A Framework of Transferring Structures Across Large-scale Information Networks

TL;DR

This paper introduces FTLSIN, a framework that transfers structural information across large-scale information networks to improve network representations, addressing the challenge of network heterogeneity.

Contribution

The paper proposes a novel two-layer random walk framework for transferring information between large-scale networks, enhancing cross-network link prediction.

Findings

Effective transfer of structural information demonstrated on real-world datasets

Improved network representation performance across different networks

Two-layer random walk effectively measures relations between networks

Abstract

The existing domain-specific methods for mining information networks in machine learning aims to represent the nodes of an information network into a vector format. However, the real-world large-scale information network cannot make well network representations by one network. When the information of the network structure transferred from one network to another network, the performance of network representation might decrease sharply. To achieve these ends, we propose a novel framework to transfer useful information across relational large-scale information networks (FTLSIN). The framework consists of a 2-layer random walks to measure the relations between two networks and predict links across them. Experiments on real-world datasets demonstrate the effectiveness of the proposed model.