English
Related papers

Related papers: Learning on Transformers is Provable Low-Rank and …

200 papers

The increasing of pre-trained models has significantly facilitated the performance on limited data tasks with transfer learning. However, progress on transfer learning mainly focuses on optimizing the weights of pre-trained models, which…

Computer Vision and Pattern Recognition · Computer Science 2021-03-03 Bingyan Liu , Yifeng Cai , Yao Guo , Xiangqun Chen

With the proliferation of large pre-trained language models (PLMs), fine-tuning all model parameters becomes increasingly inefficient, particularly when dealing with numerous downstream tasks that entail substantial training and storage…

Computation and Language · Computer Science 2024-01-23 Nadav Benedek , Lior Wolf

The components underpinning PLMs -- large weight matrices -- were shown to bear considerable redundancy. Matrix factorization, a well-established technique from matrix theory, has been utilized to reduce the number of parameters in PLM.…

Computation and Language · Computer Science 2023-06-27 Siyu Ren , Kenny Q. Zhu

Pruning is an effective way to reduce the huge inference cost of Transformer models. However, prior work on pruning Transformers requires retraining the models. This can add high training cost and high complexity to model deployment, making…

Computation and Language · Computer Science 2022-10-18 Woosuk Kwon , Sehoon Kim , Michael W. Mahoney , Joseph Hassoun , Kurt Keutzer , Amir Gholami

We propose a general method called truncated gradient to induce sparsity in the weights of online learning algorithms with convex loss functions. This method has several essential properties: The degree of sparsity is continuous -- a…

Machine Learning · Computer Science 2008-07-04 John Langford , Lihong Li , Tong Zhang

Recurrent neural networks (RNNs) trained on low-dimensional tasks have been widely used to model functional biological networks. However, the solutions found by learning and the effect of initial connectivity are not well understood. Here,…

Neurons and Cognition · Quantitative Biology 2021-05-17 Friedrich Schuessler , Francesca Mastrogiuseppe , Alexis Dubreuil , Srdjan Ostojic , Omri Barak

Large scale deep learning provides a tremendous opportunity to improve the quality of content recommendation systems by employing both wider and deeper models, but this comes at great infrastructural cost and carbon footprint in modern data…

Machine Learning · Computer Science 2020-10-22 Mao Ye , Dhruv Choudhary , Jiecao Yu , Ellie Wen , Zeliang Chen , Jiyan Yang , Jongsoo Park , Qiang Liu , Arun Kejariwal

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Machine Learning · Computer Science 2026-02-11 Jonathan Svirsky , Yehonathan Refael , Ofir Lindenbaum

Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs. Examples include \textit{graph sparsification}…

Machine Learning · Computer Science 2023-02-07 Shuai Zhang , Meng Wang , Pin-Yu Chen , Sijia Liu , Songtao Lu , Miao Liu

Network modeling of high-dimensional time series data is a key learning task due to its widespread use in a number of application areas, including macroeconomics, finance and neuroscience. While the problem of sparse modeling based on…

Methodology · Statistics 2019-03-27 Sumanta Basu , Xianqi Li , George Michailidis

Recent work on the lottery ticket hypothesis has produced highly sparse Transformers for NMT while maintaining BLEU. However, it is unclear how such pruning techniques affect a model's learned representations. By probing Transformers with…

Computation and Language · Computer Science 2020-10-14 Rajiv Movva , Jason Y. Zhao

Large language models (LLMs) show excellent performance in difficult tasks, but they often require massive memories and computational resources. How to reduce the parameter scale of LLMs has become research hotspots. In this study, we make…

Machine Learning · Computer Science 2024-04-16 Guangyan Li , Yongqiang Tang , Wensheng Zhang

Transformer becomes the state-of-the-art translation model, while it is not well studied how each intermediate component contributes to the model performance, which poses significant challenges for designing optimal architectures. In this…

Computation and Language · Computer Science 2020-11-10 Wenxuan Wang , Zhaopeng Tu

We present a novel network pruning algorithm called Dynamic Sparse Training that can jointly find the optimal network parameters and sparse network structure in a unified optimization process with trainable pruning thresholds. These…

Machine Learning · Computer Science 2020-05-15 Junjie Liu , Zhe Xu , Runbin Shi , Ray C. C. Cheung , Hayden K. H. So

How is knowledge stored in an LLM's weights? We study this via layer pruning: if removing a certain layer does not affect model performance in common question-answering benchmarks, then the weights in that layer are not necessary for…

Computation and Language · Computer Science 2025-03-04 Andrey Gromov , Kushal Tirumala , Hassan Shapourian , Paolo Glorioso , Daniel A. Roberts

A low-rank transformation learning framework for subspace clustering and classification is here proposed. Many high-dimensional data, such as face images and motion sequences, approximately lie in a union of low-dimensional subspaces. The…

Computer Vision and Pattern Recognition · Computer Science 2014-03-11 Qiang Qiu , Guillermo Sapiro

Sparsity is a desirable attribute. It can lead to more efficient and more effective representations compared to the dense model. Meanwhile, learning sparse latent representations has been a challenging problem in the field of computer…

Computer Vision and Pattern Recognition · Computer Science 2022-09-22 Hanao Li , Tian Han

A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as…

Computer Vision and Pattern Recognition · Computer Science 2019-02-26 Aaditya Prakash , James Storer , Dinei Florencio , Cha Zhang

Convolutional neural networks trained without supervision come close to matching performance with supervised pre-training, but sometimes at the cost of an even higher number of parameters. Extracting subnetworks from these large…

Computer Vision and Pattern Recognition · Computer Science 2020-01-13 Mathilde Caron , Ari Morcos , Piotr Bojanowski , Julien Mairal , Armand Joulin

Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning on multilingual…

Computation and Language · Computer Science 2022-04-07 Yanyang Li , Fuli Luo , Runxin Xu , Songfang Huang , Fei Huang , Liwei Wang