大规模改进图神经网络：结合近似PageRank和CoreRank
Improving Graph Neural Networks at Scale: Combining Approximate PageRank and CoreRank
摘要：
图神经网络（GNNs）在许多图结构的学习任务中取得了巨大的成功。尽管如此，为了传播信息，GNN依赖于消息传递方案，当使用工业规模的图时，该方案可能变得过于昂贵。受PPRGo模型的启发，我们提出了CorePPR模型，这是一种可扩展的解决方案，利用近似个性化PageRank和CoreRank的可学习凸组合来扩散GNN中的多跳邻域信息。此外，我们还引入了一种动态机制来为特定节点选择最有影响力的邻居，从而减少了训练时间，同时保持了模型的性能。总的来说，我们证明了CorePPR优于PPRGo，特别是在选择最有影响力的节点与可扩展性特别相关的大型图形上。我们的代码可在https://github.com/arielramos97/CorePPR上公开获取。
英文摘要：
Graph Neural Networks (GNNs) have achieved great successes in many learning tasks performed on graph structures. Nonetheless, to propagate information GNNs rely on a message passing scheme which can become prohibitively expensive when working with industrial-scale graphs. Inspired by the PPRGo model, we propose the CorePPR model, a scalable solution that utilises a learnable convex combination of the approximate personalised PageRank and the CoreRank to diffuse multi-hop neighbourhood information in GNNs. Additionally, we incorporate a dynamic mechanism to select the most influential neighbours for a particular node which reduces training time while preserving the performance of the model. Overall, we demonstrate that CorePPR outperforms PPRGo, particularly on large graphs where selecting the most influential nodes is particularly relevant for scalability. Our code is publicly available at: https://github.com/arielramos97/CorePPR.
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。
