Search Results for author: Hongyuan Zhang

Found 10 papers, 2 papers with code

Discretize Relaxed Solution of Spectral Clustering via a Non-Heuristic Algorithm

1 code implementation19 Oct 2023 Hongyuan Zhang, Xuelong Li

Unfortunately, the goal of the existing methods is not to find a discrete solution that minimizes the original objective.

Clustering

Variational Positive-incentive Noise: How Noise Benefits Models

no code implementations13 Jun 2023 Hongyuan Zhang, Sida Huang, Xuelong Li

From the experiments, it is shown that the proposed VPN generator can improve the base models.

Variational Inference

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One

no code implementations20 Apr 2023 Hongyuan Zhang, Yanan Zhu, Xuelong Li

It extremely limits the application of stochastic optimization algorithms so that the training of GNN is usually time-consuming.

Stochastic Optimization

Deep Manifold Learning with Graph Mining

no code implementations18 Jul 2022 Xuelong Li, Ziheng Jiao, Hongyuan Zhang, Rui Zhang

Admittedly, Graph Convolution Network (GCN) has achieved excellent results on graph datasets such as social networks, citation networks, etc.

Graph Mining

Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning

no code implementations4 Mar 2022 Xuelong Li, Hongyuan Zhang, Rui Zhang

We theoretically validate that it is equivalent to the existing matrix completion models.

Matrix Completion

AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution

no code implementations12 Nov 2021 Hongyuan Zhang, Jiankun Shi, Rui Zhang, Xuelong Li

The core problems mainly come from two aspects: (1) the graph is unavailable in the most clustering scenes so that how to construct high-quality graphs on the non-graph data is usually the most important part; (2) given n samples, the graph-based clustering methods usually consume at least $\mathcal O(n^2)$ time to build graphs and the graph convolution requires nearly $\mathcal O(n^2)$ for a dense graph and $\mathcal O(|\mathcal{E}|)$ for a sparse one with $|\mathcal{E}|$ edges.

Clustering

Non-Gradient Manifold Neural Network

no code implementations15 Jun 2021 Rui Zhang, Ziheng Jiao, Hongyuan Zhang, Xuelong Li

Moreover, by unifying the flexible Stiefel manifold and adaptive support vector machine, we devise the novel decision layer which efficiently fits the manifold structure of the data and label information.

Enhanced Principal Component Analysis under A Collaborative-Robust Framework

no code implementations22 Mar 2021 Rui Zhang, Hongyuan Zhang, Xuelong Li

Principal component analysis (PCA) frequently suffers from the disturbance of outliers and thus a spectrum of robust extensions and variations of PCA have been developed.

Clustering

Adaptive Graph Auto-Encoder for General Data Clustering

1 code implementation20 Feb 2020 Xuelong. Li, Hongyuan Zhang, Rui Zhang

Therefore, how to extend graph convolution networks into general clustering tasks is an attractive problem.

Clustering Graph Embedding +1

Embedding Graph Auto-Encoder for Graph Clustering

no code implementations20 Feb 2020 Hongyuan Zhang, Rui Zhang, Xuelong Li

Driven by theoretical analysis about relaxed k-means, we design a specific GAE-based model for graph clustering to be consistent with the theory, namely Embedding Graph Auto-Encoder (EGAE).

Clustering Graph Clustering

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