# InfraredGP: Efficient Graph Partitioning via Spectral Graph Neural Networks with Negative Corrections

arXiv: https://arxiv.org/abs/2508.19737 · HTML: https://mlsanity.com/paper/2508.19737/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 14 of 14)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Beyond Low-frequency Information in Graph Convolutional Networks](https://mlsanity.com/paper/2101.00797/) (2021)
- [Cooperative Game Theory Approaches for Network Partitioning](https://mlsanity.com/paper/1707.03587/) (2017)
- [AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter](https://mlsanity.com/paper/2104.12840/) (2021)
- [Efficient Monte Carlo and greedy heuristic for the inference of stochastic block models](https://mlsanity.com/paper/1310.4378/) (2013)
- [20 years of network community detection](https://mlsanity.com/paper/2208.00111/) (2022)
- [Temporal Link Prediction: A Unified Framework, Taxonomy, and Review](https://mlsanity.com/paper/2210.08765/) (2022)
- [Streaming Graph Challenge: Stochastic Block Partition](https://mlsanity.com/paper/1708.07883/) (2017)
- [Preconditioned Spectral Clustering for Stochastic Block Partition Streaming Graph Challenge](https://mlsanity.com/paper/1708.07481/) (2017)
- [Community detection using fast low-cardinality semidefinite programming](https://mlsanity.com/paper/2012.02676/) (2020)
- [RaftGP: Random Fast Graph Partitioning](https://mlsanity.com/paper/2312.01560/) (2023)
- [IRWE: Inductive Random Walk for Joint Inference of Identity and Position Network Embedding](https://mlsanity.com/paper/2401.00651/) (2024)
- [Towards Faster Graph Partitioning via Pre-training and Inductive Inference](https://mlsanity.com/paper/2409.00670/) (2024)
- [Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation](https://mlsanity.com/paper/2505.20992/) (2025)

## Built on by (most cited first, 1 of 1)

- [Topology-induced Operators Reveal Complementary Graph Representations without Training](https://mlsanity.com/paper/2609.08152/) (2026)

## Abstract (arXiv)

Graph partitioning (GP), a.k.a. community detection, is a classic problem that divides nodes of a graph into densely-connected blocks. From a perspective of graph signal processing, we find that graph Laplacian with a negative correction can derive graph frequencies beyond the conventional range [0, 2]. To explore whether the low-frequency information beyond this range can encode more informative properties about community structures, we propose InfraredGP. It (romannumeral1) adopts a spectral GNN as its backbone combined with low-pass filters and a negative correction mechanism, (romannumeral2) only feeds random inputs to this backbone, (romannumeral3) derives graph embeddings via one feed-forward propagation (FFP) without any training, and (romannumeral4) obtains feasible GP results by feeding the derived embeddings to BIRCH. Surprisingly, our experiments demonstrate that based solely on the negative correction mechanism that amplifies low-frequency information beyond [0, 2], InfraredGP can derive distinguishable embeddings for some standard clustering modules (e.g., BIRCH) and obtain high-quality results for GP without any training. Following the IEEE HPEC Graph Challenge benchmark, we evaluate InfraredGP for both static and streaming GP, where InfraredGP can achieve much better efficiency (e.g., 16x-23x faster) and competitive quality over various baselines. We have made our code public at https://github.com/KuroginQin/InfraredGP