Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

Abstract

While the recent advances in deep neural networks (DNN) bring remarkable success, the computational cost also increases considerably. In this paper, we introduce Greenformer, a toolkit to accelerate the computation of neural networks through matrix factorization while maintaining performance. Greenformer can be easily applied with a single line of code to any DNN model. Our experimental results show that Greenformer is effective for a wide range of scenarios. We provide the showcase of Greenformer at https://samuelcahyawijaya.github.io/greenformer-demo/.

References in corpus (6)

• Language Models are Few-Shot Learners
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better
• Quantifying the Carbon Emissions of Machine Learning
• Carbon Emissions and Large Neural Network Training
• Measuring the Algorithmic Efficiency of Neural Networks
• On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compression

Cited by in corpus (2)

• Few-Shot Bot: Prompt-Based Learning for Dialogue Systems
• Harnessing Orthogonality to Train Low-Rank Neural Networks