# Path-Augmented Graph Transformer Network

arXiv: https://arxiv.org/abs/1905.12712 · HTML: https://mlsanity.com/paper/1905.12712/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

## Built on by (most cited first, 22 of 22)

- [Do Transformers Really Perform Bad for Graph Representation?](https://mlsanity.com/paper/2106.05234/) (2021)
- [Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction](https://mlsanity.com/paper/2110.09681/) (2021)
- [Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs](https://mlsanity.com/paper/2110.01191/) (2021)
- [Rewiring with Positional Encodings for Graph Neural Networks](https://mlsanity.com/paper/2201.12674/) (2022)
- [KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction](https://mlsanity.com/paper/2206.03364/) (2022)
- [Learning Attributed Graph Representations with Communicative Message Passing Transformer](https://mlsanity.com/paper/2107.08773/) (2021)
- [Extracting Temporal Event Relation with Syntax-guided Graph Transformer](https://mlsanity.com/paper/2104.09570/) (2021)
- [Lo-Hi: Practical ML Drug Discovery Benchmark](https://mlsanity.com/paper/2310.06399/) (2023)
- [Difficulty in chirality recognition for Transformer architectures learning chemical structures from string](https://mlsanity.com/paper/2303.11593/) (2023)
- [Discovering the Representation Bottleneck of Graph Neural Networks](https://mlsanity.com/paper/2205.07266/) (2022)
- [Implementing graph neural networks with TensorFlow-Keras](https://mlsanity.com/paper/2103.04318/) (2021)
- [Uni-ELF: A Multi-Level Representation Learning Framework for Electrolyte Formulation Design](https://mlsanity.com/paper/2407.06152/) (2024)
- [Graph Scattering beyond Wavelet Shackles](https://mlsanity.com/paper/2301.11456/) (2023)
- [Open World Learning Graph Convolution for Latency Estimation in Routing Networks](https://mlsanity.com/paper/2207.14643/) (2022)
- [DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning](https://mlsanity.com/paper/2410.02023/) (2024)
- [Attention-based graph neural networks: a survey](https://mlsanity.com/paper/2605.08679/) (2026)
- [GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention](https://mlsanity.com/paper/2104.05914/) (2021)
- [Image-Like Graph Representations for Improved Molecular Property Prediction](https://mlsanity.com/paper/2111.10695/) (2021)
- [AIRI: Predicting Retention Indices and their Uncertainties using Artificial Intelligence](https://mlsanity.com/paper/2401.01506/) (2024)
- [Graph in Graph Neural Network](https://mlsanity.com/paper/2407.00696/) (2024)
- [A decoupled alignment kernel for peptide membrane permeability predictions](https://mlsanity.com/paper/2511.21566/) (2025)
- [Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentials](https://mlsanity.com/paper/2603.22810/) (2026)

## Abstract (arXiv)

Much of the recent work on learning molecular representations has been based on Graph Convolution Networks (GCN). These models rely on local aggregation operations and can therefore miss higher-order graph properties. To remedy this, we propose Path-Augmented Graph Transformer Networks (PAGTN) that are explicitly built on longer-range dependencies in graph-structured data. Specifically, we use path features in molecular graphs to create global attention layers. We compare our PAGTN model against the GCN model and show that our model consistently outperforms GCNs on molecular property prediction datasets including quantum chemistry (QM7, QM8, QM9), physical chemistry (ESOL, Lipophilictiy) and biochemistry (BACE, BBBP).