提出树为中心的图生成方法，高效还原脑连接组结构与权重。
GraphTreeGen: Subtree-Centric Approach to Efficient and Supervised Graph Generation
- 将脑图分解为熵引导的多跳子树，用共享GCN编码局部结构。
- 双分支解码器联合预测边存在性与权重，重建精度更高。
- 内存占用低，适合超分辨率与跨模态合成，适用于神经影像研究。
脑连接组作为神经连接的图表示，在理解脑组织结构中至关重要，但获取成本高且耗时，推动了生成模型的发展。现有图生成模型存在四大局限：(i) 将整图压缩为单一潜在编码（如VGAE）会模糊精细局部模式；(ii) 依赖丰富节点属性，而此类信息在连接组中罕见，影响重建质量；(iii) 边中心模型强调拓扑结构，却忽视准确的边权重预测，损害定量保真度；(iv) 计算复杂设计（如边条件卷积）内存开销大，限制可扩展性。本文提出GraphTreeGen（GTG），一种以子树为中心的高效、精准连接组生成框架。GTG将每个连接组分解为熵引导的k-hop子树，捕获关键局部结构，并通过共享图卷积网络（GCN）编码。双分支消息传递层融合子树嵌入与全局节点特征，双分支解码器联合预测边存在性与权重，以重构邻接矩阵。实验表明，GTG在自监督任务中优于当前最优基线，在有监督设置中仍具竞争力，实现更高结构保真度与更精确权重预测，且内存消耗显著降低。其模块化设计支持拓展至连接组超分辨率与跨模态合成。代码已开源：https://github.com/basiralab/GTG/
原文摘要 · Abstract (English)
Brain connectomes, representing neural connectivity as graphs, are crucial for understanding brain organization but costly and time-consuming to acquire, motivating generative approaches. Recent advances in graph generative modeling offer a data-driven alternative, enabling synthetic connectome generation and reducing dependence on large neuroimaging datasets. However, current models face key limitations: (i) compressing the whole graph into a single latent code (e.g., VGAEs) blurs fine-grained local motifs; (ii) relying on rich node attributes rarely available in connectomes reduces reconstruction quality; (iii) edge-centric models emphasize topology but overlook accurate edge-weight prediction, harming quantitative fidelity; and (iv) computationally expensive designs (e.g., edge-conditioned convolutions) impose high memory demands, limiting scalability. We propose GraphTreeGen (GTG), a subtree-centric generative framework for efficient, accurate connectome synthesis. GTG decomposes each connectome into entropy-guided k-hop trees capturing informative local structure, encoded by a shared GCN. A bipartite message-passing layer fuses subtree embeddings with global node features, while a dual-branch decoder jointly predicts edge existence and weights to reconstruct the adjacency matrix. GTG outperforms state-of-the-art baselines in self-supervised tasks and remains competitive in supervised settings, delivering higher structural fidelity and more precise weights with far less memory. Its modular design enables extensions to connectome super-resolution and cross-modality synthesis. Code: https://github.com/basiralab/GTG/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。