An Improved Image Compression Technique Using Huffman Coding and FFT

Patel, Rachit; Katiyar, Sapna; Arora, Khushboo

doi:10.1007/978-981-10-3433-6_7

Cited by 10 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…a) Parameter and gradient representation. : Discrete wavelet transform (DWT) and fast Fourier transform (FFT) have been used commonly for image compression [29]- [31]. For instance, JPEG2000 standard [32] uses the properties of DWT for compression.…”

Section: Metadata Compressionmentioning

confidence: 99%

Get More for Less in Decentralized Learning Systems

Dhasade,

Kermarrec,

Pires

et al. 2023

2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)

View full text Add to dashboard Cite

Decentralized learning (DL) systems have been gaining popularity because they avoid raw data sharing by communicating only model parameters, hence preserving data confidentiality. However, the large size of deep neural networks poses a significant challenge for decentralized training, since each node needs to exchange gigabytes of data, overloading the network. In this paper, we address this challenge with JWINS, a communication-efficient and fully decentralized learning system that shares only a subset of parameters through sparsification. JWINS uses wavelet transform to limit the information loss due to sparsification and a randomized communication cut-off that reduces communication usage without damaging the performance of trained models. We demonstrate empirically with 96 DL nodes on non-IID datasets that JWINS can achieve similar accuracies to full-sharing DL while sending up to 64% fewer bytes. Additionally, on low communication budgets, JWINS outperforms the state-of-the-art communication-efficient DL algorithm CHOCO-SGD by up to 4× in terms of network savings and time.

show abstract

Section: Metadata Compressionmentioning

confidence: 99%