Green DetNet: Computation and Memory efficient DetNet using Smart Compression and Training
This work addresses efficiency issues in wireless communication systems by providing a more resource-friendly solution for MIMO detection, though it is incremental as it builds on existing DetNet methods.
The paper tackles the problem of high computational and memory requirements in Deep Neural Network-based MIMO detection algorithms like DetNet by introducing an incremental training framework with structured regularization, achieving a 98.9% reduction in memory and 81.63% reduction in FLOPs without compromising BER performance.
This paper introduces an incremental training framework for compressing popular Deep Neural Network (DNN) based unfolded multiple-input-multiple-output (MIMO) detection algorithms like DetNet. The idea of incremental training is explored to select the optimal depth while training. To reduce the computation requirements or the number of FLoating point OPerations (FLOPs) and enforce sparsity in weights, the concept of structured regularization is explored using group LASSO and sparse group LASSO. Our methods lead to an astounding $98.9\%$ reduction in memory requirement and $81.63\%$ reduction in FLOPs when compared with DetNet without compromising on BER performance.