# Graph Neural Networks for IceCube Signal Classification

arXiv: https://arxiv.org/abs/1809.06166 · HTML: https://mlsanity.com/paper/1809.06166/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 24 of 24)

- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Combinatorial Optimization with Physics-Inspired Graph Neural Networks](https://mlsanity.com/paper/2107.01188/) (2021)
- [Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training](https://mlsanity.com/paper/2104.09376/) (2021)
- [Machine Learning in the Search for New Fundamental Physics](https://mlsanity.com/paper/2112.03769/) (2021)
- [Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy](https://mlsanity.com/paper/2211.03796/) (2022)
- [Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings](https://mlsanity.com/paper/2201.13410/) (2022)
- [A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory](https://mlsanity.com/paper/2101.11589/) (2021)
- [Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube](https://mlsanity.com/paper/2209.03042/) (2022)
- [Learning Adaptive Neighborhoods for Graph Neural Networks](https://mlsanity.com/paper/2307.09065/) (2023)
- [Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications](https://mlsanity.com/paper/2204.00323/) (2022)
- [Enhanced Graph Neural Networks with Ego-Centric Spectral Subgraph Embeddings Augmentation](https://mlsanity.com/paper/2310.12169/) (2023)
- [Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array](https://mlsanity.com/paper/2103.06054/) (2021)
- [Physics Community Needs, Tools, and Resources for Machine Learning](https://mlsanity.com/paper/2203.16255/) (2022)
- [Graph Neural Network for Neutrino Physics Event Reconstruction](https://mlsanity.com/paper/2403.11872/) (2024)
- [Tackling the muon identification in water Cherenkov detectors problem for the future Southern Wide-field Gamma-ray Observatory by means of Machine Learning](https://mlsanity.com/paper/2101.11924/) (2021)
- [Deal: Distributed End-to-End GNN Inference for All Nodes](https://mlsanity.com/paper/2503.02960/) (2025)
- [Data driven design of optical resonators](https://mlsanity.com/paper/2202.03578/) (2021)
- [Towards Real-Time Temporal Graph Learning](https://mlsanity.com/paper/2210.04114/) (2022)
- [Rejecting noise in Baikal-GVD data with neural networks](https://mlsanity.com/paper/2210.04653/) (2022)
- [Enhancing Events in Neutrino Telescopes through Deep Learning-Driven Super-Resolution](https://mlsanity.com/paper/2408.08474/) (2024)
- [Learning Efficient Representations of Neutrino Telescope Events](https://mlsanity.com/paper/2410.13148/) (2024)
- [Tagging fully hadronic exotic decays of the vectorlike B quark using a graph neural network](https://mlsanity.com/paper/2505.07769/) (2025)
- [NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes](https://mlsanity.com/paper/2511.13111/) (2025)
- [Neutrino Fingerprints: Image-Based Encodings of IceCube Events for CNN Direction Reconstruction](https://mlsanity.com/paper/2606.02788/) (2026)

## Abstract (arXiv)

Tasks involving the analysis of geometric (graph- and manifold-structured) data have recently gained prominence in the machine learning community, giving birth to a rapidly developing field of geometric deep learning. In this work, we leverage graph neural networks to improve signal detection in the IceCube neutrino observatory. The IceCube detector array is modeled as a graph, where vertices are sensors and edges are a learned function of the sensors' spatial coordinates. As only a subset of IceCube's sensors is active during a given observation, we note the adaptive nature of our GNN, wherein computation is restricted to the input signal support. We demonstrate the effectiveness of our GNN architecture on a task classifying IceCube events, where it outperforms both a traditional physics-based method as well as classical 3D convolution neural networks.