wang, Zhuo Feng

**Click to Read Paper**

VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes

Sep 01, 2018

Zongji Wang, Feng Lu

Sep 01, 2018

Zongji Wang, Feng Lu

* 11 pages, 10 figures

**Click to Read Paper**

Given two possible treatments, there may exist subgroups who benefit greater from one treatment than the other. This problem is relevant to the field of marketing, where treatments may correspond to different ways of selling a product. It is similarly relevant to the field of public policy, where treatments may correspond to specific government programs. And finally, personalized medicine is a field wholly devoted to understanding which subgroups of individuals will benefit from particular medical treatments. We present a computationally fast tree-based method, ABtree, for treatment effect differentiation. Unlike other methods, ABtree specifically produces decision rules for optimal treatment assignment on a per-individual basis. The treatment choices are selected for maximizing the overall occurrence of a desired binary outcome, conditional on a set of covariates. In this poster, we present the methodology on tree growth and pruning, and show performance results when applied to simulated data as well as real data.

**Click to Read Paper**
Offshore Wind Farm Layout Optimization Using Adapted Genetic Algorithm: A different perspective

Mar 27, 2014

Feng Liu, Zhifang Wang

Mar 27, 2014

Feng Liu, Zhifang Wang

**Click to Read Paper**

A unified framework of epidemic spreading prediction by empirical mode decomposition based ensemble learning techniques

Jan 07, 2019

Yun Feng, Bing-Chuan Wang

Jan 07, 2019

Yun Feng, Bing-Chuan Wang

* Some issues need to be addressed in this manuscript

**Click to Read Paper**

Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hopping

Feb 18, 2019

Linhao Dong, Feng Wang, Bo Xu

Feb 18, 2019

Linhao Dong, Feng Wang, Bo Xu

* To appear at ICASSP 2019

**Click to Read Paper**

**Click to Read Paper**

Exploiting Problem Structure in Combinatorial Landscapes: A Case Study on Pure Mathematics Application

Dec 22, 2018

Xiao-Feng Xie, Zun-Jing Wang

Dec 22, 2018

Xiao-Feng Xie, Zun-Jing Wang

* International Joint Conference on Artificial Intelligence, New York, 2016, pp.2683-2689

* 7 pages, 2 figures, conference

**Click to Read Paper**

Cooperative Group Optimization with Ants (CGO-AS): Leverage Optimization with Mixed Individual and Social Learning

Aug 01, 2018

Xiao-Feng Xie, Zun-Jing Wang

Aug 01, 2018

Xiao-Feng Xie, Zun-Jing Wang

* Applied Soft Computing, 50: 223-234, 2017

**Click to Read Paper**

A Novel ECOC Algorithm with Centroid Distance Based Soft Coding Scheme

Jun 22, 2018

Kaijie Feng, Kunhong Liu, Beizhan Wang

Jun 22, 2018

Kaijie Feng, Kunhong Liu, Beizhan Wang

**Click to Read Paper**

Pruning Random Forests for Prediction on a Budget

Jun 16, 2016

Feng Nan, Joseph Wang, Venkatesh Saligrama

Jun 16, 2016

Feng Nan, Joseph Wang, Venkatesh Saligrama

**Click to Read Paper**

* 9 pages, 3 figures, and 4 tables. Accepted by CVPR2016 Workshops

**Click to Read Paper**

Survey on the attention based RNN model and its applications in computer vision

Jan 25, 2016

Feng Wang, David M. J. Tax

Jan 25, 2016

Feng Wang, David M. J. Tax

**Click to Read Paper**

Optimally Pruning Decision Tree Ensembles With Feature Cost

Jan 05, 2016

Feng Nan, Joseph Wang, Venkatesh Saligrama

Jan 05, 2016

Feng Nan, Joseph Wang, Venkatesh Saligrama

**Click to Read Paper**

**Click to Read Paper**

Max-Cost Discrete Function Evaluation Problem under a Budget

Jan 12, 2015

Feng Nan, Joseph Wang, Venkatesh Saligrama

Jan 12, 2015

Feng Nan, Joseph Wang, Venkatesh Saligrama

**Click to Read Paper**

**Click to Read Paper**

Constructing Hierarchical Image-tags Bimodal Representations for Word Tags Alternative Choice

Jul 04, 2013

Fangxiang Feng, Ruifan Li, Xiaojie Wang

Jul 04, 2013

Fangxiang Feng, Ruifan Li, Xiaojie Wang

* 6 pages, 1 figure, Presented at the Workshop on Representation Learning, ICML 2013

**Click to Read Paper**