New TGHE framework enables privacy-preserving GNN inference on large graphs

Researchers have developed TGHE, a novel framework for privacy-preserving Graph Neural Network (GNN) inference in edge-cloud systems. Unlike previous graph-centric approaches that struggle with large datasets, TGHE utilizes an ego-centric method by exploiting a template phenomenon in transaction graphs. This allows it to canonicalize and pack structurally similar local computation trees into shared ciphertexts for parallel processing, significantly improving efficiency and enabling analysis of much larger graphs. AI

IMPACT This framework could enable privacy-preserving analysis of large-scale dynamic graphs in fields like finance.

RANK_REASON The cluster contains an academic paper detailing a new technical framework for GNNs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• CKKS
• Graph Neural Network

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →