Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks
This addresses computational bottlenecks for GCNs in resource-constrained environments, offering an incremental improvement over existing quantization methods.
The paper tackles the high computational cost of Graph Convolutional Networks (GCNs) for large graphs by proposing Haar wavelet compression with light quantization, which significantly outperforms aggressive feature quantization across tasks like node classification and point cloud segmentation.
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.