English
Related papers

Related papers: Weight subcloning: direct initialization of transf…

200 papers

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Computation and Language · Computer Science 2020-06-24 Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , Joseph E. Gonzalez

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

Computation and Language · Computer Science 2022-03-25 Le Hou , Richard Yuanzhe Pang , Tianyi Zhou , Yuexin Wu , Xinying Song , Xiaodan Song , Denny Zhou

Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of…

Machine Learning · Computer Science 2023-07-04 Gal Kaplun , Andrey Gurevich , Tal Swisa , Mazor David , Shai Shalev-Shwartz , Eran Malach

Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise…

Machine Learning · Computer Science 2015-06-09 Zhiyuan Tang , Dong Wang , Yiqiao Pan , Zhiyong Zhang

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

In this work we propose a HyperTransformer, a Transformer-based model for supervised and semi-supervised few-shot learning that generates weights of a convolutional neural network (CNN) directly from support samples. Since the dependence of…

Machine Learning · Computer Science 2022-07-15 Andrey Zhmoginov , Mark Sandler , Max Vladymyrov

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

Machine Learning · Computer Science 2021-03-08 MaungMaung AprilPyone , Hitoshi Kiya

With the growing burden of training deep learning models with large data sets, transfer-learning has been widely adopted in many emerging deep learning algorithms. Transformer models such as BERT are the main player in natural language…

Cryptography and Security · Computer Science 2022-07-21 Mujahid Al Rafi , Yuan Feng , Hyeran Jeon

In recent developments in the field of Computer Vision, a rise is seen in the use of transformer-based architectures. They are surpassing the state-of-the-art set by CNN architectures in accuracy but on the other hand, they are…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Durvesh Malpure , Onkar Litake , Rajesh Ingle

This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained…

Machine Learning · Computer Science 2023-02-28 Byeonggeun Kim , Jun-Tae Lee , Seunghan yang , Simyung Chang

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. Here we explore the…

Software Engineering · Computer Science 2020-03-04 Natalie Best , Jordan Ott , Erik Linstead

Transfer of pre-trained representations can improve sample efficiency and reduce computational requirements for new tasks. However, representations used for transfer are usually generic, and are not tailored to a particular distribution of…

As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task. Existing model selection techniques are often constrained in their scope…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Jiameng Bai , Sai Wu , Jie Song , Junbo Zhao , Gang Chen

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

Computer Vision and Pattern Recognition · Computer Science 2021-11-22 Shuvam Chakraborty , Burak Uzkent , Kumar Ayush , Kumar Tanmay , Evan Sheehan , Stefano Ermon

It is common practice to reuse models initially trained on different data to increase downstream task performance. Especially in the computer vision domain, ImageNet-pretrained weights have been successfully used for various tasks. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-08-01 Jonas Dippel , Matthias Lenga , Thomas Goerttler , Klaus Obermayer , Johannes Höhne

Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency, recent work has explored model upscaling: initializing larger models from trained smaller…

Machine Learning · Computer Science 2026-02-12 Yuxin Ma , Nan Chen , Mateo Díaz , Soufiane Hayou , Dmitriy Kunisky , Soledad Villar

Prior work shows that it is possible to expand pretrained Masked Language Models (MLMs) to new languages by learning a new set of embeddings, while keeping the transformer body frozen. Despite learning a small subset of parameters, this…

Computation and Language · Computer Science 2023-07-06 Kelly Marchisio , Patrick Lewis , Yihong Chen , Mikel Artetxe

Unsupervised pre-training and transfer learning are commonly used techniques to initialize training algorithms for neural networks, particularly in settings with limited labeled data. In this paper, we study the effects of unsupervised…

Machine Learning · Statistics 2025-06-12 Taj Jones-McCormick , Aukosh Jagannath , Subhabrata Sen

Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it is often necessary to acquire new data and retrain the model.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Niklas Penzel , Gideon Stein , Joachim Denzler