# AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks

arXiv: https://arxiv.org/abs/2412.12483 · HTML: https://mlsanity.com/paper/2412.12483/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 33 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 3 of 3)

- [LLM-SR: Scientific Equation Discovery via Programming with Large Language Models](https://mlsanity.com/paper/2404.18400/) (2024)
- [ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning](https://mlsanity.com/paper/2412.07507/) (2024)
- [DECN: Evolution Inspired Deep Convolution Network for Black-box Optimization](https://mlsanity.com/paper/2304.09599/) (2023)

## Built on by (most cited first, 5 of 5)

- [A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving](https://mlsanity.com/paper/2509.08269/) (2025)
- [Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search](https://mlsanity.com/paper/2608.03129/) (2026)
- [Community-Aware Temporal Walks: Parameter-Free Representation Learning on Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2501.11880/) (2025)
- [Convex--Concave Quadratic Spectral Filtering for Graph Neural Networks](https://mlsanity.com/paper/2606.24956/) (2026)
- [Not Just Oversmoothing: Detecting the Echo Chamber Effect in Graph Neural Networks](https://mlsanity.com/paper/2609.06521/) (2026)

## Abstract (arXiv)

In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and heterogeneous graphs-simultaneously. This challenge has led to the manual design of GNNs tailored to specific graph types, but these approaches are limited by the high cost of labor and the constraints of expert knowledge, which cannot keep up with the rapid growth of graph data. To overcome these challenges, we propose AutoSGNN, an automated framework for discovering propagation mechanisms in spectral GNNs. AutoSGNN unifies the search space for spectral GNNs by integrating large language models with evolutionary strategies to automatically generate architectures that adapt to various graph types. Extensive experiments on nine widely-used datasets, encompassing both homophilic and heterophilic graphs, demonstrate that AutoSGNN outperforms state-of-the-art spectral GNNs and graph neural architecture search methods in both performance and efficiency.