DATA-DRIVEN LEARNING OF GEOMETRIC SCATTERING MODULES FOR GNNS.

DATA-DRIVEN LEARNING OF GEOMETRIC SCATTERING MODULES FOR GNNS.
复制标题

DOI:
10.1109/mlsp52302.2021.9596169
复制
发表时间:
2021-10
期刊:
IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing
影响因子:
--
通讯作者:
Wolf, Guy
Wolf, Guy
中科院分区:
其他
文献类型:
--
作者:
Tong, Alexander;Wenkel, Frederick;Macdonald, Kincaid;Krishnaswamy, Smita;Wolf, Guy

文献摘要

参考文献

被引文献

相似文献

我们提出了一种新的图神经网络(GNN)模块,它基于对近期提出的几何散射变换的松弛,该变换由一系列图小波滤波器组成。我们的可学习几何散射(LEGS)模块能够对小波进行自适应调整,以促使带通特征在学习到的表示中出现。与许多流行的图神经网络相比,将我们的LEGS模块整合到图神经网络中能够学习到更长距离的图关系,而许多流行的图神经网络通常依赖于通过邻居之间的平滑性或相似性对图结构进行编码。此外,与竞争的图神经网络相比,其小波先验导致了架构简化,学习到的参数显著减少。我们在图分类基准测试中展示了基于LEGS的网络的预测性能,以及在生化图数据探索任务中其学习到的特征的描述质量。
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.
DOI: 10.1016/j.acha.2006.04.004
发表时间: 2006-07-01
影响因子: 2.5
作者:
Coifman, Ronald R.;Maggioni, Mauro
通讯作者: Maggioni, Mauro
DOI: 10.1002/prot.25390
发表时间: 2018-03
期刊: Proteins
影响因子: 2.9
作者:
Ovchinnikov S;Park H;Kim DE;DiMaio F;Baker D
通讯作者: Baker D
DOI: 10.1002/prot.25049
发表时间: 2016-09-01
影响因子: 2.9
作者:
Modi, Vivek;Xu, Qifang;Dunbrack, Roland L., Jr.
通讯作者: Dunbrack, Roland L., Jr.
DOI: 10.1002/prot.25415
发表时间: 2018-03
期刊: Proteins
影响因子: 2.9
作者:
Moult J;Fidelis K;Kryshtafovych A;Schwede T;Tramontano A
通讯作者: Tramontano A
DOI: 10.1002/cpa.21413
发表时间: 2012-10-01
影响因子: 3
作者:
Mallat, Stephane
通讯作者: Mallat, Stephane