# Cross-domain Network Representations

## TL;DR

This paper introduces CDNR, a novel cross-domain network representation method that transfers structural knowledge from rich to scarce domains using random walks, enhancing network embeddings for universal networks.

## Contribution

The paper proposes a new cross-domain network representation algorithm that effectively transfers structural knowledge across domains, addressing limitations of domain-specific approaches.

## Key findings

- CDNR outperforms existing methods on real-world datasets.
- It enables network representation in domains lacking rich topological information.
- The approach is effective in an unsupervised setting.

## Abstract

The purpose of network representation is to learn a set of latent features by obtaining community information from network structures to provide knowledge for machine learning tasks. Recent research has driven significant progress in network representation by employing random walks as the network sampling strategy. Nevertheless, existing approaches rely on domain-specifically rich community structures and fail in the network that lack topological information in its own domain. In this paper, we propose a novel algorithm for cross-domain network representation, named as CDNR. By generating the random walks from a structural rich domain and transferring the knowledge on the random walks across domains, it enables a network representation for the structural scarce domain as well. To be specific, CDNR is realized by a cross-domain two-layer node-scale balance algorithm and a cross-domain two-layer knowledge transfer algorithm in the framework of cross-domain two-layer random walk learning. Experiments on various real-world datasets demonstrate the effectiveness of CDNR for universal networks in an unsupervised way.