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

arXiv: https://arxiv.org/abs/2605.15888 · HTML: https://mlsanity.com/paper/2605.15888/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 15 May 2026.

## Builds on (most cited first, 27 of 27)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://mlsanity.com/paper/2302.08043/) (2023)
- [Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning](https://mlsanity.com/paper/2105.09111/) (2021)
- [Universal Prompt Tuning for Graph Neural Networks](https://mlsanity.com/paper/2209.15240/) (2022)
- [Unsupervised Attributed Multiplex Network Embedding](https://mlsanity.com/paper/1911.06750/) (2019)
- [HDMI: High-order Deep Multiplex Infomax](https://mlsanity.com/paper/2102.07810/) (2021)
- [Graph Prompt Learning: A Comprehensive Survey and Beyond](https://mlsanity.com/paper/2311.16534/) (2023)
- [Pro-tuning: Unified Prompt Tuning for Vision Tasks](https://mlsanity.com/paper/2207.14381/) (2022)
- [Heterogeneous Graph Masked Autoencoders](https://mlsanity.com/paper/2208.09957/) (2022)
- [HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learning](https://mlsanity.com/paper/2312.01878/) (2023)
- [HiGPT: Heterogeneous Graph Language Model](https://mlsanity.com/paper/2402.16024/) (2024)
- [HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2310.15318/) (2023)
- [GraphLoRA: Structure-Aware Contrastive Low-Rank Adaptation for Cross-Graph Transfer Learning](https://mlsanity.com/paper/2409.16670/) (2024)
- [Edge Prompt Tuning for Graph Neural Networks](https://mlsanity.com/paper/2503.00750/) (2025)
- [Heterogeneous Graph Contrastive Multi-view Learning](https://mlsanity.com/paper/2210.00248/) (2022)
- [One Prompt Fits All: Universal Graph Adaptation for Pretrained Models](https://mlsanity.com/paper/2509.22416/) (2025)
- [MUG: Meta-path-aware Universal Heterogeneous Graph Pre-Training](https://mlsanity.com/paper/2602.22645/) (2026)
- [Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding](https://mlsanity.com/paper/2602.13075/) (2026)
- [Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning](https://mlsanity.com/paper/2507.09132/) (2025)

## Built on by (most cited first, 1 of 1)

- [DeKoR: Decomposed Knowledge Routing for Efficient GNN--LLM Fusion](https://mlsanity.com/paper/2610.14710/) (2026)

## Abstract (arXiv)

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.