FedGraph: A Research Library and Benchmark for Federated Graph Learning
- URL: http://arxiv.org/abs/2410.06340v2
- Date: Fri, 1 Nov 2024 21:02:52 GMT
- Title: FedGraph: A Research Library and Benchmark for Federated Graph Learning
- Authors: Yuhang Yao, Yuan Li, Xinyi Fan, Junhao Li, Kay Liu, Weizhao Jin, Srivatsan Ravi, Philip S. Yu, Carlee Joe-Wong,
- Abstract summary: We introduce FedGraph, a research library built for practical distributed deployment and benchmarking in federated graph learning.
FedGraph supports a range of state-of-the-art graph learning methods and includes built-in profiling tools to evaluate system performance.
We demonstrate the first privacy-preserving federated learning system to run on graphs with 100 million nodes.
- Score: 40.257355007504074
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Federated graph learning is an emerging field with significant practical challenges. While many algorithms have been proposed to enhance the accuracy of training graph neural networks, e.g., for node classification problems on large graphs, in a federated manner, their system performance is often overlooked, even though it is crucial for real-world deployment. To address this gap, we introduce FedGraph, a research library built for practical distributed deployment and benchmarking in federated graph learning. FedGraph supports a range of state-of-the-art graph learning methods and includes built-in profiling tools to evaluate system performance, focusing specifically on communication and computation costs during training. Unlike existing benchmark platforms, FedGraph natively incorporates homomorphic encryption to enhance privacy preservation and facilitates the development of practical applications by enabling distributed training across multiple physical machines, providing an evaluation framework that can guide the system design of future federated graph learning algorithms. Leveraging these optimizations, we use FedGraph to demonstrate the first privacy-preserving federated learning system to run on graphs with 100 million nodes.
Related papers
- Bures-Wasserstein Means of Graphs [60.42414991820453]
We propose a novel framework for defining a graph mean via embeddings in the space of smooth graph signal distributions.
By finding a mean in this embedding space, we can recover a mean graph that preserves structural information.
We establish the existence and uniqueness of the novel graph mean, and provide an iterative algorithm for computing it.
arXiv Detail & Related papers (2023-05-31T11:04:53Z) - Lumos: Heterogeneity-aware Federated Graph Learning over Decentralized
Devices [19.27111697495379]
Graph neural networks (GNNs) have been widely deployed in real-world networked applications and systems.
We propose the first federated GNN framework called Lumos that supports supervised and unsupervised learning.
Based on the constructed tree for each client, a decentralized tree-based GNN trainer is proposed to support versatile training.
arXiv Detail & Related papers (2023-03-01T13:27:06Z) - State of the Art and Potentialities of Graph-level Learning [54.68482109186052]
Graph-level learning has been applied to many tasks including comparison, regression, classification, and more.
Traditional approaches to learning a set of graphs rely on hand-crafted features, such as substructures.
Deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations.
arXiv Detail & Related papers (2023-01-14T09:15:49Z) - Graph Pooling for Graph Neural Networks: Progress, Challenges, and
Opportunities [128.55790219377315]
Graph neural networks have emerged as a leading architecture for many graph-level tasks.
graph pooling is indispensable for obtaining a holistic graph-level representation of the whole graph.
arXiv Detail & Related papers (2022-04-15T04:02:06Z) - FedGraph: Federated Graph Learning with Intelligent Sampling [7.798227884125872]
Federated learning has attracted much research attention due to its privacy protection in distributed machine learning.
Existing work of federated learning mainly focuses on Convolutional Neural Network (CNN), which cannot efficiently handle graph data that are popular in many applications.
In this paper, we propose FedGraph for federated graph learning among multiple computing clients, each of which holds a subgraph.
arXiv Detail & Related papers (2021-11-02T04:58:03Z) - CogDL: A Comprehensive Library for Graph Deep Learning [55.694091294633054]
We present CogDL, a library for graph deep learning that allows researchers and practitioners to conduct experiments, compare methods, and build applications with ease and efficiency.
In CogDL, we propose a unified design for the training and evaluation of GNN models for various graph tasks, making it unique among existing graph learning libraries.
We develop efficient sparse operators for CogDL, enabling it to become the most competitive graph library for efficiency.
arXiv Detail & Related papers (2021-03-01T12:35:16Z) - Co-embedding of Nodes and Edges with Graph Neural Networks [13.020745622327894]
Graph embedding is a way to transform and encode the data structure in high dimensional and non-Euclidean feature space.
CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space.
Our approach achieves or matches the state-of-the-art performance in four graph learning tasks.
arXiv Detail & Related papers (2020-10-25T22:39:31Z) - GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training [62.73470368851127]
Graph representation learning has emerged as a powerful technique for addressing real-world problems.
We design Graph Contrastive Coding -- a self-supervised graph neural network pre-training framework.
We conduct experiments on three graph learning tasks and ten graph datasets.
arXiv Detail & Related papers (2020-06-17T16:18:35Z) - SIGN: Scalable Inception Graph Neural Networks [4.5158585619109495]
We propose a new, efficient and scalable graph deep learning architecture that sidesteps the need for graph sampling.
Our architecture allows using different local graph operators to best suit the task at hand.
We obtain state-of-the-art results on ogbn-papers100M, the largest public graph dataset, with over 110 million nodes and 1.5 billion edges.
arXiv Detail & Related papers (2020-04-23T14:46:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.