English
Related papers

Related papers: FedGraph: A Research Library and Benchmark for Fed…

200 papers

Graphs are crucial for modeling relational and biological data. As datasets grow larger in real-world scenarios, the risk of exposing sensitive information increases, making privacy-preserving training methods like federated learning (FL)…

Machine Learning · Computer Science 2025-01-24 Emir Ceyani , Han Xie , Baturalp Buyukates , Carl Yang , Salman Avestimehr

Deep learning has achieved great success in many applications. However, its deployment in practice has been hurdled by two issues: the privacy of data that has to be aggregated centrally for model training and high communication overhead…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-02-04 Tien-Dung Cao , Tram Truong-Huu , Hien Tran , Khanh Tran

Graph federated learning enables the collaborative extraction of high-order information from distributed subgraphs while preserving the privacy of raw data. However, graph data often exhibits overlap among different clients. Previous…

Machine Learning · Computer Science 2025-12-30 Zihao Zhou , Shusen Yang , Fangyuan Zhao , Xuebin Ren

Financial crime detection using graph learning improves financial safety and efficiency. However, criminals may commit financial crimes across different institutions to avoid detection, which increases the difficulty of detection for…

Cryptography and Security · Computer Science 2023-10-13 Zhirui Pan , Guangzhong Wang , Zhaoning Li , Lifeng Chen , Yang Bian , Zhongyuan Lai

Federated Learning is a machine learning paradigm where we aim to train machine learning models in a distributed fashion. Many clients/edge devices collaborate with each other to train a single model on the central. Clients do not share…

Machine Learning · Computer Science 2022-11-28 Mann Patel

Federated Learning (FL) has shown great potential as a privacy-preserving solution to learning from decentralized data that are only accessible to end devices (i.e., clients). In many scenarios, however, a large proportion of the clients…

Machine Learning · Computer Science 2022-01-31 Wentai Wu , Ligang He , Weiwei Lin , Carsten Maple

As special information carriers containing both structure and feature information, graphs are widely used in graph mining, e.g., Graph Neural Networks (GNNs). However, in some practical scenarios, graph data are stored separately in…

Machine Learning · Computer Science 2022-09-12 Taolin Zhang , Chuan Chen , Yaomin Chang , Lin Shu , Zibin Zheng

Federated Graph Learning (FGL) is a distributed learning paradigm that enables collaborative training over large-scale subgraphs located on multiple local systems. However, most existing FGL approaches rely on synchronous communication,…

Machine Learning · Computer Science 2025-08-06 Zhongzheng Yuan , Lianshuai Guo , Xunkai Li , Yinlin Zhu , Wenyu Wang , Meixia Qu

Federated Learning (FL) enables geographically distributed clients to collaboratively train machine learning models by sharing only their local models, ensuring data privacy. However, FL is vulnerable to untargeted attacks that aim to…

Machine Learning · Computer Science 2025-05-21 Di Wu , Qian Li , Heng Yang , Yong Han

Recently, Federated Graph Learning (FGL) has attracted significant attention as a distributed framework based on graph neural networks, primarily due to its capability to break data silos. Existing FGL studies employ community split on the…

Machine Learning · Computer Science 2024-01-23 Xunkai Li , Zhengyu Wu , Wentao Zhang , Henan Sun , Rong-Hua Li , Guoren Wang

Graph Neural Networks (GNNs) are the first choice methods for graph machine learning problems thanks to their ability to learn state-of-the-art level representations from graph-structured data. However, centralizing a massive amount of…

Machine Learning · Computer Science 2021-06-08 Chaoyang He , Emir Ceyani , Keshav Balasubramanian , Murali Annavaram , Salman Avestimehr

Federated Graph Learning (FGL) has emerged as a promising paradigm for breaking data silos among distributed private graphs. In practical scenarios involving heterogeneous distributed graph data, personalized Federated Graph Learning (pFGL)…

Machine Learning · Computer Science 2025-08-07 Guochen Yan , Xunkai Li , Luyuan Xie , Qingni Shen , Yuejian Fang , Zhonghai Wu

Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions. As graphs are getting bigger and bigger nowadays, it is common to see their subgraphs…

Machine Learning · Computer Science 2021-11-09 Ke Zhang , Carl Yang , Xiaoxiao Li , Lichao Sun , Siu Ming Yiu

Federated learning, where algorithms are trained across multiple decentralized devices without sharing local data, is increasingly popular in distributed machine learning practice. Typically, a graph structure $G$ exists behind local…

Machine Learning · Statistics 2022-09-20 Huiyuan Wang , Xuyang Zhao , Wei Lin

Existing traffic flow forecasting approaches by deep learning models achieve excellent success based on a large volume of datasets gathered by governments and organizations. However, these datasets may contain lots of user's private data,…

Machine Learning · Computer Science 2020-05-04 Yi Liu , James J. Q. Yu , Jiawen Kang , Dusit Niyato , Shuyu Zhang

Federated Learning (FL) confronts a significant challenge known as data heterogeneity, which impairs model performance and convergence. Existing methods have made notable progress in addressing this issue. However, improving performance in…

Machine Learning · Computer Science 2025-10-24 Zhiqin Yang , Yonggang Zhang , Chenxin Li , Yiu-ming Cheung , Bo Han , Yixuan Yuan

Recently, federated learning has attracted much attention as a privacy-preserving integrated analysis that enables integrated analysis of data held by multiple institutions without sharing raw data. On the other hand, federated learning…

Machine Learning · Computer Science 2024-09-30 Akira Imakura , Tetsuya Sakurai

Federated Learning (FL) is a promising distributed learning mechanism which still faces two major challenges, namely privacy breaches and system efficiency. In this work, we reconceptualize the FL system from the perspective of network…

Machine Learning · Computer Science 2024-01-10 Yuchen Shi , Zheqi Zhu , Pingyi Fan , Khaled B. Letaief , Chenghui Peng

Increasing concerns and regulations about data privacy and sparsity necessitate the study of privacy-preserving, decentralized learning methods for natural language processing (NLP) tasks. Federated learning (FL) provides promising…

In federated graph learning (FGL), a complete graph is divided into multiple subgraphs stored in each client due to privacy concerns, and all clients jointly train a global graph model by only transmitting model parameters. A pain point of…

Machine Learning · Computer Science 2025-03-26 Bo Yan , Zhongjian Zhang , Huabin Sun , Mengmei Zhang , Yang Cao , Chuan Shi