Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures
This addresses the issue of limited adoption of big NLP models in resource-constrained settings, though it is an incremental improvement on existing pruning methods.
The paper tackles the problem of compressing large Transformer models like BERT for resource-constrained environments by pruning redundant attention heads using an A* search algorithm, achieving up to 40% head removal with no accuracy loss.
Recent years have seen a growing adoption of Transformer models such as BERT in Natural Language Processing and even in Computer Vision. However, due to their size, there has been limited adoption of such models within resource-constrained computing environments. This paper proposes novel pruning algorithm to compress transformer models by eliminating redundant Attention Heads. We apply the A* search algorithm to obtain a pruned model with strict accuracy guarantees. Our results indicate that the method could eliminate as much as 40% of the attention heads in the BERT transformer model with no loss in accuracy.