English
Related papers

Related papers: Parameter Transfer Unit for Deep Neural Networks

200 papers

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…

Computation and Language · Computer Science 2023-03-07 Zhen Wang , Rameswar Panda , Leonid Karlinsky , Rogerio Feris , Huan Sun , Yoon Kim

This paper focuses on spectral graph convolutional neural networks (ConvNets), where filters are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the dataset consists of signals…

Machine Learning · Computer Science 2021-06-15 Ron Levie , Wei Huang , Lorenzo Bucci , Michael M. Bronstein , Gitta Kutyniok

Transformer-based deep NLP models are trained using hundreds of millions of parameters, limiting their applicability in computationally constrained environments. In this paper, we study the cause of these limitations by defining a notion of…

Computation and Language · Computer Science 2020-10-07 Fahim Dalvi , Hassan Sajjad , Nadir Durrani , Yonatan Belinkov

Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sharing practice is to share the bottom layers of a deep…

Machine Learning · Computer Science 2022-03-22 Lijun Zhang , Qizheng Yang , Xiao Liu , Hui Guan

Transfer learning using deep neural networks as feature extractors has become increasingly popular over the past few years. It allows to obtain state-of-the-art accuracy on datasets too small to train a deep neural network on its own, and…

Machine Learning · Computer Science 2017-10-25 Vincent Gripon , Ghouthi B. Hacene , Matthias Löwe , Franck Vermet

Recent work on deep learning for tabular data demonstrates the strong performance of deep tabular models, often bridging the gap between gradient boosted decision trees and neural networks. Accuracy aside, a major advantage of neural models…

Objective: Neural network de-identification studies have focused on individual datasets. These studies assume the availability of a sufficient amount of human-annotated data to train models that can generalize to corresponding test data. In…

Computation and Language · Computer Science 2021-08-18 Kahyun Lee , Nicholas J. Dobbins , Bridget McInnes , Meliha Yetisgen , Ozlem Uzuner

Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge. However, the ability to perform few or zero-shot adaptation to novel…

Machine Learning · Computer Science 2020-10-14 Samarth Sinha , Karsten Roth , Anirudh Goyal , Marzyeh Ghassemi , Hugo Larochelle , Animesh Garg

Recent years, transfer learning has attracted much attention in the community of machine learning. In this paper, we mainly focus on the tasks of parameter transfer under the framework of extreme learning machine (ELM). Unlike the existing…

Machine Learning · Computer Science 2018-10-24 Chao Chen , Boyuan Jiang , Xinyu Jin

This paper is about regularizing deep convolutional networks (CNNs) based on an adaptive framework for transfer learning with limited training data in the target domain. Recent advances of CNN regularization in this context are commonly due…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Yang Zhong , Atsuto Maki

We study the problem of user association, namely finding the optimal assignment of user equipment to base stations to achieve a targeted network performance. In this paper, we focus on the knowledge transferability of association policies.…

Machine Learning · Computer Science 2021-06-07 Mohamed Sana , Nicola di Pietro , Emilio Calvanese Strinati

Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Xander Coetzer , Arné Schreuder , Anna Sergeevna Bosman

The development of deep learning techniques has allowed Neural Machine Translation (NMT) models to become extremely powerful, given sufficient training data and training time. However, systems struggle when translating text from a new…

Computation and Language · Computer Science 2022-03-23 Danielle Saunders

Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…

Multimedia · Computer Science 2022-12-07 Shinta Otake , Rei Kawakami , Nakamasa Inoue

Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Yunhui Guo , Honghui Shi , Abhishek Kumar , Kristen Grauman , Tajana Rosing , Rogerio Feris

It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution…

Machine Learning · Computer Science 2022-06-28 Bruno Casella , Alessio Barbaro Chisari , Sebastiano Battiato , Mario Valerio Giuffrida

Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferable targeted attacks that can mislead DNN models into…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Kaisheng Liang , Xuelong Dai , Yanjie Li , Dong Wang , Bin Xiao

Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks. However, the pretrained models are often prohibitively large…

Machine Learning · Computer Science 2025-01-07 Yonggan Fu , Ye Yuan , Shang Wu , Jiayi Yuan , Yingyan Celine Lin

Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. Parameter inefficiency can however arise when, during transfer learning, all the parameters of a large pre-trained model need to be updated…

Computation and Language · Computer Science 2023-03-07 Yingting Li , Ambuj Mehrish , Shuai Zhao , Rishabh Bhardwaj , Amir Zadeh , Navonil Majumder , Rada Mihalcea , Soujanya Poria

Agnostic domain shift is the main reason of model degradation on the unknown target domains, which brings an urgent need to develop Domain Generalization (DG). Recent advances at DG use dynamic networks to achieve training-free adaptation…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Luojun Lin , Zhifeng Shen , Zhishu Sun , Yuanlong Yu , Lei Zhang , Weijie Chen
‹ Prev 1 3 4 5 6 7 10 Next ›