# Pathfinder Discovery Networks for Neural Message Passing

arXiv: https://arxiv.org/abs/2010.12878 · HTML: https://mlsanity.com/paper/2010.12878/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 16 of 16)

- [PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models](https://mlsanity.com/paper/2104.07788/) (2021)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [Empowering Graph Representation Learning with Test-Time Graph Transformation](https://mlsanity.com/paper/2210.03561/) (2022)
- [PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm](https://mlsanity.com/paper/2203.00638/) (2022)
- [TF-GNN: Graph Neural Networks in TensorFlow](https://mlsanity.com/paper/2207.03522/) (2022)
- [Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networks](https://mlsanity.com/paper/2102.08100/) (2021)
- [Graph Neural Network for Cell Tracking in Microscopy Videos](https://mlsanity.com/paper/2202.04731/) (2022)
- [Synthetic Graph Generation to Benchmark Graph Learning](https://mlsanity.com/paper/2204.01376/) (2022)
- [Towards Data-centric Graph Machine Learning: Review and Outlook](https://mlsanity.com/paper/2309.10979/) (2023)
- [MOOMIN: Deep Molecular Omics Network for Anti-Cancer Drug Combination Therapy](https://mlsanity.com/paper/2110.15087/) (2021)
- [Deep Surrogate Docking: Accelerating Automated Drug Discovery with Graph Neural Networks](https://mlsanity.com/paper/2211.02720/) (2022)
- [Architectural Implications of GNN Aggregation Programming Abstractions](https://mlsanity.com/paper/2310.12184/) (2023)
- [TigerLily: Finding drug interactions in silico with the Graph](https://mlsanity.com/paper/2204.08206/) (2022)
- [SynHING: Synthetic Heterogeneous Information Network Generation for Graph Learning and Explanation](https://mlsanity.com/paper/2401.04133/) (2024)
- [Optimizing Luxury Vehicle Dealership Networks: A Graph Neural Network Approach to Site Selection](https://mlsanity.com/paper/2408.13961/) (2024)
- [Higher-Order Cell Tracking Transformer](https://mlsanity.com/paper/2607.11754/) (2026)

## Abstract (arXiv)

In this work we propose Pathfinder Discovery Networks (PDNs), a method for jointly learning a message passing graph over a multiplex network with a downstream semi-supervised model. PDNs inductively learn an aggregated weight for each edge, optimized to produce the best outcome for the downstream learning task. PDNs are a generalization of attention mechanisms on graphs which allow flexible construction of similarity functions between nodes, edge convolutions, and cheap multiscale mixing layers. We show that PDNs overcome weaknesses of existing methods for graph attention (e.g. Graph Attention Networks), such as the diminishing weight problem. Our experimental results demonstrate competitive predictive performance on academic node classification tasks. Additional results from a challenging suite of node classification experiments show how PDNs can learn a wider class of functions than existing baselines. We analyze the relative computational complexity of PDNs, and show that PDN runtime is not considerably higher than static-graph models. Finally, we discuss how PDNs can be used to construct an easily interpretable attention mechanism that allows users to understand information propagation in the graph.