Polynomial Contrastive Learning for Privacy-Preserving Representation Learning on Graphs
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Representation LearningSelf-Supervised LearningContrastive LearningSimilar Papers 제목 키워드 기반
On Efficiently Explaining Graph-Based Classifiers
Recent work has shown that not only decision trees (DTs) may not be interpretable but also proposed a polynomial-time algorithm for computing one PI-explanation of a DT. This paper shows that for a wide range of classifi…
Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective
Learning with graphs has attracted significant attention recently. Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification,…
Link PredictionNode ClassificationPrivacy PreservingRepresentation LearningPreserving Differential Privacy in Convolutional Deep Belief Networks
The remarkable development of deep learning in medicine and healthcare domain presents obvious privacy issues, when deep neural networks are built on users' personal and highly sensitive data, e.g., clinical records, use…
On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks
Outsourcing deep neural networks (DNNs) inference tasks to an untrusted cloud raises data privacy and integrity concerns. While there are many techniques to ensure privacy and integrity for polynomial-based computations,…
Privacy PreservingCSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research
Child Sexual Abuse Imagery (CSAI) classification is an important yet challenging problem for computer vision research due to the strict legal and ethical restrictions that prevent the public sharing of CSAI datasets. Thi…