mlsanityData to 14 Oct 2026

Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

arXiv 2109.06762 ↗First posted 14 Sep 2021cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 12 of its 15 references that are in the map. First posted on arXiv 14 Sep 2021.

Builds on

12 of 15 references.

References · 12

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  4. 2019Green AIcited by 627
  5. 2021Carbon Emissions and Large Neural Network Trainingcited by 567
  6. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
  7. 2020Measuring the Algorithmic Efficiency of Neural Networkscited by 52
  8. 2019Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformercited by 47
  9. 2021Multimodal End-to-End Sparse Model for Emotion Recognitioncited by 40
  10. 2019On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compressioncited by 14
  11. 2017Factorization tricks for LSTM networkscited by 13
  12. 2021Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximationcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 2; 2024: 2.

7 papers.

  1. 2021Language Models are Few-shot Multilingual Learnerscited by 92
  2. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  3. 2022NusaCrowd: Open Source Initiative for Indonesian NLP Resourcescited by 38
  4. 2023Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecyclecited by 14
  5. 2024Harnessing Orthogonality to Train Low-Rank Neural Networkscited by 4
  6. 2023Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognitioncited by 1
  7. 2024AB-Training: A Communication-Efficient Approach for Distributed Low-Rank Learningcited by 0