G-NAC：让数据在图上像元胞自动机一样自发聚成域的无监督聚类
G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation
一种新的无监督聚类思路：数据点像元胞自动机一样自己"长"出类别，73 个聚类任务上追平了 Genie，还能迁移到大图。
arXiv 论文提出无监督聚类方法 G-NAC，把观测数据当作固定邻域图上的细胞，由共享的循环图神经元胞规则通过局部交互演化潜在域状态。在 57 个基准数据集的 73 个聚类任务上，G-NAC 平均调整兰德指数（ARI）达到 0.7951，与 Genie 的 0.7941 相当，高于其他受测基线。训练时间和 GPU 显存在 5,000 到 100,000 节点范围内近似线性增长，学到的转移规则还能迁移到独立的 100,000 节点样本。论文同时指出该方法依赖图质量、读出设计和源图与目标图的相似性。
G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation
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.