mlsanityData to 14 Oct 2026

Path-Augmented Graph Transformer Network

arXiv 1905.12712 ↗First posted 29 May 2019cs.LG stat.MLcited by 22

Not on the map. Why?

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).

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 4; 2023: 3; 2024: 4; 2025: 1; 2026: 2.

22 papers.

Sort:

  1. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 320
  2. 2021Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction predictioncited by 68
  3. 2021Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphscited by 44
  4. 2022Rewiring with Positional Encodings for Graph Neural Networkscited by 36
  5. 2022KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Predictioncited by 31
  6. 2021Learning Attributed Graph Representations with Communicative Message Passing Transformercited by 20
  7. 2021Extracting Temporal Event Relation with Syntax-guided Graph Transformercited by 16
  8. 2023Lo-Hi: Practical ML Drug Discovery Benchmarkcited by 10
  9. 2023Difficulty in chirality recognition for Transformer architectures learning chemical structures from stringcited by 7
  10. 2022Discovering the Representation Bottleneck of Graph Neural Networkscited by 4
  11. 2021Implementing graph neural networks with TensorFlow-Kerascited by 3
  12. 2024Uni-ELF: A Multi-Level Representation Learning Framework for Electrolyte Formulation Designcited by 3
10 more
  1. 2023Graph Scattering beyond Wavelet Shacklescited by 2
  2. 2022Open World Learning Graph Convolution for Latency Estimation in Routing Networkscited by 1
  3. 2024DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learningcited by 1
  4. 2026Attention-based graph neural networks: a surveycited by 1
  5. 2021GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attentioncited by 0
  6. 2021Image-Like Graph Representations for Improved Molecular Property Predictioncited by 0
  7. 2024AIRI: Predicting Retention Indices and their Uncertainties using Artificial Intelligencecited by 0
  8. 2024Graph in Graph Neural Networkcited by 0
  9. 2025A decoupled alignment kernel for peptide membrane permeability predictionscited by 0
  10. 2026Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentialscited by 0