-
Geometric Scattering Attention Networks
Geometric scattering has recently gained recognition in graph representa...
read it
-
Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
Graph convolutional networks (GCNs) have shown promising results in proc...
read it
-
Understanding Graph Neural Networks with Asymmetric Geometric Scattering Transforms
The scattering transform is a multilayered wavelet-based deep learning a...
read it
-
Graph Autoencoders with Deconvolutional Networks
Recent studies have indicated that Graph Convolutional Networks (GCNs) a...
read it
-
Dynamic Self-training Framework for Graph Convolutional Networks
Graph neural networks (GNN) such as GCN, GAT, MoNet have achieved state-...
read it
-
Efficient and Stable Graph Scattering Transforms via Pruning
Graph convolutional networks (GCNs) have well-documented performance in ...
read it
-
Parzen Filters for Spectral Decomposition of Signals
We propose a novel family of band-pass filters for efficient spectral de...
read it
Data-Driven Learning of Geometric Scattering Networks
Graph neural networks (GNNs) in general, and graph convolutional networks (GCN) in particular, often rely on low-pass graph filters to incorporate geometric information in the form of local smoothness over neighboring nodes. While this approach performs well on a surprising number of standard benchmarks, the efficacy of such models does not translate consistently to more complex domains, such as graph data in the biochemistry domain. We argue that these more complex domains require priors that encourage learning of band-pass and high-pass features rather than oversmoothed signals of standard GCN architectures. Here, we propose an alternative GNN architecture, based on a relaxation of recently proposed geometric scattering transforms, which consists of a cascade of graph wavelet filters. Our learned geometric scattering (LEGS) architecture adaptively tunes these wavelets and their scales to encourage band-pass features to emerge in learned representations. This results in a simplified GNN with significantly fewer learned parameters compared to competing methods. We demonstrate the predictive performance of our method on several biochemistry graph classification benchmarks, as well as the descriptive quality of its learned features in biochemical graph data exploration tasks. Our results show that the proposed LEGS network matches or outperforms popular GNNs, as well as the original geometric scattering construction, while also retaining certain mathematical properties of its handcrafted (nonlearned) design.
READ FULL TEXT
Comments
There are no comments yet.