Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks.

Moshe Eliasof, Benjamin J. Bodner, Eran Treister

Research output: Working paper/PreprintPreprint

Abstract

Graph Convolutional Networks (GCNs) are widely
used in a variety of applications, and can be seen as an unstructured version of standard Convolutional Neural Networks (CNNs). As in CNNs, the computational cost of GCNs for large
input graphs (such as large point clouds or meshes) can be high and inhibit the use of these networks, especially in environments with low computational resources. To ease these costs, quantization can be applied to GCNs. However, aggressive quantization of the feature maps can lead to a significant degradation in\ performance. On a different note, Haar wavelet transforms are known to be one of the most effective and efficient approaches
to compress signals. Therefore, instead of applying aggressive quantization to feature maps, we propose to utilize Haar wavelet
compression and light quantization to reduce the computations and the bandwidth involved with the network. We demonstrate that this approach surpasses aggressive feature quantization by a significant margin, for a variety of problems ranging from node classification to point cloud classification and part and semantic segmentation.
Original languageEnglish GB
Volumeabs/2110.04824
StatePublished - 2021

Publication series

NameCoRR

Fingerprint

Dive into the research topics of 'Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks.'. Together they form a unique fingerprint.

Cite this