提出首个能区分有向与无向边的图神经网络，提升交通等场景的信号建模精度。
Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance
- 重新定义方向等变性，使模型能感知边的方向性。
- 引入方向不变性，用于建模无方向性的边信号，如管道直径。
- 新架构EIGN在流量模拟任务上误差降低23.5%，性能领先。
交通、土木工程和电气工程中的许多应用涉及边级信号。这些信号可分为固有有向（如管道中水流）和无向（如管道直径）。传统拓扑方法通过为每条边分配方向来表示有向信号，但无法处理无向信号，也无法判断边本身是否具有方向性。本文提出：(i) 修订方向等变性，实现对边方向敏感的建模；(ii) 引入方向不变性，以描述无方向信号；(iii) 构建EIGN架构，采用新型方向感知的边级图移位算子，理论上满足上述需求。EIGN是首个通用的边级信号图神经网络，能同时建模有向与无向信号，并区分边的类型。全面评估显示，其在边级任务中表现优异，例如在流量模拟任务中RMSE最高降低23.5%。
原文摘要 · Abstract (English)
Many applications in traffic, civil engineering, or electrical engineering revolve around edge-level signals. Such signals can be categorized as inherently directed, for example, the water flow in a pipe network, and undirected, like the diameter of a pipe. Topological methods model edge signals with inherent direction by representing them relative to a so-called orientation assigned to each edge. These approaches can neither model undirected edge signals nor distinguish if an edge itself is directed or undirected. We address these shortcomings by (i) revising the notion of orientation equivariance to enable edge direction-aware topological models, (ii) proposing orientation invariance as an additional requirement to describe signals without inherent direction, and (iii) developing EIGN, an architecture composed of novel direction-aware edge-level graph shift operators, that provably fulfills the aforementioned desiderata. It is the first general-purpose topological GNN for edge-level signals that can model directed and undirected signals while distinguishing between directed and undirected edges. A comprehensive evaluation shows that EIGN outperforms prior work in edge-level tasks, for example, improving in RMSE on flow simulation tasks by up to 23.5%.
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。