LGAISep 14, 2021

Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

arXiv:2109.06762v38 citations
Originality Synthesis-oriented
AI Analysis

This provides a practical solution for researchers and practitioners needing efficient DNNs, though it appears incremental as a toolkit based on existing factorization methods.

The authors tackled the high computational cost of deep neural networks by introducing Greenformer, a toolkit that accelerates computation through matrix factorization while maintaining performance, achieving effectiveness across a wide range of scenarios.

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/.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes