Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

2021/09/14 by Samuel Cahyawijaya, Cahyawijaya, Samuel, Genta Indra Winata +11
Computer Science · #Advanced Neural Network Applications #Algorithms and Data Compression #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Speech Recognition and Synthesis #cs.AI #cs.LG

paper · pdf · doi:10.48550/arxiv.2109.06762

openalex publication_date 2021/09/14 · arxiv created 2021/10/09 · arxiv updated 2021/10/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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/.

Citations

• Quantifying the Carbon Emissions of Machine Learning
• Measuring the Algorithmic Efficiency of Neural Networks
• Language Models are Few-Shot Learners
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better
• Green AI

Related

• Fast and Low-Memory Deep Neural Networks Using Binary Matrix Factorization
• NeuralMatrix: Compute the Entire Neural Networks with Linear Matrix Operations for Efficient Inference
• Neural Network Matrix Factorization
• Fixed-point Factorized Networks
• Accelerating Neural Network Training: A Brief Review