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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Peiyuan, Huang, Yongqi, Zhao, Jitao, He, Dongxiao, Jin, Di, Zhang, Weixiong
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910223701114880
author Li, Peiyuan
Huang, Yongqi
Zhao, Jitao
He, Dongxiao
Jin, Di
Zhang, Weixiong
author_facet Li, Peiyuan
Huang, Yongqi
Zhao, Jitao
He, Dongxiao
Jin, Di
Zhang, Weixiong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15888
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts
Li, Peiyuan
Huang, Yongqi
Zhao, Jitao
He, Dongxiao
Jin, Di
Zhang, Weixiong
Machine Learning
Artificial Intelligence
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.
title CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.15888