no code implementations • 23 Apr 2024 • Ziheng Jiao, Hongyuan Zhang, Xuelong Li
Notably, due to extracting the intra-sample representation of a single instance and the topological relationship among the datasets simultaneously, the performance of distilled ``boosted'' two-layer GNN on Mini-ImageNet is much higher than CNN containing dozens of layers such as ResNet152.
1 code implementation • 19 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.
no code implementations • 13 Jun 2023 • Hongyuan Zhang, Sida Huang, Xuelong Li
From the experiments, it is shown that the proposed VPN generator can improve the base models.
1 code implementation • 20 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.
no code implementations • 18 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.
no code implementations • 4 Mar 2022 • Xuelong Li, Hongyuan Zhang, Rui Zhang
We theoretically validate that it is equivalent to the existing matrix completion models.
no code implementations • 12 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.
no code implementations • 15 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.
no code implementations • 22 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.
no code implementations • 20 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).
1 code implementation • 20 Feb 2020 • Xuelong. Li, Hongyuan Zhang, Rui Zhang
Therefore, how to extend graph convolution networks into general clustering tasks is an attractive problem.