A Transfer Learning Framework for Multilayer Networks via Model Averaging

TL;DR

This paper introduces a transfer learning framework for multilayer networks that uses model averaging and cross-validation to improve link prediction accuracy without sharing raw data.

Contribution

A novel bi-level model averaging method for multilayer networks that automatically weights models and preserves privacy, with proven optimality and convergence.

Findings

Outperforms existing methods in predictive accuracy.

Demonstrates robustness across different scenarios.

Efficient and privacy-preserving computational framework.

Abstract

Link prediction in multilayer networks is a key challenge in applications such as recommendation systems and protein-protein interaction prediction. While many techniques have been developed, most rely on assumptions about shared structures and require access to raw auxiliary data, limiting their practicality. To address these issues, we propose a novel transfer learning framework for multilayer networks using a bi-level model averaging method. A $K$-fold cross-validation criterion based on edges is used to automatically weight inter-layer and intra-layer candidate models. This enables the transfer of information from auxiliary layers while mitigating model uncertainty, even without prior knowledge of shared structures. Theoretically, we prove the optimality and weight convergence of our method under mild conditions. Computationally, our framework is efficient and privacy-preserving, as it avoids raw data sharing and supports parallel processing across multiple servers. Simulations show our method outperforms others in predictive accuracy and robustness. We further demonstrate its practical value through two real-world recommendation system applications.