English
Related papers

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

200 papers

We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality while reducing decoding latency. Sparse Forcing is motivated by an empirical observation…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Boxun Xu , Yuming Du , Zichang Liu , Siyu Yang , Ziyang Jiang , Siqi Yan , Rajasi Saha , Albert Pumarola , Wenchen Wang , Peng Li

To accelerate inference of Convolutional Neural Networks (CNNs), various techniques have been proposed to reduce computation redundancy. Converting convolutional layers into frequency domain significantly reduces the computation complexity…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Yue Niu , Hanqing Zeng , Ajitesh Srivastava , Kartik Lakhotia , Rajgopal Kannan , Yanzhi Wang , Viktor Prasanna

Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called…

Computer Vision and Pattern Recognition · Computer Science 2018-06-18 Michele Pratusevich

Recent studies demonstrate that deep networks, even robustified by the state-of-the-art adversarial training (AT), still suffer from large robust generalization gaps, in addition to the much more expensive training costs than standard…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Tianlong Chen , Zhenyu Zhang , Pengjun Wang , Santosh Balachandra , Haoyu Ma , Zehao Wang , Zhangyang Wang

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression…

Machine Learning · Computer Science 2020-06-15 Tao Lin , Sebastian U. Stich , Luis Barba , Daniil Dmitriev , Martin Jaggi

Graph neural networks (GNNs) are emerging as a powerful technique for modeling graph structures. Due to the sparsity of real-world graph data, GNN performance is limited by extensive sparse matrix multiplication (SpMM) operations involved…

Machine Learning · Computer Science 2021-11-02 Shenghao Qiu , You Liang , Zheng Wang

The brain, as the source of inspiration for Artificial Neural Networks (ANN), is based on a sparse structure. This sparse structure helps the brain to consume less energy, learn easier and generalize patterns better than any other ANN. In…

Machine Learning · Computer Science 2021-03-16 Seyed Majid Naji , Azra Abtahi , Farokh Marvasti

With the rapid adoption of machine learning (ML), a number of domains now use the approach of fine tuning models which were pre-trained on a large corpus of data. However, our experiments show that even fine-tuning on models like BERT can…

Machine Learning · Computer Science 2021-04-06 Yuhan Liu , Saurabh Agarwal , Shivaram Venkataraman

Sparse neural networks have been widely applied to reduce the computational demands of training and deploying over-parameterized deep neural networks. For inference acceleration, methods that discover a sparse network from a pre-trained…

Machine Learning · Computer Science 2021-06-16 Shiwei Liu , Decebal Constantin Mocanu , Yulong Pei , Mykola Pechenizkiy

We introduce a method to speed up training by 2x and inference by 3x in deep neural networks using structured pruning applied before training. Unlike previous works on pruning before training which prune individual weights, our work…

Machine Learning · Computer Science 2020-07-02 Joost van Amersfoort , Milad Alizadeh , Sebastian Farquhar , Nicholas Lane , Yarin Gal

Sparse training is often adopted in cross-device federated learning (FL) environments where constrained devices collaboratively train a machine learning model on private data by exchanging pseudo-gradients across heterogeneous networks.…

Machine Learning · Computer Science 2025-04-08 Adriano Guastella , Lorenzo Sani , Alex Iacob , Alessio Mora , Paolo Bellavista , Nicholas D. Lane

Fine-tuning pretrained self-supervised language models is widely adopted for transfer learning to downstream tasks. Fine-tuning can be achieved by freezing gradients of the pretrained network and only updating gradients of a newly added…

Computation and Language · Computer Science 2023-07-20 James O' Neill , Sourav Dutta

This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017). We examine some of the critical parameters that affect the…

Computation and Language · Computer Science 2018-05-03 Martin Popel , Ondřej Bojar

This study investigates the layerwise importance of feed-forward networks (FFNs) in Transformer-based language models during pretraining. We introduce an experimental approach that, while maintaining the total parameter count, increases the…

Computation and Language · Computer Science 2025-08-26 Wataru Ikeda , Kazuki Yano , Ryosuke Takahashi , Jaesung Lee , Keigo Shibata , Jun Suzuki

The high energy cost of processing deep convolutional neural networks impedes their ubiquitous deployment in energy-constrained platforms such as embedded systems and IoT devices. This work introduces convolutional layers with pre-defined…

Computer Vision and Pattern Recognition · Computer Science 2020-02-06 Souvik Kundu , Mahdi Nazemi , Massoud Pedram , Keith M. Chugg , Peter A. Beerel

The excessive computational requirements of modern artificial neural networks (ANNs) are posing limitations on the machines that can run them. Sparsification of ANNs is often motivated by time, memory and energy savings only during model…

Machine Learning · Computer Science 2025-05-01 Mike Heddes , Narayan Srinivasa , Tony Givargis , Alexandru Nicolau

Adapter Tuning, which freezes the pretrained language models (PLMs) and only fine-tunes a few extra modules, becomes an appealing efficient alternative to the full model fine-tuning. Although computationally efficient, the recent Adapters…

Computation and Language · Computer Science 2022-11-11 Shwai He , Liang Ding , Daize Dong , Miao Zhang , Dacheng Tao

The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Wei Shang , Dongwei Ren , Wanying Zhang , Pengfei Zhu , Qinghua Hu , Wangmeng Zuo

The transformer architecture has prevailed in various deep learning settings due to its exceptional capabilities to select and compose structural information. Motivated by these capabilities, Sanford et al. proposed the sparse token…

Machine Learning · Statistics 2024-06-12 Zixuan Wang , Stanley Wei , Daniel Hsu , Jason D. Lee

Recent advances in Transformers have come with a huge requirement on computing resources, highlighting the importance of developing efficient training techniques to make Transformer training faster, at lower cost, and to higher accuracy by…

Machine Learning · Computer Science 2023-05-05 Bohan Zhuang , Jing Liu , Zizheng Pan , Haoyu He , Yuetian Weng , Chunhua Shen