从节点连线图中精准恢复图结构，提升边关系建模能力
VisAdj: Learning Adjacency Matrices from Node-Link Images
- 用注意力稀疏采样动态选候选边对，提高召回率
- 通过线图变换器联合推理边，显式建模邻接边依赖
- 在合成图、道路网和船舶图像上显著优于基线方法
从节点连线图中学习邻接矩阵是从小样本视觉观测中恢复结构化图信息的基础问题。现有方法通常依赖固定的KNN启发式规则选择候选边，无法捕捉边之间的依赖关系。为此，我们提出VisAdj框架，实现拓扑感知的邻接预测。VisAdj引入注意力稀疏邻居采样器，自适应选择高召回率的候选节点对，并使用线图变换器进行联合边推理，将候选边视为标记，显式建模共现边间的依赖关系。在合成图、道路网络和船舶图像上的大量实验表明，VisAdj始终以明显优势超越现有基线方法。
原文摘要 · Abstract (English)
Learning adjacency matrices from node-link images is a fundamental problem for recovering structured graph information from visual observations. Existing methods typically rely on fixed KNN-based heuristics for candidate edge selection and fail to capture dependencies among edges. To overcome these limitations, we propose VisAdj, a new framework for topology-aware adjacency prediction. VisAdj introduces an attention-sparse neighbor sampler to adaptively select a high-recall set of candidate node pairs and performs joint edge inference using a line-graph transformer that treats candidate edges as tokens and explicitly models dependencies among incident edges. Extensive experiments on synthetic graphs, road networks, and vessel images demonstrate that VisAdj consistently outperforms existing baselines by clear margins.
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。