G-NAC：通过涌现域形成的图神经自动机聚类
G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation
AI总结：
提出G-NAC，一种基于循环图神经细胞规则的无监督聚类方法，在73个任务中达到0.7951的平均ARI，并实现线性扩展与规则迁移。
AI中文摘要：
我们提出了图神经自动机聚类（G-NAC），一种无监督聚类方法，其中观测值作为固定邻接图上的细胞进行交互。一个共享的循环图神经细胞规则通过局部交互演化潜在域状态，这些状态被转换为基于秩的谱亲和力以进行划分。在来自57个基准数据集的73个聚类任务中，G-NAC实现了0.7951的平均调整兰德指数（ARI），与Genie的0.7941相当，并高于其他评估的基线。经验训练时间和GPU内存从5,000到100,000个节点近似线性扩展。学习到的转换规则也从较小的源图迁移到在匹配条件下生成的独立的100,000节点样本。这些结果展示了一种循环图聚类公式，同时识别了对图质量、读出设计和源-目标相似性的依赖。
英文摘要：
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.
