图神经网络深度与广度的解耦
Decoupling the Depth and Scope of Graph Neural Networks
摘要：
最先进的图神经网络（GNN）在图和模型大小方面具有有限的可扩展性。在大型图上，增加模型深度通常意味着范围的指数扩展（即，感受野）。除了几个层次之外，还出现了两个根本性的挑战：1。由于过度平滑而降低的表现力，以及2.由于邻域爆炸而导致的昂贵计算。我们提出了一个设计原则来解耦GNN的深度和范围-生成目标实体的表示（即，节点或边），我们首先提取一个局部化的子图作为有界大小的范围，然后在子图的顶部应用任意深度的GNN。一个正确提取的子图由少量的关键邻居组成，同时排除不相关的。GNN，无论它有多深，都将局部邻域平滑为信息表示，而不是将全局图过度平滑为“白噪声”。理论上，解耦从图信号处理（GCN），函数逼近（GraphSAGE）和拓扑学习（GIN）的角度提高了GNN的表达能力。从经验上看，在七个图（最多110 M个节点）和六个主干GNN架构上，我们的设计实现了显着的准确性提高，计算量和硬件成本降低了几个数量级。
英文摘要：
State-of-the-art Graph Neural Networks (GNNs) have limited scalability with respect to the graph and model sizes. On large graphs, increasing the model depth often means exponential expansion of the scope (i.e., receptive field). Beyond just a few layers, two fundamental challenges emerge: 1. degraded expressivity due to oversmoothing, and 2. expensive computation due to neighborhood explosion. We propose a design principle to decouple the depth and scope of GNNs -- to generate representation of a target entity (i.e., a node or an edge), we first extract a localized subgraph as the bounded-size scope, and then apply a GNN of arbitrary depth on top of the subgraph. A properly extracted subgraph consists of a small number of critical neighbors, while excluding irrelevant ones. The GNN, no matter how deep it is, smooths the local neighborhood into informative representation rather than oversmoothing the global graph into "white noise". Theoretically, decoupling improves the GNN expressive power from the perspectives of graph signal processing (GCN), function approximation (GraphSAGE) and topological learning (GIN). Empirically, on seven graphs (with up to 110M nodes) and six backbone GNN architectures, our design achieves significant accuracy improvement with orders of magnitude reduction in computation and hardware cost.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
