← Search

Yuchao Tang

2 accepted papers

2026

FedSkeleton: Secure Multi-Party Graph Skeleton Construction for Privacy-Preserving Federated Time-Series Forecasting

AAAI 2026technical

In real-world time-series modelling, graph structures are widely adopted because they explicitly encode node topology and capture complex network dynamics. In practice, however, a complete graph is often partitioned across multiple parties; each party can access only its local sub-graph and, owing t

Cited by 0SourcePDFScholar
2024

Optimizing ADMM and Over-Relaxed ADMM Parameters for Linear Quadratic Problems

AAAI 2024technical

The Alternating Direction Method of Multipliers (ADMM) has gained significant attention across a broad spectrum of machine learning applications. Incorporating the over-relaxation technique shows potential for enhancing the convergence rate of ADMM. However, determining optimal algorithmic parameter…

Cited by 3SourcePDFScholar