English
Related papers

Related papers: Accelerating Transformer Pre-training with 2:4 Spa…

200 papers

Training on edge devices poses several challenges as these devices are generally resource-constrained, especially in terms of power. State-of-the-art techniques at the device level reduce the GPU frequency to enforce power constraints,…

Machine Learning · Computer Science 2025-02-26 Mohamed Aboelenien Ahmed , Kilian Pfeiffer , Heba Khdr , Osama Abboud , Ramin Khalili , Jörg Henkel

Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed. Actually, an important observation shows…

Machine Learning · Computer Science 2020-07-21 Xucheng Ye , Pengcheng Dai , Junyu Luo , Xin Guo , Yingjie Qi , Jianlei Yang , Yiran Chen

Nowadays, increasingly larger Deep Neural Networks (DNNs) are being developed, trained, and utilized. These networks require significant computational resources, putting a strain on both advanced and limited devices. Our solution is to…

This paper studies structured sparse training of CNNs with a gradual pruning technique that leads to fixed, sparse weight matrices after a set number of epochs. We simplify the structure of the enforced sparsity so that it reduces overhead…

Machine Learning · Computer Science 2020-01-14 Noah Gamboa , Kais Kudrolli , Anand Dhoot , Ardavan Pedram

Large and sparse feed-forward layers (S-FFN) such as Mixture-of-Experts (MoE) have proven effective in scaling up Transformers model size for \textit{pretraining} large language models. By only activating part of the FFN parameters…

Computation and Language · Computer Science 2023-10-25 Zeyu Leo Liu , Tim Dettmers , Xi Victoria Lin , Veselin Stoyanov , Xian Li

We present a new training methodology for transformers using a multilevel, layer-parallel approach. Through a neural ODE formulation of transformers, our application of a multilevel parallel-in-time algorithm for the forward and…

Machine Learning · Computer Science 2026-01-27 Shuai Jiang , Marc Salvadó-Benasco , Eric C. Cyr , Alena Kopaničáková , Rolf Krause , Jacob B. Schroder

Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value. The current work focuses on fine-grained pruning, which uses…

Machine Learning · Computer Science 2022-09-28 Xiatao Kang , Ping Li , Jiayi Yao , Chengxi Li

We propose a mask pretraining method for Graph Neural Networks (GNNs) to improve their performance on fitting potential energy surfaces, particularly in water systems. GNNs are pretrained by recovering spatial information related to…

Machine Learning · Computer Science 2024-06-21 Zehua Zhang , Zijie Li , Amir Barati Farimani

Early stopping monitors global validation loss and halts all parameter updates simultaneously, which is computationally costly for large transformers due to the extended time required for validation inference. We propose \textit{GradES}, a…

Machine Learning · Computer Science 2025-10-20 Qifu Wen , Xi Zeng , Zihan Zhou , Shuaijun Liu , Mehdi Hosseinzadeh , Ningxin Su , Reza Rawassizadeh

Pruning of deep neural networks has been an effective technique for reducing model size while preserving most of the performance of dense networks, crucial for deploying models on memory and power-constrained devices. While recent sparse…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Andy Li , Aiden Durrant , Milan Markovic , Tianjin Huang , Souvik Kundu , Tianlong Chen , Lu Yin , Georgios Leontidis

Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network performance. One…

Machine Learning · Computer Science 2019-12-25 Simon Alford , Ryan Robinett , Lauren Milechin , Jeremy Kepner

Long training times of deep neural networks are a bottleneck in machine learning research. The major impediment to fast training is the quadratic growth of both memory and compute requirements of dense and convolutional layers with respect…

Machine Learning · Computer Science 2020-02-20 Mihailo Isakov , Michel A. Kinsy

While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data. In this work we introduce a suite of tools that exploit sparsity in…

Computer Vision and Pattern Recognition · Computer Science 2020-03-13 Timo Hackel , Mikhail Usvyatsov , Silvano Galliani , Jan D. Wegner , Konrad Schindler

Transformers consist of diverse building blocks, such as embedding layers, normalization layers, self-attention mechanisms, and point-wise feedforward networks. Thus, understanding the differences and interactions among these blocks is…

Machine Learning · Computer Science 2025-06-16 Jinbo Wang , Mingze Wang , Zhanpeng Zhou , Junchi Yan , Weinan E , Lei Wu

During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of the model's parameters during training,…

Machine Learning · Computer Science 2021-11-19 Yi-Lin Sung , Varun Nair , Colin Raffel

Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features. As such, achieving high-performance execution for GNNs becomes crucially important. Prior works have proposed to explore the…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-30 Yangjie Zhou , Yaoxu Song , Jingwen Leng , Zihan Liu , Weihao Cui , Zhendong Zhang , Cong Guo , Quan Chen , Li Li , Minyi Guo

Scaling transformers has led to significant breakthroughs in many domains, leading to a paradigm in which larger versions of existing models are trained and released on a periodic basis. New instances of such models are typically trained…

Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Chuanjian Liu , Yunhe Wang , Kai Han , Chunjing Xu , Chang Xu

In natural language processing (NLP), the "Transformer" architecture was proposed as the first transduction model replying entirely on self-attention mechanisms without using sequence-aligned recurrent neural networks (RNNs) or convolution,…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-07-20 Bingbing Li , Santosh Pandey , Haowen Fang , Yanjun Lyv , Ji Li , Jieyang Chen , Mimi Xie , Lipeng Wan , Hang Liu , Caiwen Ding

We present flattened convolutional neural networks that are designed for fast feedforward execution. The redundancy of the parameters, especially weights of the convolutional filters in convolutional neural networks has been extensively…

Neural and Evolutionary Computing · Computer Science 2015-11-23 Jonghoon Jin , Aysegul Dundar , Eugenio Culurciello
‹ Prev 1 3 4 5 6 7 10 Next ›