Poster

Information Obfuscation of Graph Neural Networks

Peiyuan Liao · Han Zhao · Keyulu Xu · Tommi Jaakkola · Geoff Gordon · Stefanie Jegelka · Ruslan Salakhutdinov

Keywords: [ Networks and Relational Learning ] [ Algorithms ]

[ Abstract ]
[ Paper ]
[ Visit Poster at Spot C1 in Virtual World ]
Tue 20 Jul 9 p.m. PDT — 11 p.m. PDT
 
Spotlight presentation: Deep Learning Algorithms and Applications
Tue 20 Jul 6 p.m. PDT — 7 p.m. PDT

Abstract:

While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes. In this paper, we study the problem of protecting sensitive attributes by information obfuscation when learning with graph structured data. We propose a framework to locally filter out pre-determined sensitive attributes via adversarial training with the total variation and the Wasserstein distance. Our method creates a strong defense against inference attacks, while only suffering small loss in task performance. Theoretically, we analyze the effectiveness of our framework against a worst-case adversary, and characterize an inherent trade-off between maximizing predictive accuracy and minimizing information leakage. Experiments across multiple datasets from recommender systems, knowledge graphs and quantum chemistry demonstrate that the proposed approach provides a robust defense across various graph structures and tasks, while producing competitive GNN encoders for downstream tasks.

Chat is not available.