Geometric Scattering for Graph Data Analysis
arXiv:1810.03068
Abstract
We explore the generalization of scattering transforms from traditional (e.g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis. In particular, we focus on the capacity of these features to retain informative variability and relations in the data (e.g., between individual graphs, or in aggregate), while relating our construction to previous theoretical results that establish the stability of similar transforms to families of graph deformations. We demonstrate the application the our geometric scattering features in graph classification of social network data, and in data exploration of biochemistry data.
References in corpus (13)
- Geometric deep learning: going beyond Euclidean data
- How transferable are features in deep neural networks?
- Deep Scattering Spectrum
- graph2vec: Learning Distributed Representations of Graphs
- Rigid-Motion Scattering for Texture Classification
- On Valid Optimal Assignment Kernels and Applications to Graph Classification
- Graph Capsule Convolutional Neural Networks
- Covariant Compositional Networks For Learning Graphs
- Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
- Audio Texture Synthesis with Scattering Moments
- Wavelet Scattering on the Pitch Spiral
- Steerable Wavelet Scattering for 3D Atomic Systems with Application to Li-Si Energy Prediction
- Geometric Scattering on Manifolds