Graph Domain Adaptation with Localized Graph Signal Representations

TL;DR

This paper introduces a graph domain adaptation method that leverages localized graph signal representations, specifically spectral graph wavelets, to transfer label information from a labeled source graph to an unlabeled or sparsely labeled target graph, improving classification accuracy.

Contribution

The paper presents a novel domain adaptation algorithm for graphs that uses localized spectral graph wavelets to model local label variations and transfer information between source and target graphs.

Findings

Achieves higher classification accuracy than existing methods

Effectively captures local label variations on graphs

Demonstrates robustness across multiple datasets

Abstract

In this paper we propose a domain adaptation algorithm designed for graph domains. Given a source graph with many labeled nodes and a target graph with few or no labeled nodes, we aim to estimate the target labels by making use of the similarity between the characteristics of the variation of the label functions on the two graphs. Our assumption about the source and the target domains is that the local behaviour of the label function, such as its spread and speed of variation on the graph, bears resemblance between the two graphs. We estimate the unknown target labels by solving an optimization problem where the label information is transferred from the source graph to the target graph based on the prior that the projections of the label functions onto localized graph bases be similar between the source and the target graphs. In order to efficiently capture the local variation of the label functions on the graphs, spectral graph wavelets are used as the graph bases. Experimentation on various data sets shows that the proposed method yields quite satisfactory classification accuracy compared to reference domain adaptation methods.