# CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning

arXiv: https://arxiv.org/abs/2603.27685 · HTML: https://mlsanity.com/paper/2603.27685/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 29 Mar 2026.

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

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://mlsanity.com/paper/2302.08043/) (2023)
- [All in One: Multi-task Prompting for Graph Neural Networks](https://mlsanity.com/paper/2307.01504/) (2023)
- [Heterogeneous Graph Neural Networks for Malicious Account Detection](https://mlsanity.com/paper/2002.12307/) (2020)
- [All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining](https://mlsanity.com/paper/2402.09834/) (2024)
- [Simple and Efficient Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2207.02547/) (2022)
- [Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution](https://mlsanity.com/paper/1909.01541/) (2019)
- [DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection](https://mlsanity.com/paper/2207.03579/) (2022)
- [SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation](https://mlsanity.com/paper/2502.05424/) (2025)
- [Anomaly Detection in Dynamic Graphs via Transformer](https://mlsanity.com/paper/2106.09876/) (2021)
- [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)
- [Data Augmentation on Graphs: A Technical Survey](https://mlsanity.com/paper/2212.09970/) (2022)
- [Heterogeneous Feature Augmentation for Ponzi Detection in Ethereum](https://mlsanity.com/paper/2204.08916/) (2022)
- [HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answering](https://mlsanity.com/paper/2501.01203/) (2025)
- [HGMP:Heterogeneous Graph Multi-Task Prompt Learning](https://mlsanity.com/paper/2507.07405/) (2025)
- [Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights](https://mlsanity.com/paper/2603.10033/) (2026)
- [Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision](https://mlsanity.com/paper/2408.00641/) (2024)

## Abstract (arXiv)

Heterogeneous graph representation learning (HGRL) is essential for modeling complex systems with diverse node and edge types. However, most existing methods are limited to closed-world settings with shared schemas and feature spaces, hindering cross-domain generalization. While recent graph foundation models improve transferability, they often target homogeneous graphs, rely on domain-specific schemas, or require rich textual attributes. Consequently, text-free and few-shot cross-domain HGRL remains underexplored. To address this, we propose CrossHGL, a foundation framework that preserves and transfers multi-relational structural semantics without external textual supervision. Specifically, a semantic-preserving transformation strategy homogenizes heterogeneous graphs while encoding interaction semantics into edge features. Based on this, a prompt-aware multi-domain pre-training framework with a Tri-Prompt mechanism captures transferable knowledge across feature, edge, and structure perspectives via self-supervised contrastive learning. For target-domain adaptation, we develop a parameter-efficient fine-tuning strategy that freezes the pre-trained backbone and performs few-shot classification via prompt composition and prototypical learning. Experiments on node-level and graph-level tasks show that CrossHGL consistently outperforms state-of-the-art baselines, yielding average relative improvements of 25.1% and 7.6% in Micro-F1 for node and graph classification, respectively, while remaining competitive in challenging feature-degenerated settings.