Search Results for author: Junbin Gao

Found 70 papers, 14 papers with code

Quasi-Framelets: Another Improvement to GraphNeural Networks

no code implementations11 Jan 2022 Mengxi Yang, Xuebin Zheng, Jie Yin, Junbin Gao

This paper aims to provide a novel design of a multiscale framelets convolution for spectral graph neural networks.

Graph Learning

Wasserstein Adversarially Regularized Graph Autoencoder

no code implementations9 Nov 2021 Huidong Liang, Junbin Gao

This paper introduces Wasserstein Adversarially Regularized Graph Autoencoder (WARGA), an implicit generative algorithm that directly regularizes the latent distribution of node embedding to a target distribution via the Wasserstein metric.

Link Prediction Node Clustering

Graph Denoising with Framelet Regularizer

1 code implementation5 Nov 2021 Bingxin Zhou, Ruikun Li, Xuebin Zheng, Yu Guang Wang, Junbin Gao

As graph data collected from the real world is merely noise-free, a practical representation of graphs should be robust to noise.

Denoising

Generalized Bures-Wasserstein Geometry for Positive Definite Matrices

1 code implementation20 Oct 2021 Andi Han, Bamdev Mishra, Pratik Jawanpuria, Junbin Gao

This paper proposes a generalized Bures-Wasserstein (BW) Riemannian geometry for the manifold of symmetric positive definite matrices.

Neural Ordinary Differential Equation Model for Evolutionary Subspace Clustering and Its Applications

no code implementations22 Jul 2021 Mingyuan Bai, S. T. Boris Choy, Junping Zhang, Junbin Gao

In this paper, we propose a neural ODE model for evolutionary subspace clustering to overcome this limitation and a new objective function with subspace self-expressiveness constraint is introduced.

Time Series Time Series Analysis

Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures

no code implementations14 Jun 2021 Renlong Jie, Junbin Gao

It is extended from the existing study on differentiable neural architecture search, and we made the backbone architecture transformable rather than fixed during the training process.

Language Modelling Neural Architecture Search +2

A Discussion On the Validity of Manifold Learning

no code implementations3 Jun 2021 Dai Shi, Andi Han, Yi Guo, Junbin Gao

In this work, we investigate the validity of learning results of some widely used DR and ManL methods through the chart mapping function of a manifold.

Dimensionality Reduction Speech Recognition

On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry

1 code implementation NeurIPS 2021 Andi Han, Bamdev Mishra, Pratik Jawanpuria, Junbin Gao

We build on this to show that the BW metric is a more suitable and robust choice for several Riemannian optimization problems over ill-conditioned SPD matrices.

Riemannian optimization

Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification

no code implementations28 Apr 2021 Jie Chen, Shouzhen Chen, Mingyuan Bai, Jian Pu, Junping Zhang, Junbin Gao

In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention.

General Classification Graph Learning +1

Grassmann Graph Embedding

no code implementations ICLR Workshop GTRL 2021 Bingxin Zhou, Xuebin Zheng, Yu Guang Wang, Ming Li, Junbin Gao

Geometric deep learning that employs the geometric and topological features of data has attracted increasing attention in deep neural networks.

Dimensionality Reduction Graph Embedding

How Framelets Enhance Graph Neural Networks

1 code implementation13 Feb 2021 Xuebin Zheng, Bingxin Zhou, Junbin Gao, Yu Guang Wang, Pietro Lio, Ming Li, Guido Montufar

The graph neural networks with the proposed framelet convolution and pooling achieve state-of-the-art performance in many node and graph prediction tasks.

Denoising

CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering

1 code implementation18 Jan 2021 Guangyu Huo, Yong Zhang, Junbin Gao, Boyue Wang, Yongli Hu, BaoCai Yin

In this paper, we propose a cross-attention based deep clustering framework, named Cross-Attention Fusion based Enhanced Graph Convolutional Network (CaEGCN), which contains four main modules: the cross-attention fusion module which innovatively concatenates the Content Auto-encoder module (CAE) relating to the individual data and Graph Convolutional Auto-encoder module (GAE) relating to the relationship between the data in a layer-by-layer manner, and the self-supervised model that highlights the discriminative information for clustering tasks.

Deep Clustering Graph Convolutional Network

Escape saddle points faster on manifolds via perturbed Riemannian stochastic recursive gradient

no code implementations23 Oct 2020 Andi Han, Junbin Gao

In this paper, we propose a variant of Riemannian stochastic recursive gradient method that can achieve second-order convergence guarantee and escape saddle points using simple perturbation.

Adaptive Hierarchical Hyper-gradient Descent

no code implementations17 Aug 2020 Renlong Jie, Junbin Gao, Andrey Vasnev, Minh-Ngoc Tran

In this study, we investigate learning rate adaption at different levels based on the hyper-gradient descent framework and propose a method that adaptively learns the optimizer parameters by combining multiple levels of learning rates with hierarchical structures.

Meta-Learning

Riemannian stochastic recursive momentum method for non-convex optimization

no code implementations11 Aug 2020 Andi Han, Junbin Gao

We propose a stochastic recursive momentum method for Riemannian non-convex optimization that achieves a near-optimal complexity of $\tilde{\mathcal{O}}(\epsilon^{-3})$ to find $\epsilon$-approximate solution with one sample.

Regularized Flexible Activation Function Combinations for Deep Neural Networks

no code implementations26 Jul 2020 Renlong Jie, Junbin Gao, Andrey Vasnev, Min-ngoc Tran

Based on this, a novel family of flexible activation functions that can replace sigmoid or tanh in LSTM cells are implemented, as well as a new family by combining ReLU and ELUs.

Image Compression Time Series +1

MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning

no code implementations22 Jul 2020 Xuebin Zheng, Bingxin Zhou, Ming Li, Yu Guang Wang, Junbin Gao

In this paper, we propose a framework for graph neural networks with multiresolution Haar-like wavelets, or MathNet, with interrelated convolution and pooling strategies.

Graph Classification

Variance reduction for Riemannian non-convex optimization with batch size adaptation

no code implementations3 Jul 2020 Andi Han, Junbin Gao

Variance reduction techniques are popular in accelerating gradient descent and stochastic gradient descent for optimization problems defined on both Euclidean space and Riemannian manifold.

Riemannian optimization

A Bayesian Long Short-Term Memory Model for Value at Risk and Expected Shortfall Joint Forecasting

no code implementations23 Jan 2020 Zhengkun Li, Minh-Ngoc Tran, Chao Wang, Richard Gerlach, Junbin Gao

Value-at-Risk (VaR) and Expected Shortfall (ES) are widely used in the financial sector to measure the market risk and manage the extreme market movement.

Bayesian Inference Time Series

On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods

no code implementations17 Jan 2020 Bingxin Zhou, Xuebin Zheng, Junbin Gao

Adam-type optimizers, as a class of adaptive moment estimation methods with the exponential moving average scheme, have been successfully used in many applications of deep learning.

Stochastic Optimization

Coupling Matrix Manifolds and Their Applications in Optimal Transport

no code implementations15 Nov 2019 Dai Shi, Junbin Gao, Xia Hong, S. T. Boris Choy, Zhiyong Wang

These geometrical features of CMM have paved the way for developing numerical Riemannian optimization algorithms such as Riemannian gradient descent and Riemannian trust-region algorithms, forming a uniform optimization method for all types of OT problems.

Riemannian optimization

LSTM-Assisted Evolutionary Self-Expressive Subspace Clustering

no code implementations19 Oct 2019 Di Xu, Tianhang Long, Junbin Gao

Massive volumes of high-dimensional data that evolves over time is continuously collected by contemporary information processing systems, which brings up the problem of organizing this data into clusters, i. e. achieve the purpose of dimensional deduction, and meanwhile learning its temporal evolution patterns.

COMBINED FLEXIBLE ACTIVATION FUNCTIONS FOR DEEP NEURAL NETWORKS

no code implementations25 Sep 2019 Renlong Jie, Junbin Gao, Andrey Vasnev, Minh-Ngoc Tran

Based on this, we develop two novel flexible activation functions that can be implemented in LSTM cells and auto-encoder layers.

Image Classification Time Series +1

Tensor-Train Parameterization for Ultra Dimensionality Reduction

no code implementations14 Aug 2019 Mingyuan Bai, S. T. Boris Choy, Xin Song, Junbin Gao

Thus, we propose a tensor-train parameterization for ultra dimensionality reduction (TTPUDR) in which the traditional LPP mapping is tensorized in terms of tensor-trains and the LPP objective is replaced with the Frobenius norm to increase the robustness of the model.

Dimensionality Reduction

Shared Generative Latent Representation Learning for Multi-view Clustering

1 code implementation23 Jul 2019 Ming Yin, Weitian Huang, Junbin Gao

Clustering multi-view data has been a fundamental research topic in the computer vision community.

Representation Learning

DataLearner: A Data Mining and Knowledge Discovery Tool for Android Smartphones and Tablets

1 code implementation10 Jun 2019 Darren Yates, Md Zahidul Islam, Junbin Gao

Smartphones have become the ultimate 'personal' computer, yet despite this, general-purpose data-mining and knowledge discovery tools for mobile devices are surprisingly rare.

General Classification

Manifold Optimization Assisted Gaussian Variational Approximation

no code implementations11 Feb 2019 Bingxin Zhou, Junbin Gao, Minh-Ngoc Tran, Richard Gerlach

Gaussian variational approximation is a popular methodology to approximate posterior distributions in Bayesian inference especially in high dimensional and large data settings.

Bayesian Inference

Sparse Least Squares Low Rank Kernel Machines

no code implementations29 Jan 2019 Di Xu, Manjing Fang, Xia Hong, Junbin Gao

A general framework of least squares support vector machine with low rank kernels, referred to as LR-LSSVM, is introduced in this paper.

A Review for Weighted MinHash Algorithms

1 code implementation12 Nov 2018 Wei Wu, Bin Li, Ling Chen, Junbin Gao, Chengqi Zhang

In this review, we mainly categorize the Weighted MinHash algorithms into quantization-based approaches, "active index"-based ones and others, and show the evolution and inherent connection of the weighted MinHash algorithms, from the integer weighted MinHash algorithms to real-valued weighted MinHash ones (particularly the Consistent Weighted Sampling scheme).

Data Structures and Algorithms

Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification

no code implementations3 Aug 2018 Lin Wu, Yang Wang, Junbin Gao, Xue Li

Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security.

Metric Learning Video-Based Person Re-Identification

Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification

1 code implementation30 Apr 2018 Lin Wu, Yang Wang, Junbin Gao, DaCheng Tao

Recent effective methods are developed in a pair-wise similarity learning system to detect a fixed set of features from distinct regions which are mapped to their vector embeddings for the distance measuring.

Foveation Person Re-Identification +1

Tensorial Recurrent Neural Networks for Longitudinal Data Analysis

no code implementations1 Aug 2017 Mingyuan Bai, Boyan Zhang, Junbin Gao

In this paper, we propose a new variant of tensorial neural networks which directly take tensorial time series data as inputs.

Time Series

What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification

no code implementations21 Jul 2017 Lin Wu, Yang Wang, Xue Li, Junbin Gao

To address \emph{what} to match, our deep network emphasizes common local patterns by learning joint representations in a multiplicative way.

Person Re-Identification

Vectorial Dimension Reduction for Tensors Based on Bayesian Inference

no code implementations3 Jul 2017 Fujiao Ju, Yanfeng Sun, Junbin Gao, Yongli Hu, Bao-Cai Yin

Under this expression, the projection base of the model is based on the tensor CandeComp/PARAFAC (CP) decomposition and the number of free parameters in the model only grows linearly with the number of modes rather than exponentially.

Bayesian Inference Dimensionality Reduction

Grassmannian Manifold Optimization Assisted Sparse Spectral Clustering

no code implementations CVPR 2017 Qiong Wang, Junbin Gao, Hong Li

Spectral Clustering is one of pioneered clustering methods in machine learning and pattern recognition field.

Dimensionality Reduction

Low-Rank-Sparse Subspace Representation for Robust Regression

no code implementations CVPR 2017 Yongqiang Zhang, Daming Shi, Junbin Gao, Dansong Cheng

Learning robust regression model from high-dimensional corrupted data is an essential and difficult problem in many practical applications.

Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification

no code implementations10 Jun 2017 Lin Wu, Yang Wang, Junbin Gao, Xue Li

To this end, a novel objective function is proposed to jointly optimize similarity metric learning, local positive mining and robust deep embedding.

Metric Learning Person Re-Identification

Assessing the Performance of Deep Learning Algorithms for Newsvendor Problem

no code implementations9 Jun 2017 Yanfei Zhang, Junbin Gao

In the traditional approach to solving this problem, it relies on the probability distribution of the demand.

Localized LRR on Grassmann Manifolds: An Extrinsic View

no code implementations17 May 2017 Boyue Wang, Yongli Hu, Junbin Gao, Yanfeng Sun, Bao-Cai Yin

Subspace data representation has recently become a common practice in many computer vision tasks.

Locality Preserving Projections for Grassmann manifold

no code implementations27 Apr 2017 Boyue Wang, Yongli Hu, Junbin Gao, Yanfeng Sun, Haoran Chen, Bao-Cai Yin

Learning on Grassmann manifold has become popular in many computer vision tasks, with the strong capability to extract discriminative information for imagesets and videos.

Dimensionality Reduction

Tractable Clustering of Data on the Curve Manifold

1 code implementation13 Apr 2017 Stephen Tierney, Junbin Gao, Yi Guo, Zheng Zhang

However the data may actually be functional i. e.\ each data point is a function of some variable such as time and the function is discretely sampled.

Efficient Sparse Subspace Clustering by Nearest Neighbour Filtering

1 code implementation13 Apr 2017 Stephen Tierney, Yi Guo, Junbin Gao

Sparse Subspace Clustering (SSC) has been used extensively for subspace identification tasks due to its theoretical guarantees and relative ease of implementation.

General Classification

Collaborative Low-Rank Subspace Clustering

1 code implementation13 Apr 2017 Stephen Tierney, Yi Guo, Junbin Gao

In this paper we present Collaborative Low-Rank Subspace Clustering.

Partial Least Squares Regression on Riemannian Manifolds and Its Application in Classifications

no code implementations21 Sep 2016 Haoran Chen, Yanfeng Sun, Junbin Gao, Yongli Hu, Bao-Cai Yin

Partial least squares regression (PLSR) has been a popular technique to explore the linear relationship between two datasets.

General Classification

Matrix Variate RBM Model with Gaussian Distributions

no code implementations21 Sep 2016 Simeng Liu, Yanfeng Sun, Yongli Hu, Junbin Gao, Bao-Cai Yin

Restricted Boltzmann Machine (RBM) is a particular type of random neural network models modeling vector data based on the assumption of Bernoulli distribution.

General Classification Image Classification

Low-rank Multi-view Clustering in Third-Order Tensor Space

no code implementations30 Aug 2016 Ming Yin, Junbin Gao, Shengli Xie, Yi Guo

Multi-view subspace clustering is based on the fact that the multi-view data are generated from a latent subspace.

Multi-view Subspace Clustering

Laplacian LRR on Product Grassmann Manifolds for Human Activity Clustering in Multi-Camera Video Surveillance

no code implementations13 Jun 2016 Boyue Wang, Yongli Hu, Junbin Gao, Yanfeng Sun, Bao-Cai Yin

In multi-camera video surveillance, it is challenging to represent videos from different cameras properly and fuse them efficiently for specific applications such as human activity recognition and clustering.

Activity Recognition

Neighborhood Preserved Sparse Representation for Robust Classification on Symmetric Positive Definite Matrices

no code implementations27 Jan 2016 Ming Yin, Shengli Xie, Yi Guo, Junbin Gao, Yun Zhang

Due to its promising classification performance, sparse representation based classification(SRC) algorithm has attracted great attention in the past few years.

General Classification Robust classification +1

Partial Sum Minimization of Singular Values Representation on Grassmann Manifolds

no code implementations21 Jan 2016 Boyue Wang, Yongli Hu, Junbin Gao, Yanfeng Sun, Bao-Cai Yin

As a significant subspace clustering method, low rank representation (LRR) has attracted great attention in recent years.

Kernelized LRR on Grassmann Manifolds for Subspace Clustering

no code implementations9 Jan 2016 Boyue Wang, Yongli Hu, Junbin Gao, Yanfeng Sun, Bao-Cai Yin

The novelty of this paper is to generalize LRR on Euclidean space onto an LRR model on Grassmann manifold in a uniform kernelized LRR framework.

Mixture of Bilateral-Projection Two-dimensional Probabilistic Principal Component Analysis

no code implementations CVPR 2016 Fujiao Ju, Yanfeng Sun, Junbin Gao, Simeng Liu, Yongli Hu

This paper proposes a mixture of bilateral-projection probabilistic principal component analysis model (mixB2DPPCA) on 2D data.

Bayesian Inference

Block-Diagonal Sparse Representation by Learning a Linear Combination Dictionary for Recognition

no code implementations7 Jan 2016 Xinglin Piao, Yongli Hu, Yanfeng Sun, Junbin Gao, Bao-Cai Yin

In a sparse representation based recognition scheme, it is critical to learn a desired dictionary, aiming both good representational power and discriminative performance.

Dictionary Learning

Low-Rank Representation over the Manifold of Curves

no code implementations5 Jan 2016 Stephen Tierney, Junbin Gao, Yi Guo, Zhengwu Zhang

However the data may actually be functional i. e.\ each data point is a function of some variable such as time and the function is discretely sampled.

Matrix Variate RBM and Its Applications

no code implementations5 Jan 2016 Guanglei Qi, Yanfeng Sun, Junbin Gao, Yongli Hu, Jinghua Li

In this paper, a Matrix-Variate Restricted Boltzmann Machine (MVRBM) model is proposed by generalizing the classic RBM to explicitly model matrix data.

Handwritten Digit Recognition Image Super-Resolution

Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds

no code implementations CVPR 2016 Ming Yin, Yi Guo, Junbin Gao, Zhaoshui He, Shengli Xie

Sparse subspace clustering (SSC), as one of the most successful subspace clustering methods, has achieved notable clustering accuracy in computer vision tasks.

Tensor Sparse and Low-Rank based Submodule Clustering Method for Multi-way Data

no code implementations2 Jan 2016 Xinglin Piao, Yongli Hu, Junbin Gao, Yanfeng Sun, Zhouchen Lin, Bao-Cai Yin

A new submodule clustering method via sparse and low-rank representation for multi-way data is proposed in this paper.

Fast Optimization Algorithm on Riemannian Manifolds and Its Application in Low-Rank Representation

no code implementations7 Dec 2015 Haoran Chen, Yanfeng Sun, Junbin Gao, Yongli Hu

The paper addresses the problem of optimizing a class of composite functions on Riemannian manifolds and a new first order optimization algorithm (FOA) with a fast convergence rate is proposed.

Matrix Completion

l1-norm Penalized Orthogonal Forward Regression

no code implementations4 Sep 2015 Xia Hong, Sheng Chen, Yi Guo, Junbin Gao

A l1-norm penalized orthogonal forward regression (l1-POFR) algorithm is proposed based on the concept of leaveone- out mean square error (LOOMSE).

Low Rank Representation on Riemannian Manifold of Square Root Densities

no code implementations18 Aug 2015 Yifan Fu, Junbin Gao, Xia Hong, David Tien

In this paper, we present a novel low rank representation (LRR) algorithm for data lying on the manifold of square root densities.

General Classification

Segmentation of Subspaces in Sequential Data

1 code implementation16 Apr 2015 Stephen Tierney, Yi Guo, Junbin Gao

We propose Ordered Subspace Clustering (OSC) to segment data drawn from a sequentially ordered union of subspaces.

Kernelized Low Rank Representation on Grassmann Manifolds

no code implementations8 Apr 2015 Boyue Wang, Yongli Hu, Junbin Gao, Yanfeng Sun, Bao-Cai Yin

One of its successful applications is subspace clustering which means data are clustered according to the subspaces they belong to.

Heterogeneous Tensor Decomposition for Clustering via Manifold Optimization

no code implementations7 Apr 2015 Yanfeng Sun, Junbin Gao, Xia Hong, Bamdev Mishra, Bao-Cai Yin

In contrast to existing techniques, we propose a new clustering algorithm that alternates between different modes of the proposed heterogeneous tensor model.

Tensor Decomposition

Scalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient

no code implementations10 Mar 2015 Mingkui Tan, Shijie Xiao, Junbin Gao, Dong Xu, Anton Van Den Hengel, Qinfeng Shi

Nuclear-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR).

Matrix Completion

Relations among Some Low Rank Subspace Recovery Models

no code implementations6 Dec 2014 Hongyang Zhang, Zhouchen Lin, Chao Zhang, Junbin Gao

More specifically, we discover that once a solution to one of the models is obtained, we can obtain the solutions to other models in closed-form formulations.

Subspace Clustering for Sequential Data

no code implementations CVPR 2014 Stephen Tierney, Junbin Gao, Yi Guo

We propose Ordered Subspace Clustering (OSC) to segment data drawn from a sequentially ordered union of subspaces.

Cannot find the paper you are looking for? You can Submit a new open access paper.