Polynomial Contrastive Learning for Privacy-Preserving Representation Learning on Graphs
This work addresses privacy-preserving representation learning on graphs for applications requiring data confidentiality, representing an incremental advancement by adapting existing methods for encryption compatibility.
The paper tackles the incompatibility of self-supervised learning methods like GRACE with Homomorphic Encryption due to non-polynomial operations, introducing Poly-GRACE, which achieves competitive performance on benchmark datasets, with superior results on CiteSeer.
Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations on graph data without requiring manual labels. However, leading SSL methods like GRACE are fundamentally incompatible with privacy-preserving technologies such as Homomorphic Encryption (HE) due to their reliance on non-polynomial operations. This paper introduces Poly-GRACE, a novel framework for HE-compatible self-supervised learning on graphs. Our approach consists of a fully polynomial-friendly Graph Convolutional Network (GCN) encoder and a novel, polynomial-based contrastive loss function. Through experiments on three benchmark datasets -- Cora, CiteSeer, and PubMed -- we demonstrate that Poly-GRACE not only enables private pre-training but also achieves performance that is highly competitive with, and in the case of CiteSeer, superior to the standard non-private baseline. Our work represents a significant step towards practical and high-performance privacy-preserving graph representation learning.