Fast Clifford Neural Layers
This work provides a performance improvement for researchers and practitioners using Clifford algebra in neural networks for PDE modeling, but it is incremental as it focuses on optimization rather than new methods.
The paper tackled the problem of slow inference in Clifford neural layers for PDE modeling by optimizing 2/3D Clifford convolutional and multivector activation layers for CPU performance, resulting in a 30% speedup over standard PyTorch in large-scale scenarios.
Clifford Neural Layers improve PDE modeling by introducing Clifford Algebra into neural networks. In this project we focus on optimizing the inference of 2/3D Clifford convolutional layers and multivector activation layers for one core CPU performance. Overall, by testing on a real network block involving Clifford convolutional layers and multivector activation layers, we observe that our implementation is 30% faster than standard PyTorch implementation in relatively large data + network size (>L2 cache). We open source our code base at https://github.com/egretwAlker/c-opt-clifford-layers