Search Results for author: Zhao Kang

Found 48 papers, 24 papers with code

Intensity-free Convolutional Temporal Point Process: Incorporating Local and Global Event Contexts

no code implementations24 Jun 2023 Wang-Tao Zhou, Zhao Kang, Ling Tian, Yi Su

Popular convolutional neural networks, which are designated for local context capturing, have never been applied to TPP modelling due to their incapability of modelling in continuous time.

TieFake: Title-Text Similarity and Emotion-Aware Fake News Detection

1 code implementation19 Apr 2023 Quanjiang Guo, Zhao Kang, Ling Tian, Zhouguo Chen

We also propose a scale-dot product attention mechanism to capture the similarity between title features and textual features.

Fake News Detection text similarity

Spacecraft Anomaly Detection with Attention Temporal Convolution Network

1 code implementation13 Mar 2023 Liang Liu, Ling Tian, Zhao Kang, Tianqi Wan

The time series telemetry data generated by on-orbit spacecraft \textcolor{blue}{contains} important information about the status of spacecraft.

Anomaly Detection Graph Attention +2

Document-level Relation Extraction with Cross-sentence Reasoning Graph

1 code implementation7 Mar 2023 Hongfei Liu, Zhao Kang, Lizong Zhang, Ling Tian, Fujun Hua

Specifically, a simplified document-level graph is constructed to model the semantic information of all mentions and sentences in a document, and an entity-level graph is designed to explore relations of long-distance cross-sentence entity pairs.

Document-level Relation Extraction

High-order Multi-view Clustering for Generic Data

1 code implementation22 Sep 2022 Erlin Pan, Zhao Kang

Firstly, graph filtering is applied to encode structure information, which unifies the processing of attributed graph data and non-graph data in a single framework.

Clustering Vocal Bursts Intensity Prediction

Structure-Preserving Graph Representation Learning

1 code implementation2 Sep 2022 Ruiyi Fang, Liangjian Wen, Zhao Kang, Jianzhuang Liu

To this end, we propose a novel Structure-Preserving Graph Representation Learning (SPGRL) method, to fully capture the structure information of graphs.

Graph Representation Learning Node Classification

Eliminating Gradient Conflict in Reference-based Line-Art Colorization

1 code implementation13 Jul 2022 Zekun Li, Zhengyang Geng, Zhao Kang, Wenyu Chen, Yibo Yang

To understand the instability in training, we detect the gradient flow of attention and observe gradient conflict among attention branches.

Line Art Colorization SSIM

Scalable Multi-view Clustering with Graph Filtering

1 code implementation18 May 2022 Liang Liu, Peng Chen, Guangchun Luo, Zhao Kang, Yonggang Luo, Sanchu Han

With the explosive growth of multi-source data, multi-view clustering has attracted great attention in recent years.


Log-based Sparse Nonnegative Matrix Factorization for Data Representation

no code implementations22 Apr 2022 Chong Peng, Yiqun Zhang, Yongyong Chen, Zhao Kang, Chenglizhao Chen, Qiang Cheng

Nonnegative matrix factorization (NMF) has been widely studied in recent years due to its effectiveness in representing nonnegative data with parts-based representations.

Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization

no code implementations8 Jan 2022 Chong Peng, Yang Liu, Yongyong Chen, Xinxin Wu, Andrew Cheng, Zhao Kang, Chenglizhao Chen, Qiang Cheng

In this paper, we propose a novel nonconvex approach to robust principal component analysis for HSI denoising, which focuses on simultaneously developing more accurate approximations to both rank and column-wise sparsity for the low-rank and sparse components, respectively.

Hyperspectral Image Denoising Image Denoising

Multilayer Graph Contrastive Clustering Network

no code implementations28 Dec 2021 Liang Liu, Zhao Kang, Ling Tian, Wenbo Xu, Xixu He

To this end, we propose a generic and effective autoencoder framework for multilayer graph clustering named Multilayer Graph Contrastive Clustering Network (MGCCN).

Clustering Graph Clustering

Multi-view Contrastive Graph Clustering

1 code implementation NeurIPS 2021 Erlin Pan, Zhao Kang

With the explosive growth of information technology, multi-view graph data have become increasingly prevalent and valuable.

Clustering Contrastive Learning +1

Self-supervised Consensus Representation Learning for Attributed Graph

1 code implementation10 Aug 2021 Changshu Liu, Liangjian Wen, Zhao Kang, Guangchun Luo, Ling Tian

Self-supervised loss is designed to maximize the agreement of the embeddings of the same node in the topology graph and the feature graph.

Graph Representation Learning Node Classification +1

Self-paced Principal Component Analysis

no code implementations25 Jun 2021 Zhao Kang, Hongfei Liu, Jiangxin Li, Xiaofeng Zhu, Ling Tian

Notably, the complexity of each sample is calculated at the beginning of each iteration in order to integrate samples from simple to more complex into training.

Dimensionality Reduction

Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering

1 code implementation18 Jun 2021 Zhengrui Ma, Zhao Kang, Guangchun Luo, Ling Tian

The success of subspace clustering depends on the assumption that the data can be separated into different subspaces.

Clustering Graph Similarity

Smoothed Multi-View Subspace Clustering

1 code implementation18 Jun 2021 Peng Chen, Liang Liu, Zhengrui Ma, Zhao Kang

In recent years, multi-view subspace clustering has achieved impressive performance due to the exploitation of complementary imformation across multiple views.

Clustering Multi-view Subspace Clustering

Pseudo-supervised Deep Subspace Clustering

1 code implementation8 Apr 2021 Juncheng Lv, Zhao Kang, Xiao Lu, Zenglin Xu

To tackle these problems, we use pairwise similarity to weigh the reconstruction loss to capture local structure information, while a similarity is learned by the self-expression layer.


Structured Graph Learning for Scalable Subspace Clustering: From Single-view to Multi-view

no code implementations16 Feb 2021 Zhao Kang, Zhiping Lin, Xiaofeng Zhu, Wenbo Xu

Extensive experiments demonstrate the efficiency and effectiveness of our approach with respect to many state-of-the-art clustering methods.

Clustering Graph Learning

Kernel Two-Dimensional Ridge Regression for Subspace Clustering

no code implementations3 Nov 2020 Chong Peng, Qian Zhang, Zhao Kang, Chenglizhao Chen, Qiang Cheng

It directly uses 2D data as inputs such that the learning of representations benefits from inherent structures and relationships of the data.

Clustering regression +1

Structured Graph Learning for Clustering and Semi-supervised Classification

no code implementations31 Aug 2020 Zhao Kang, Chong Peng, Qiang Cheng, Xinwang Liu, Xi Peng, Zenglin Xu, Ling Tian

Furthermore, most existing graph-based methods conduct clustering and semi-supervised classification on the graph learned from the original data matrix, which doesn't have explicit cluster structure, thus they might not achieve the optimal performance.

Classification Clustering +2

On Deep Unsupervised Active Learning

no code implementations28 Jul 2020 Changsheng Li, Handong Ma, Zhao Kang, Ye Yuan, Xiao-Yu Zhang, Guoren Wang

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating.

Active Learning

Relation-Guided Representation Learning

no code implementations11 Jul 2020 Zhao Kang, Xiao Lu, Jian Liang, Kun Bai, Zenglin Xu

In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning.

Clustering Representation Learning

Two-Dimensional Semi-Nonnegative Matrix Factorization for Clustering

no code implementations19 May 2020 Chong Peng, Zhilu Zhang, Zhao Kang, Chenglizhao Chen, Qiang Cheng

In particular, projection matrices are sought under the guidance of building new data representations, such that the spatial information is retained and projections are enhanced by the goal of clustering, which helps construct optimal projection directions.

Clustering Vocal Bursts Valence Prediction

Multi-view Subspace Clustering via Partition Fusion

no code implementations3 Dec 2019 Juncheng Lv, Zhao Kang, Boyu Wang, Luping Ji, Zenglin Xu

Multi-view clustering is an important approach to analyze multi-view data in an unsupervised way.

Clustering Graph Learning +1

Structure Learning with Similarity Preserving

no code implementations3 Dec 2019 Zhao Kang, Xiao Lu, Yiwei Lu, Chong Peng, Zenglin Xu

Leveraging on the underlying low-dimensional structure of data, low-rank and sparse modeling approaches have achieved great success in a wide range of applications.


Large-scale Multi-view Subspace Clustering in Linear Time

2 code implementations21 Nov 2019 Zhao Kang, Wangtao Zhou, Zhitong Zhao, Junming Shao, Meng Han, Zenglin Xu

A plethora of multi-view subspace clustering (MVSC) methods have been proposed over the past few years.

Clustering Multi-view Subspace Clustering

Multi-graph Fusion for Multi-view Spectral Clustering

1 code implementation16 Sep 2019 Zhao Kang, Guoxin Shi, Shudong Huang, Wenyu Chen, Xiaorong Pu, Joey Tianyi Zhou, Zenglin Xu

Most existing methods don't pay attention to the quality of the graphs and perform graph learning and spectral clustering separately.

Clustering Graph Learning

Multiple Partitions Aligned Clustering

1 code implementation13 Sep 2019 Zhao Kang, Zipeng Guo, Shudong Huang, Siying Wang, Wenyu Chen, Yuanzhang Su, Zenglin Xu

Most existing multi-view clustering methods explore the heterogeneous information in the space where the data points lie.


Latent Multi-view Semi-Supervised Classification

1 code implementation9 Sep 2019 Xiaofan Bo, Zhao Kang, Zhitong Zhao, Yuanzhang Su, Wenyu Chen

To explore underlying complementary information from multiple views, in this paper, we propose a novel Latent Multi-view Semi-Supervised Classification (LMSSC) method.

Classification General Classification +3

Nonnegative Matrix Factorization with Local Similarity Learning

no code implementations9 Jul 2019 Chong Peng, Zhao Kang, Chenglizhao Chen, Qiang Cheng

Existing nonnegative matrix factorization methods focus on learning global structure of the data to construct basis and coefficient matrices, which ignores the local structure that commonly exists among data.


Low-rank Kernel Learning for Graph-based Clustering

no code implementations14 Mar 2019 Zhao Kang, Liangjian Wen, Wenyu Chen, Zenglin Xu

By formulating graph construction and kernel learning in a unified framework, the graph and consensus kernel can be iteratively enhanced by each other.

Clustering graph construction +1

Robust Graph Learning from Noisy Data

1 code implementation17 Dec 2018 Zhao Kang, Haiqi Pan, Steven C. H. Hoi, Zenglin Xu

The proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the graph smoothness assumption, 2) improved graph construction by exploiting clean data recovered by robust PCA.

Clustering General Classification +7

Self-weighted Multiple Kernel Learning for Graph-based Clustering and Semi-supervised Classification

no code implementations20 Jun 2018 Zhao Kang, Xiao Lu, Jin-Feng Yi, Zenglin Xu

There are two possible reasons for the failure: (i) most existing MKL methods assume that the optimal kernel is a linear combination of base kernels, which may not hold true; and (ii) some kernel weights are inappropriately assigned due to noises and carelessly designed algorithms.

Clustering General Classification

Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN

no code implementations16 Nov 2017 Dan Ma, Bin Liu, Zhao Kang, Jiayu Zhou, Jianke Zhu, Zenglin Xu

Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications.

Image Generation

Unified Spectral Clustering with Optimal Graph

1 code implementation12 Nov 2017 Zhao Kang, Chong Peng, Qiang Cheng, Zenglin Xu

Second, the discrete solution may deviate from the spectral solution since k-means method is well-known as sensitive to the initialization of cluster centers.

Clustering graph construction

Twin Learning for Similarity and Clustering: A Unified Kernel Approach

no code implementations1 May 2017 Zhao Kang, Chong Peng, Qiang Cheng

Thus the learned similarity matrix is often not suitable, let alone optimal, for the subsequent clustering.


Top-N Recommendation on Graphs

1 code implementation27 Sep 2016 Zhao Kang, Chong Peng, Ming Yang, Qiang Cheng

To alleviate this problem, this paper proposes a simple recommendation algorithm that fully exploits the similarity information among users and items and intrinsic structural information of the user-item matrix.

Collaborative Filtering Recommendation Systems

A Fast Factorization-based Approach to Robust PCA

no code implementations27 Sep 2016 Chong Peng, Zhao Kang, Qiang Chen

Our method can be used as a light-weight, scalable tool for RPCA in the absence of the precise value of the true rank.

Top-N Recommendation with Novel Rank Approximation

1 code implementation25 Feb 2016 Zhao Kang, Qiang Cheng

Some empirical results demonstrate that it can provide a better approximation to original problems than convex relaxation.

Recommendation Systems

Top-N Recommender System via Matrix Completion

no code implementations19 Jan 2016 Zhao Kang, Chong Peng, Qiang Cheng

Top-N recommender systems have been investigated widely both in industry and academia.

Matrix Completion Recommendation Systems

Robust PCA via Nonconvex Rank Approximation

1 code implementation17 Nov 2015 Zhao Kang, Chong Peng, Qiang Cheng

This approximation to the matrix rank is tighter than the nuclear norm.

Robust Subspace Clustering via Tighter Rank Approximation

1 code implementation30 Oct 2015 Zhao Kang, Chong Peng, Qiang Cheng

For this nonconvex minimization problem, we develop an effective optimization procedure based on a type of augmented Lagrange multipliers (ALM) method.

Clustering Face Clustering +1

Robust Subspace Clustering via Smoothed Rank Approximation

1 code implementation18 Aug 2015 Zhao Kang, Chong Peng, Qiang Cheng

However, for many real-world applications, nuclear norm approximation to the rank function can only produce a result far from the optimum.

Clustering Face Clustering +1

LogDet Rank Minimization with Application to Subspace Clustering

no code implementations3 Jul 2015 Zhao Kang, Chong Peng, Jie Cheng, Qiang Chen

Most of the recent studies use the nuclear norm as a convex surrogate of the rank operator.

Clustering Face Clustering +1

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