# Leveraging Classical Algorithms for Graph Neural Networks

arXiv: https://arxiv.org/abs/2510.21574 · HTML: https://mlsanity.com/paper/2510.21574/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism](https://mlsanity.com/paper/2201.12987/) (2022)
- [Graph Foundation Models: Concepts, Opportunities and Challenges](https://mlsanity.com/paper/2310.11829/) (2023)
- [Neural Algorithmic Reasoning](https://mlsanity.com/paper/2105.02761/) (2021)
- [Position: Graph Foundation Models are Already Here](https://mlsanity.com/paper/2402.02216/) (2024)
- [Neural Algorithmic Reasoners are Implicit Planners](https://mlsanity.com/paper/2110.05442/) (2021)
- [Dual Algorithmic Reasoning](https://mlsanity.com/paper/2302.04496/) (2023)
- [GraphFM: A generalist graph transformer that learns transferable representations across diverse domains](https://mlsanity.com/paper/2407.11907/) (2024)
- [Reasoning-Modulated Representations](https://mlsanity.com/paper/2107.08881/) (2021)
- [Continuous Neural Algorithmic Planners](https://mlsanity.com/paper/2211.15839/) (2022)

## Abstract (arXiv)

Neural networks excel at processing unstructured data but often fail to generalise out-of-distribution, whereas classical algorithms guarantee correctness but lack flexibility. We explore whether pretraining Graph Neural Networks (GNNs) on classical algorithms can improve their performance on molecular property prediction tasks from the Open Graph Benchmark: ogbg-molhiv (HIV inhibition) and ogbg-molclintox (clinical toxicity). GNNs trained on 24 classical algorithms from the CLRS Algorithmic Reasoning Benchmark are used to initialise and freeze selected layers of a second GNN for molecular prediction. Compared to a randomly initialised baseline, the pretrained models achieve consistent wins or ties, with the Segments Intersect algorithm pretraining yielding a 6% absolute gain on ogbg-molhiv and Dijkstra pretraining achieving a 3% gain on ogbg-molclintox. These results demonstrate embedding classical algorithmic priors into GNNs provides useful inductive biases, boosting performance on complex, real-world graph data.