DeepAI AI Chat
Log In Sign Up

Parallel Blockwise Knowledge Distillation for Deep Neural Network Compression

by   Cody Blakeney, et al.

Deep neural networks (DNNs) have been extremely successful in solving many challenging AI tasks in natural language processing, speech recognition, and computer vision nowadays. However, DNNs are typically computation intensive, memory demanding, and power hungry, which significantly limits their usage on platforms with constrained resources. Therefore, a variety of compression techniques (e.g. quantization, pruning, and knowledge distillation) have been proposed to reduce the size and power consumption of DNNs. Blockwise knowledge distillation is one of the compression techniques that can effectively reduce the size of a highly complex DNN. However, it is not widely adopted due to its long training time. In this paper, we propose a novel parallel blockwise distillation algorithm to accelerate the distillation process of sophisticated DNNs. Our algorithm leverages local information to conduct independent blockwise distillation, utilizes depthwise separable layers as the efficient replacement block architecture, and properly addresses limiting factors (e.g. dependency, synchronization, and load balancing) that affect parallelism. The experimental results running on an AMD server with four Geforce RTX 2080Ti GPUs show that our algorithm can achieve 3x speedup plus 19 distillation, and 3.5x speedup plus 29 both with negligible accuracy loss. The speedup of ResNet distillation can be further improved to 3.87 when using four RTX6000 GPUs in a distributed cluster.


page 6

page 11

page 12


Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks

Quantization, knowledge distillation, and magnitude pruning are among th...

A Survey of Methods for Low-Power Deep Learning and Computer Vision

Deep neural networks (DNNs) are successful in many computer vision tasks...

Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy

Deep learning networks have achieved state-of-the-art accuracies on comp...

SlimNets: An Exploration of Deep Model Compression and Acceleration

Deep neural networks have achieved increasingly accurate results on a wi...

HAKD: Hardware Aware Knowledge Distillation

Despite recent developments, deploying deep neural networks on resource ...

Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation

Due to the prosperity of Artificial Intelligence (AI) techniques, more a...