GDA-HIN: A Generalized Domain Adaptive Model across Heterogeneous Information Networks

TL;DR

This paper introduces GDA-HIN, a novel model for domain adaptation across heterogeneous information networks that effectively handles shared and private node types, improving knowledge transfer between networks.

Contribution

The paper proposes GDA-HIN, a generalized model that aligns shared node types and leverages private node types in heterogeneous networks for better domain adaptation.

Findings

GDA-HIN outperforms state-of-the-art methods on multiple datasets.

It effectively aligns shared node distributions across networks.

Utilizes both shared and private node types for improved transfer learning.

Abstract

Domain adaptation using graph-structured networks learns label-discriminative and network-invariant node embeddings by sharing graph parameters. Most existing works focus on domain adaptation of homogeneous networks. The few works that study heterogeneous cases only consider shared node types but ignore private node types in individual networks. However, for given source and target heterogeneous networks, they generally contain shared and private node types, where private types bring an extra challenge for graph domain adaptation. In this paper, we investigate Heterogeneous Information Networks (HINs) with both shared and private node types and propose a Generalized Domain Adaptive model across HINs (GDA-HIN) to handle the domain shift between them. GDA-HIN can not only align the distribution of identical-type nodes and edges in two HINs but also make full use of different-type nodes and edges to improve the performance of knowledge transfer. Extensive experiments on several datasets demonstrate that GDA-HIN can outperform state-of-the-art methods in various domain adaptation tasks across heterogeneous networks.