Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Data

TL;DR

This paper introduces DNAN, a novel graph domain adaptation method that combines nuclear-norm Wasserstein discrepancy with denoising autoencoders to improve class alignment and robustness in graph classification tasks.

Contribution

The paper proposes DNAN, integrating NWD and a variational autoencoder for effective domain adaptation in graph data, addressing limitations of adversarial and pseudo-labeling methods.

Findings

DNAN outperforms state-of-the-art methods on graph classification benchmarks.

The combination of NWD and denoising enhances domain alignment and feature robustness.

Experimental results validate the effectiveness of DNAN in various scenarios.

Abstract

Graph-structured data can be found in numerous domains, yet the scarcity of labeled instances hinders its effective utilization of deep learning in many scenarios. Traditional unsupervised domain adaptation (UDA) strategies for graphs primarily hinge on adversarial learning and pseudo-labeling. These approaches fail to effectively leverage graph discriminative features, leading to class mismatching and unreliable label quality. To navigate these obstacles, we develop the Denoising and Nuclear-Norm Wasserstein Adaptation Network (DNAN). DNAN employs the Nuclear-norm Wasserstein discrepancy (NWD), which can simultaneously achieve domain alignment and class distinguishment. DANA also integrates a denoising mechanism via a variational graph autoencoder that mitigates data noise. This denoising mechanism helps capture essential features of both source and target domains, improving the robustness of the domain adaptation process. Our comprehensive experiments demonstrate that DNAN outperforms state-of-the-art methods on standard UDA benchmarks for graph classification.