English
Related papers

Related papers: FastFold: Reducing AlphaFold Training Time from 11…

200 papers

Large deep learning models have achieved impressive performance across a range of applications. However, their large memory requirements, including parameter memory and activation memory, have become a significant challenge for their…

Performance · Computer Science 2024-07-10 Xuanlei Zhao , Shenggan Cheng , Guangyang Lu , Jiarui Fang , Haotian Zhou , Bin Jia , Ziming Liu , Yang You

Tensor decomposition is one of the well-known approaches to reduce the latency time and number of parameters of a pre-trained model. However, in this paper, we propose an approach to use tensor decomposition to reduce training time of…

Computer Vision and Pattern Recognition · Computer Science 2020-06-30 Mostafa Elhoushi , Ye Henry Tian , Zihao Chen , Farhan Shafiq , Joey Yiwei Li

Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Haiwen Diao , Bo Wan , Ying Zhang , Xu Jia , Huchuan Lu , Long Chen

While a big wave of artificial intelligence (AI) has propagated to the field of computational fluid dynamics (CFD) acceleration studies, recent research has highlighted that the development of AI techniques that reconciles the following…

Fluid Dynamics · Physics 2023-11-28 Joongoo Jeon , Juhyeong Lee , Ricardo Vinuesa , Sung Joong Kim

Federated Learning (FL) since proposed has been applied in many fields, such as credit assessment, medical, etc. Because of the difference in the network or computing resource, the clients may not update their gradients at the same time…

Machine Learning · Computer Science 2021-11-19 Zhicheng Zhou , Hailong Chen , Kunhua Li , Fei Hu , Bingjie Yan , Jieren Cheng , Xuyan Wei , Bernie Liu , Xiulai Li , Fuwen Chen , Yongji Sui

Training Convolutional Neural Networks (CNN) is a resource intensive task that requires specialized hardware for efficient computation. One of the most limiting bottleneck of CNN training is the memory cost associated with storing the…

Computer Vision and Pattern Recognition · Computer Science 2019-10-25 Tristan Hascoet , Quentin Febvre , Yasuo Ariki , Tetsuya Takiguchi

The computational requirements for training deep neural networks (DNNs) have grown to the point that it is now standard practice to parallelize training. Existing deep learning systems commonly use data or model parallelism, but…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-07-23 Zhihao Jia , Matei Zaharia , Alex Aiken

Molecular docking that predicts the bound structures of small molecules (ligands) to their protein targets, plays a vital role in drug discovery. However, existing docking methods often face limitations: they either overlook crucial…

Quantitative Methods · Quantitative Biology 2025-02-24 Zizhuo Zhang , Lijun Wu , Kaiyuan Gao , Jiangchao Yao , Tao Qin , Bo Han

Training large transformers is slow, but recent innovations on GPU architecture give us an advantage. NVIDIA Ampere GPUs can execute a fine-grained 2:4 sparse matrix multiplication twice as fast as its dense equivalent. In the light of this…

Machine Learning · Computer Science 2024-10-29 Yuezhou Hu , Kang Zhao , Weiyu Huang , Jianfei Chen , Jun Zhu

The whole computer hardware industry embraced multicores. For these machines, the extreme optimisation of sequential algorithms is no longer sufficient to squeeze the real machine power, which can be only exploited via thread-level…

Distributed, Parallel, and Cluster Computing · Computer Science 2010-09-21 Marco aldinucci , Salvatore Ruggieri , Massimo Torquati

In many retrieval systems the original high dimensional data (e.g., images) is mapped to a lower dimensional feature through a learned embedding model. The task of retrieving the most similar data from a gallery set to a given query data is…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Florian Jaeckle , Fartash Faghri , Ali Farhadi , Oncel Tuzel , Hadi Pouransari

AlphaFold 3 (AF3), the latest version of protein structure prediction software, goes beyond its predecessors by predicting protein-protein complexes. It could revolutionize drug discovery and protein engineering, marking a major step…

Biomolecules · Quantitative Biology 2024-06-07 JunJie Wee , Guo-Wei Wei

Data accesses between on- and off-chip memories account for a large fraction of overall energy consumption during inference with deep learning networks. We present APack, a simple and effective, lossless, off-chip memory compression…

Hardware Architecture · Computer Science 2022-01-24 Alberto Delmas Lascorz , Mostafa Mahmoud , Andreas Moshovos

Training large transformer models is one of the most important computational challenges of modern AI. In this paper, we show how to significantly accelerate training of large transformer models by reducing activation recomputation.…

Machine Learning · Computer Science 2022-05-12 Vijay Korthikanti , Jared Casper , Sangkug Lym , Lawrence McAfee , Michael Andersch , Mohammad Shoeybi , Bryan Catanzaro

Convolution models with long filters have demonstrated state-of-the-art reasoning abilities in many long-sequence tasks but lag behind the most optimized Transformers in wall-clock time. A major bottleneck is the Fast Fourier Transform…

Machine Learning · Computer Science 2023-11-13 Daniel Y. Fu , Hermann Kumbong , Eric Nguyen , Christopher Ré

The bio-inspired integrate-fire-reset mechanism of spiking neurons constitutes the foundation for efficient processing in Spiking Neural Networks (SNNs). Recent progress in large models demands that spiking neurons support highly parallel…

Neural and Evolutionary Computing · Computer Science 2026-02-03 Yanbin Huang , Man Yao , Yuqi Pan , Changze Lv , Siyuan Xu , Xiaoqing Zheng , Bo Xu , Guoqi Li

CIFAR-10 is among the most widely used datasets in machine learning, facilitating thousands of research projects per year. To accelerate research and reduce the cost of experiments, we introduce training methods for CIFAR-10 which reach 94%…

Machine Learning · Computer Science 2024-04-08 Keller Jordan

The scale of transformer model pre-training is constrained by the increasing computation and communication cost. Low-rank bottleneck architectures offer a promising solution to significantly reduce the training time and memory footprint…

Machine Learning · Computer Science 2026-05-13 Zhengyang Wang , Ziyue Liu , Ruijie Zhang , Avinash Maurya , Paul Hovland , Bogdan Nicolae , Franck Cappello , Zheng Zhang

We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering…

Federated learning (FL) has recently emerged as a compelling machine learning paradigm, prioritizing the protection of privacy for training data. The increasing demand to address issues such as ``the right to be forgotten'' and combat data…