Towards Federated Learning of Deep Graph Neural Networks
Lists
Only you see this
Abstract
Graph neural networks (GNNs) learn node representations by recursively aggregating neighborhood information on graph data. However, in the federated setting, data samples (nodes) located in different clients may be connected to each other, leading to huge information loss to the training method. Existing federated graph learning frameworks solve such a problem by generating missing neighbors or sending information across clients directly. None are suitable for training deep GNNs, which require a more expansive receptive field and higher communication costs. In this work, we introduce a novel framework named $Fed^2GNN$ for federated graph learning of deep GNNs via reconstructing neighborhood information of nodes. Specifically, we design a graph structure named rooted tree. The node embedding obtained by encoding on the rooted tree is the same as that obtained by encoding on the induced subgraph surrounding the node, which allows us to reconstruct the neighborhood information by building the rooted tree of the node. An encoder-decoder framework is then proposed, wherein we first encode missing neighbor information and then decode it to build the rooted tree. Extensive experiments on real-world network datasets show the effectiveness of our framework for training deep GNNs while also achieving better performance for training shadow GNN models
BibTeX
@inproceedings{tian2023towards,
author = {Zhihua Tian and Yuan Ding and Rui Zhang and Jian Liu and Kui Ren},
title = {{Towards Federated Learning of Deep Graph Neural Networks}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=OMwyBv1UBh},
}Loading related content...