M3FGM:a node masking and multi-granularity message passing-based federated graph model for spatial-temporal data prediction

TL;DR

This paper introduces M3FGM, a federated graph model with node masking and multi-granularity message passing, improving spatial-temporal data prediction while addressing client offline issues and revealing better client relationships.

Contribution

The paper proposes a novel GNN-based split federated learning method with node masking and multi-granularity message passing to enhance privacy, robustness, and client relationship modeling.

Findings

Outperforms baseline models on real traffic datasets

Achieves superior spatial-temporal prediction accuracy

Handles client offline scenarios effectively

Abstract

Researchers are solving the challenges of spatial-temporal prediction by combining Federated Learning (FL) and graph models with respect to the constrain of privacy and security. In order to make better use of the power of graph model, some researchs also combine split learning(SL). However, there are still several issues left unattended: 1) Clients might not be able to access the server during inference phase; 2) The graph of clients designed manually in the server model may not reveal the proper relationship between clients. This paper proposes a new GNN-oriented split federated learning method, named node {\bfseries M}asking and {\bfseries M}ulti-granularity {\bfseries M}essage passing-based Federated Graph Model (M$^3$FGM) for the above issues. For the first issue, the server model of M$^3$FGM employs a MaskNode layer to simulate the case of clients being offline. We also redesign the decoder of the client model using a dual-sub-decoders structure so that each client model can use its local data to predict independently when offline. As for the second issue, a new GNN layer named Multi-Granularity Message Passing (MGMP) layer enables each client node to perceive global and local information. We conducted extensive experiments in two different scenarios on two real traffic datasets. Results show that M$^3$FGM outperforms the baselines and variant models, achieves the best results in both datasets and scenarios.