Federated Dynamic GNN with Secure Aggregation

Abstract

Given video data from multiple personal devices or street cameras, can we exploit the structural and dynamic information to learn dynamic representation of objects for applications such as distributed surveillance, without storing data at a central server that leads to a violation of user privacy? In this work, we introduce Federated Dynamic Graph Neural Network (Feddy), a distributed and secured framework to learn the object representations from multi-user graph sequences: i) It aggregates structural information from nearby objects in the current graph as well as dynamic information from those in the previous graph. It uses a self-supervised loss of predicting the trajectories of objects. ii) It is trained in a federated learning manner. The centrally located server sends the model to user devices. Local models on the respective user devices learn and periodically send their learning to the central server without ever exposing the user's data to server. iii) Studies showed that the aggregated parameters could be inspected though decrypted when broadcast to clients for model synchronizing, after the server performed a weighted average. We design an appropriate aggregation mechanism of secure aggregation primitives that can protect the security and privacy in federated learning with scalability. Experiments on four video camera datasets (in four different scenes) as well as simulation demonstrate that Feddy achieves great effectiveness and security.

16 pages, 2 figures

References in corpus (12)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Inductive Representation Learning on Large Graphs
• Federated Learning: Strategies for Improving Communication Efficiency
• Deep Convolutional Networks on Graph-Structured Data
• Towards Federated Learning at Scale: System Design
• Learning Convolutional Neural Networks for Graphs
• Federated Optimization:Distributed Optimization Beyond the Datacenter
• Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
• Dynamic Graph Convolutional Networks
• Attributed Network Embedding for Learning in a Dynamic Environment
• Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing
• Practical Secure Aggregation for Federated Learning on User-Held Data

Cited by in corpus (9)

• FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
• FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
• Federated Graph Classification over Non-IID Graphs
• Graph Federated Learning for CIoT Devices in Smart Home Applications
• SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
• Federated Graph Learning -- A Position Paper
• 2SFGL: A Simple And Robust Protocol For Graph-Based Fraud Detection
• Federated learning with differential privacy and an untrusted aggregator
• FedGraph: Federated Graph Learning with Intelligent Sampling