English
Related papers

Related papers: Towards Structured Dynamic Sparse Pre-Training of …

200 papers

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse…

Machine Learning · Computer Science 2019-08-27 Tim Dettmers , Luke Zettlemoyer

Diffusion models (DMs) are a powerful type of generative models that have achieved state-of-the-art results in various image synthesis tasks and have shown potential in other domains, such as natural language processing and temporal data…

Machine Learning · Computer Science 2026-02-05 Inês Cardoso Oliveira , Decebal Constantin Mocanu , Luis A. Leiva

We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives. Unlike existing pruning or architecture search techniques that operate on…

Machine Learning · Computer Science 2023-06-07 Xin Yuan , Pedro Savarese , Michael Maire

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the…

Machine Learning · Computer Science 2023-09-11 Denis Kuznedelev , Eldar Kurtic , Eugenia Iofinova , Elias Frantar , Alexandra Peste , Dan Alistarh

There exists a plethora of techniques for inducing structured sparsity in parametric models during the optimization process, with the final goal of resource-efficient inference. However, few methods target a specific number of…

Machine Learning · Computer Science 2018-11-26 Raphael Tang , Ashutosh Adhikari , Jimmy Lin

Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-training and supervised fine-tuning. However, the costs…

Computation and Language · Computer Science 2024-06-07 Da Ma , Lu Chen , Pengyu Wang , Hongshen Xu , Hanqi Li , Liangtai Sun , Su Zhu , Shuai Fan , Kai Yu

We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror descent that exploits the naturally incurred sparsity by alternating between periods of static and dynamic sparsity pattern updates. The key…

Machine Learning · Computer Science 2026-05-19 Yannick Lunk , Sebastian J. Scott , Leon Bungert

Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their…

Machine Learning · Computer Science 2024-06-06 Amit Dhurandhar , Tejaswini Pedapati , Ronny Luss , Soham Dan , Aurelie Lozano , Payel Das , Georgios Kollias

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and…

Computation and Language · Computer Science 2020-10-06 Zihan Liu , Genta Indra Winata , Andrea Madotto , Pascale Fung

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

Recent research has focused on weight sparsity in deep neural network training to reduce FLOPs, aiming for improved efficiency (test accuracy w.r.t training FLOPs). However, sparse weight training often compromises accuracy, requiring…

Machine Learning · Computer Science 2024-07-19 Vithursan Thangarasa , Shreyas Saxena , Abhay Gupta , Sean Lie

Large pre-trained language models have recently gained significant traction due to their improved performance on various down-stream tasks like text classification and question answering, requiring only few epochs of fine-tuning. However,…

Computation and Language · Computer Science 2023-09-01 Souvik Kundu , Sharath Nittur Sridhar , Maciej Szankin , Sairam Sundaresan

Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the…

Computation and Language · Computer Science 2020-12-07 Daniel Grießhaber , Johannes Maucher , Ngoc Thang Vu

Many applications require sparse neural networks due to space or inference time restrictions. There is a large body of work on training dense networks to yield sparse networks for inference, but this limits the size of the largest trainable…

Machine Learning · Computer Science 2021-07-26 Utku Evci , Trevor Gale , Jacob Menick , Pablo Samuel Castro , Erich Elsen

Transformer-based language models have become a key building block for natural language processing. While these models are extremely accurate, they can be too large and computationally intensive to run on standard deployments. A variety of…

Computation and Language · Computer Science 2022-10-19 Eldar Kurtic , Daniel Campos , Tuan Nguyen , Elias Frantar , Mark Kurtz , Benjamin Fineran , Michael Goin , Dan Alistarh

Neural information retrieval architectures based on transformers such as BERT are able to significantly improve system effectiveness over traditional sparse models such as BM25. Though highly effective, these neural approaches are very…

Information Retrieval · Computer Science 2022-04-26 Antonio Mallia , Joel Mackenzie , Torsten Suel , Nicola Tonellotto

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…

Computation and Language · Computer Science 2019-08-16 Yaru Hao , Li Dong , Furu Wei , Ke Xu

In recent years, BERT has made significant breakthroughs on many natural language processing tasks and attracted great attentions. Despite its accuracy gains, the BERT model generally involves a huge number of parameters and needs to be…

Computation and Language · Computer Science 2021-02-19 Cheng Yang , Shengnan Wang , Yuechuan Li , Chao Yang , Ming Yan , Jingqiao Zhang , Fangquan Lin

The pre-trained language models like BERT, though powerful in many natural language processing tasks, are both computation and memory expensive. To alleviate this problem, one approach is to compress them for specific tasks before…

Computation and Language · Computer Science 2020-10-12 Lu Hou , Zhiqi Huang , Lifeng Shang , Xin Jiang , Xiao Chen , Qun Liu

We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified. We show that with small-to-medium training data, applying BitFit on pre-trained BERT models is competitive with…

Machine Learning · Computer Science 2026-01-30 Elad Ben-Zaken , Shauli Ravfogel , Yoav Goldberg