FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacy
This addresses the need for privacy-preserving graph representation learning for data holders in distributed networks, though it is incremental as it adapts existing federated and embedding methods to a specific graph scenario.
FedWalk tackles the problem of unsupervised node embedding in federated settings with privacy concerns by developing a communication-efficient algorithm that protects raw graph data locally, achieving competitive performance with only up to 1.8% Micro-F1 and 4.4% Macro-F1 score loss while reducing inter-device communication by about 6.7 times per walk.
Node embedding aims to map nodes in the complex graph into low-dimensional representations. The real-world large-scale graphs and difficulties of labeling motivate wide studies of unsupervised node embedding problems. Nevertheless, previous effort mostly operates in a centralized setting where a complete graph is given. With the growing awareness of data privacy, data holders who are only aware of one vertex and its neighbours demand greater privacy protection. In this paper, we introduce FedWalk, a random-walk-based unsupervised node embedding algorithm that operates in such a node-level visibility graph with raw graph information remaining locally. FedWalk is designed to offer centralized competitive graph representation capability with data privacy protection and great communication efficiency. FedWalk instantiates the prevalent federated paradigm and contains three modules. We first design a hierarchical clustering tree (HCT) constructor to extract the structural feature of each node. A dynamic time warping algorithm seamlessly handles the structural heterogeneity across different nodes. Based on the constructed HCT, we then design a random walk generator, wherein a sequence encoder is designed to preserve privacy and a two-hop neighbor predictor is designed to save communication cost. The generated random walks are then used to update node embedding based on a SkipGram model. Extensive experiments on two large graphs demonstrate that Fed-Walk achieves competitive representativeness as a centralized node embedding algorithm does with only up to 1.8% Micro-F1 score and 4.4% Marco-F1 score loss while reducing about 6.7 times of inter-device communication per walk.