{"ID":2869004,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25205","arxiv_id":"2509.25205","title":"Polynomial Contrastive Learning for Privacy-Preserving Representation Learning on Graphs","abstract":"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.","short_abstract":"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-polyn...","url_abs":"https://arxiv.org/abs/2509.25205","url_pdf":"https://arxiv.org/pdf/2509.25205v1","authors":"[\"Daksh Pandey\"]","published":"2025-09-19T20:00:30Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CR\",\"math.RA\"]","methods":"[]","has_code":false}