Adversarial Signed Graph Learning with Differential Privacy

TL;DR

This paper introduces ASGL, a novel adversarial learning approach that ensures node-level differential privacy in signed graph embeddings by decomposing graphs, perturbing gradients, and using a BFS-based sign inference strategy.

Contribution

The paper proposes a new privacy-preserving signed graph learning method that effectively reduces sensitivity and maintains utility through adversarial training and graph decomposition.

Findings

ASGL achieves strong privacy-utility trade-offs in experiments.

Gradient perturbation mitigates cascading errors in signed graph learning.

Subgraph separation and BFS strategy lower sensitivity and improve sign inference.

Abstract

Signed graphs with positive and negative edges can model complex relationships in social networks. Leveraging on balance theory that deduces edge signs from multi-hop node pairs, signed graph learning can generate node embeddings that preserve both structural and sign information. However, training on sensitive signed graphs raises significant privacy concerns, as model parameters may leak private link information. Existing protection methods with differential privacy (DP) typically rely on edge or gradient perturbation for unsigned graph protection. Yet, they are not well-suited for signed graphs, mainly because edge perturbation tends to cascading errors in edge sign inference under balance theory, while gradient perturbation increases sensitivity due to node interdependence and gradient polarity change caused by sign flips, resulting in larger noise injection. In this paper, motivated by the robustness of adversarial learning to noisy interactions, we present ASGL, a privacy-preserving adversarial signed graph learning method that preserves high utility while achieving node-level DP. We first decompose signed graphs into positive and negative subgraphs based on edge signs, and then design a gradient-perturbed adversarial module to approximate the true signed connectivity distribution. In particular, the gradient perturbation helps mitigate cascading errors, while the subgraph separation facilitates sensitivity reduction. Further, we devise a constrained breadth-first search tree strategy that fuses with balance theory to identify the edge signs between generated node pairs. This strategy also enables gradient decoupling, thereby effectively lowering gradient sensitivity. Extensive experiments on real-world datasets show that ASGL achieves favorable privacy-utility trade-offs across multiple downstream tasks.