CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

TL;DR

CHoE introduces a cross-domain heterogeneous graph prompt learning framework that uses structure-conditioned experts and a semantic fusion module to improve performance across multiple domains.

Contribution

It proposes a novel cross-domain HGPL method with expert routing and semantic fusion, addressing domain shift limitations in existing HGPL approaches.

Findings

CHoE outperforms baseline methods in few-shot cross-domain tasks.

The structure-conditioned experts improve domain adaptation.

Semantic fusion enhances multi-view representation integration.

Abstract

Heterogeneous Graph Prompt Learning (HGPL)has emerged as a promising paradigm for bridging the gap between the objectives of pre-training foundation models and their downstream applications in heterogeneous graph settings. However, existing HGPL methods are primarily designed for in-domain scenarios, whereas real-world deployments often span multiple domains, and the data used for pre-training and downstream tasks may originate from different distributions. Consequently, the applicability of current HGPL approaches is limited to in-domain settings, and their performance typically degrades when application domains shift. To address this serious limitation, we develop CHoE, a cross-domain HGPL method built upon an expert network. During pre-training, we introduce and train structure-conditioned experts, and during prompt tuning, we adopt a structure-aware expert routing and load balancing mechanism to select structurally compatible experts for each meta-path view. In addition, we design a prompt-based semantic fusion module to integrate representations across multiple views for downstream prediction. Extensive experiments show that CHoE consistently improves performance in few-shot cross-domain applications, outperforming all baseline approaches.