几何散射网络的数据驱动学习
Data-Driven Learning of Geometric Scattering Networks
摘要：
我们提出了一个新的图神经网络（GNN）模块，最近提出的几何散射变换，其中包括级联的图形小波滤波器的松弛的基础上。我们的可学习几何散射（LEGS）模块使自适应调整的小波，鼓励带通功能出现在学习表示。与许多流行的GNN相比，将我们的LEGS模块并入GNN可以学习更长范围的图关系，这些GNN通常依赖于通过邻居之间的平滑度或相似性来编码图结构。此外，它的小波先验导致简化的架构，与竞争的GNN相比，学习的参数显著减少。我们展示了基于LEGS的网络在图分类基准上的预测性能，以及它们在生化图数据探索任务中学习到的特征的描述性质量。
英文摘要：
We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist of a cascade of graph wavelet filters. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations. The incorporation of our LEGS-module in GNNs enables the learning of longer-range graph relations compared to many popular GNNs, which often rely on encoding graph structure via smoothness or similarity between neighbors. Further, its wavelet priors result in simplified architectures with significantly fewer learned parameters compared to competing GNNs. We demonstrate the predictive performance of LEGS-based networks on graph classification benchmarks, as well as the descriptive quality of their learned features in biochemical graph data exploration tasks.
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。
