analiza aiqbench
G-NAC presents a novel unsupervised clustering framework using recurrent graph-neural cellular rules that achieves state-of-the-art performance on 73 benchmark tasks with linear scaling up to 100,000 nodes. The method's ability to transfer learned transition rules from smaller source graphs to large independent samples offers practical advantages for handling massive datasets without retraining. While the approach is grounded in graph neural networks, its core contribution lies in advancing machine learning methodologies for data partitioning rather than addressing quantum phenomena or policy issues.
G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation
arXiv:2609.24823v1 Announce Type: new Abstract: We introduce Graph Neural Automata Clustering (G-NAC), an unsupervised clustering method in which observations interact as cells on a fixed neighborhood graph. A shared recurrent graph-neural cellular rule evolves latent domain states through local interactions, which are converted into a rank-based spectral affinity for partitioning. Across 73 clustering tasks from 57 benchmark datasets, G-NAC achieved a mean adjusted Rand index (ARI) of 0.7951, comparable to Genie at 0.7941 and higher than the other evaluated baselines. Empirical training time and GPU memory scaled approximately linearly from 5,000 to 100,000 nodes. Learned transition rules also transferred from smaller source graphs to independent 100,000-node samples generated under matched conditions. These results demonstrate a recurrent graph-clustering formulation while identifying dependencies on graph quality, readout design, and source-target similarity.
Abstract:We introduce Graph Neural Automata Clustering (G-NAC), an unsupervised clustering method in which observations interact as cells on a fixed neighborhood graph. A shared recurrent graph-neural cellular rule evolves latent domain states through local interactions, which are converted into a rank-based spectral affinity for partitioning. Across 73 clustering tasks from 57 benchmark datasets, G-NAC achieved a mean adjusted Rand index (ARI) of 0.7951, comparable to Genie at 0.7941 and higher than the other evaluated baselines. Empirical training time and GPU memory scaled approximately linearly from 5,000 to 100,000 nodes. Learned transition rules also transferred from smaller source graphs to independent 100,000-node samples generated under matched conditions. These results demonstrate a recurrent graph-clustering formulation while identifying dependencies on graph quality, readout design, and source-target similarity.
Machine Learning (cs.LG); Signal Processing (eess.SP)
arXiv:2609.24823 [cs.LG]
(or arXiv:2609.24823v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.24823 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 221 cuvinte
Subiecte conexe
PIRAMID: Progress and Plans
LessWrong · 27 iul. 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
LatentFlow: Visual Analytics for Latent Space Analysis in Molecular Graph Neural Networks
arXiv · 27 iul. 2026
Outage Detection in Self-Healing Smart Grids Using Reinforcement Learning with Spectral Graph Neural Networks
arXiv · 9 iun. 2026