# MUG: Meta-path-aware Universal Heterogeneous Graph Pre-Training

arXiv: https://arxiv.org/abs/2602.22645 · HTML: https://mlsanity.com/paper/2602.22645/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [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)
- [Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning](https://mlsanity.com/paper/2105.09111/) (2021)
- [A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources](https://mlsanity.com/paper/2011.14867/) (2020)
- [GFT: Graph Foundation Model with Transferable Tree Vocabulary](https://mlsanity.com/paper/2411.06070/) (2024)
- [SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation](https://mlsanity.com/paper/2502.05424/) (2025)
- [GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs](https://mlsanity.com/paper/2410.10329/) (2024)
- [Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models](https://mlsanity.com/paper/2405.13934/) (2024)
- [GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning](https://mlsanity.com/paper/2310.07365/) (2023)
- [One Prompt Fits All: Universal Graph Adaptation for Pretrained Models](https://mlsanity.com/paper/2509.22416/) (2025)
- [Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning](https://mlsanity.com/paper/2205.00256/) (2022)

## Built on by (most cited first, 5 of 5)

- [Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment](https://mlsanity.com/paper/2605.00731/) (2026)
- [CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts](https://mlsanity.com/paper/2605.15888/) (2026)
- [Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models](https://mlsanity.com/paper/2607.28980/) (2026)
- [Temporal Heterogeneous Graph Pretraining for Relational Deep Learning](https://mlsanity.com/paper/2609.35219/) (2026)
- [More Domains, No Gains? FLO: Fast-Slow Reciprocal Learning for Multi-Domain Graph Pre-training](https://mlsanity.com/paper/2610.14748/) (2026)

## Abstract (arXiv)

Universal graph pre-training has emerged as a key paradigm in graph representation learning, offering a promising way to train encoders to learn transferable representations from unlabeled graphs and to effectively generalize across a wide range of downstream tasks. However, recent explorations in universal graph pre-training primarily focus on homogeneous graphs and it remains unexplored for heterogeneous graphs, which exhibit greater structural and semantic complexity. This heterogeneity makes it highly challenging to train a universal encoder for diverse heterogeneous graphs: (i) the diverse types with dataset-specific semantics hinder the construction of a unified representation space; (ii) the number and semantics of meta-paths vary across datasets, making encoding and aggregation patterns learned from one dataset difficult to apply to others. To address these challenges, we propose a novel Meta-path-aware Universal heterogeneous Graph pre-training (MUG) approach. Specifically, for challenge (i), MUG introduces a input unification module that integrates information from multiple node and relation types within each heterogeneous graph into a unified representation.This representation is then projected into a shared space by a dimension-aware encoder, enabling alignment across graphs with diverse schemas.Furthermore, for challenge (ii), MUG trains a shared encoder to capture consistent structural patterns across diverse meta-path views rather than relying on dataset-specific aggregation strategies, while a global objective encourages discriminability and reduces dataset-specific biases. Extensive experiments demonstrate the effectiveness of MUG on some real datasets.