DeepAI AI Chat
Log In Sign Up

Structured Pattern Pruning Using Regularization

by   Dongjun Park, et al.

Iterative Magnitude Pruning (IMP) is a network pruning method that repeats the process of removing weights with the least magnitudes and retraining the model. When visualizing the weight matrices of language models pruned by IMP, previous research has shown that a structured pattern emerges, wherein the resulting surviving weights tend to prominently cluster in a select few rows and columns of the matrix. Though the need for further research in utilizing these structured patterns for potential performance gains has previously been indicated, it has yet to be thoroughly studied. We propose SPUR (Structured Pattern pruning Using Regularization), a novel pruning mechanism that preemptively induces structured patterns in compression by adding a regularization term to the objective function in the IMP. Our results show that SPUR can significantly preserve model performance under high sparsity settings regardless of the language or the task. Our contributions are as follows: (i) We propose SPUR, a network pruning mechanism that improves upon IMP regardless of the language or the task. (ii) We are the first to empirically verify the efficacy of "structured patterns" observed previously in pruning research. (iii) SPUR is a resource-efficient mechanism in that it does not require significant additional computations.


page 1

page 2

page 3

page 4


Knowledge-preserving Pruning for Pre-trained Language Models without Retraining

Given a pre-trained language model, how can we efficiently compress it w...

MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models

Pruning is an effective method to reduce the memory footprint and comput...

Joint Shortening and Puncturing Optimization for Structured LDPC Codes

The demand for flexible broadband wireless services makes the pruning te...

Structured Pruning for Efficient ConvNets via Incremental Regularization

Parameter pruning is a promising approach for CNN compression and accele...

What Matters In The Structured Pruning of Generative Language Models?

Auto-regressive large language models such as GPT-3 require enormous com...

Selective Brain Damage: Measuring the Disparate Impact of Model Pruning

Neural network pruning techniques have demonstrated it is possible to re...

Regularization-based Pruning of Irrelevant Weights in Deep Neural Architectures

Deep neural networks exploiting millions of parameters are nowadays the ...