A Dynamic Reduction Network for Point Clouds

Abstract

Classifying whole images is a classic problem in machine learning, and graph neural networks are a powerful methodology to learn highly irregular geometries. It is often the case that certain parts of a point cloud are more important than others when determining overall classification. On graph structures this started by pooling information at the end of convolutional filters, and has evolved to a variety of staged pooling techniques on static graphs. In this paper, a dynamic graph formulation of pooling is introduced that removes the need for predetermined graph structure. It achieves this by dynamically learning the most important relationships between data via an intermediate clustering. The network architecture yields interesting results considering representation size and efficiency. It also adapts easily to a large number of tasks from image classification to energy regression in high energy particle physics.

4 pages, 2 figures, to be updated

References in corpus (9)

• Decoupled Weight Decay Regularization
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Fast Graph Representation Learning with PyTorch Geometric
• Self-Attention Graph Pooling
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Edge Contraction Pooling for Graph Neural Networks
• Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
• Software compensation in Particle Flow reconstruction

Cited by in corpus (2)

• Applications and Techniques for Fast Machine Learning in Science
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays