# Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning

arXiv: https://arxiv.org/abs/2204.04510 · HTML: https://mlsanity.com/paper/2204.04510/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2022.

## Built on by (most cited first, 4 of 4)

- [Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention](https://mlsanity.com/paper/2410.06746/) (2024)
- [Stochastic Subgraph Neighborhood Pooling for Subgraph Classification](https://mlsanity.com/paper/2304.08556/) (2023)
- [Generalizing Weisfeiler-Lehman Kernels to Subgraphs](https://mlsanity.com/paper/2412.02181/) (2024)
- [GoMS: Graph of Molecule Substructure Network for Molecule Property Prediction](https://mlsanity.com/paper/2512.12489/) (2025)

## Abstract (arXiv)

Subgraph representation learning has emerged as an important problem, but it is by default approached with specialized graph neural networks on a large global graph. These models demand extensive memory and computational resources but challenge modeling hierarchical structures of subgraphs. In this paper, we propose Subgraph-To-Node (S2N) translation, a novel formulation for learning representations of subgraphs. Specifically, given a set of subgraphs in the global graph, we construct a new graph by coarsely transforming subgraphs into nodes. Demonstrating both theoretical and empirical evidence, S2N not only significantly reduces memory and computational costs compared to state-of-the-art models but also outperforms them by capturing both local and global structures of the subgraph. By leveraging graph coarsening methods, our method outperforms baselines even in a data-scarce setting with insufficient subgraphs. Our experiments on eight benchmarks demonstrate that fined-tuned models with S2N translation can process 183 -- 711 times more subgraph samples than state-of-the-art models at a better or similar performance level.