no code implementations • 22 Apr 2024 • Yinlin Zhu, Xunkai Li, Zhengyu Wu, Di wu, Miao Hu, Rong-Hua Li
Subgraph federated learning (subgraph-FL) is a new distributed paradigm that facilitates the collaborative training of graph neural networks (GNNs) by multi-client subgraphs.
1 code implementation • 9 Feb 2024 • Xunkai Li, Jingyuan Ma, Zhengyu Wu, Daohan Su, Wentao Zhang, Rong-Hua Li, Guoren Wang
However, (i) Most scalable GNNs tend to treat all nodes in graphs with the same propagation rules, neglecting their topological uniqueness; (ii) Existing node-wise propagation optimization strategies are insufficient on web-scale graphs with intricate topology, where a full portrayal of nodes' local properties is required.
1 code implementation • 22 Jan 2024 • Xunkai Li, Yulin Zhao, Zhengyu Wu, Wentao Zhang, Rong-Hua Li, Guoren Wang
With the rapid advancement of AI applications, the growing needs for data privacy and model robustness have highlighted the importance of machine unlearning, especially in thriving graph-based scenarios.
1 code implementation • 22 Jan 2024 • Xunkai Li, Meihao Liao, Zhengyu Wu, Daohan Su, Wentao Zhang, Rong-Hua Li, Guoren Wang
Most existing graph neural networks (GNNs) are limited to undirected graphs, whose restricted scope of the captured relational information hinders their expressive capabilities and deployments in real-world scenarios.
1 code implementation • 22 Jan 2024 • Xunkai Li, Zhengyu Wu, Wentao Zhang, Yinlin Zhu, Rong-Hua Li, Guoren Wang
Existing FGL studies fall into two categories: (i) FGL Optimization, which improves multi-client training in existing machine learning models; (ii) FGL Model, which enhances performance with complex local models and multi-client interactions.
no code implementations • 22 Jan 2024 • Xunkai Li, Zhengyu Wu, Wentao Zhang, Henan Sun, Rong-Hua Li, Guoren Wang
Then, each client conducts personalized training based on the local subgraph and the federated knowledge extractor.
no code implementations • 7 Dec 2023 • Henan Sun, Xunkai Li, Zhengyu Wu, Daohan Su, Rong-Hua Li, Guoren Wang
Despite numerous attempts, most existing GNNs struggle to achieve optimal node representations due to the constraints of undirected graphs.
Ranked #28 on Node Classification on Cornell
no code implementations • 17 Oct 2023 • Zening Li, Rong-Hua Li, Meihao Liao, Fusheng Jin, Guoren Wang
We propose LDP-GE, a novel privacy-preserving graph embedding framework, to protect the privacy of node data.
no code implementations • 22 Nov 2022 • Longlong Lin, Rong-Hua Li, Tao Jia
Despite the significant success of conductance-based graph clustering, existing algorithms are either hard to obtain satisfactory clustering qualities, or have high time and space complexity to achieve provable clustering qualities.
1 code implementation • 2020 • Rong-Hua Li, Jeffrey Xu Yu, Lu Qin, Rui Mao, Tan Ji
In this paper, we first present a comprehensive analysis of the drawbacks of three widely-used random walk based graph sampling algorithms, called re-weighted random walk (RW) algorithm, Metropolis-Hastings random walk (MH) algorithm and maximum-degree random walk (MD) algorithm.