English
Related papers

Related papers: KNN-BERT: Fine-Tuning Pre-Trained Models with KNN …

200 papers

Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Raphaël Achddou , J. Matias di Martino , Guillermo Sapiro

This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Mahmudul Hasan , Mabsur Fatin Bin Hossain

While pre-trained language models (e.g., BERT) have achieved impressive results on different natural language processing tasks, they have large numbers of parameters and suffer from big computational and memory costs, which make them…

Computation and Language · Computer Science 2021-06-01 Jin Xu , Xu Tan , Renqian Luo , Kaitao Song , Jian Li , Tao Qin , Tie-Yan Liu

He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional…

Machine Learning · Computer Science 2019-10-22 Dan Hendrycks , Kimin Lee , Mantas Mazeika

k-Nearest Neighbors is one of the most fundamental but effective classification models. In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nearest Neighbors…

Machine Learning · Computer Science 2019-11-28 Yiming Xu , Diego Klabjan

It has been proven that transfer learning provides an easy way to achieve state-of-the-art accuracies on several vision tasks by training a simple classifier on top of features obtained from pre-trained neural networks. The goal of this…

Machine Learning · Computer Science 2016-06-07 Milad Mohammadi , Subhasis Das

Pre-trained language models can be fine-tuned to solve diverse NLP tasks, including in few-shot settings. Thus fine-tuning allows the model to quickly pick up task-specific ``skills,'' but there has been limited study of where these…

Computation and Language · Computer Science 2023-07-04 Abhishek Panigrahi , Nikunj Saunshi , Haoyu Zhao , Sanjeev Arora

High dimensionality, i.e. data having a large number of variables, tends to be a challenge for most machine learning tasks, including classification. A classifier usually builds a model representing how a set of inputs explain the outputs.…

Machine Learning · Computer Science 2018-03-12 Francisco J. Pulgar , Francisco Charte , Antonio J. Rivera , María J. del Jesus

Recent works have proven the effectiveness of k-nearest-neighbor machine translation(a.k.a kNN-MT) approaches to produce remarkable improvement in cross-domain translations. However, these models suffer from heavy retrieve overhead on the…

Computation and Language · Computer Science 2025-01-07 Xiangyu Shi , Yunlong Liang , Jinan Xu , Yufeng Chen

The emerging classical-quantum transfer learning paradigm has brought a decent performance to quantum computational models in many tasks, such as computer vision, by enabling a combination of quantum models and classical pre-trained neural…

Quantum Physics · Physics 2023-02-28 Qiuchi Li , Benyou Wang , Yudong Zhu , Christina Lioma , Qun Liu

Despite deep recurrent neural networks (RNNs) demonstrate strong performance in text classification, training RNN models are often expensive and requires an extensive collection of annotated data which may not be available. To overcome the…

Computation and Language · Computer Science 2018-10-02 Wasi Uddin Ahmad , Xueying Bai , Nanyun Peng , Kai-Wei Chang

$k$-Nearest neighbor machine translation ($k$NN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains. By using an upstream NMT model to traverse the downstream training corpus, it…

Computation and Language · Computer Science 2023-05-29 Zhiwei Cao , Baosong Yang , Huan Lin , Suhang Wu , Xiangpeng Wei , Dayiheng Liu , Jun Xie , Min Zhang , Jinsong Su

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…

Machine Learning · Computer Science 2021-06-03 Omer Faruk Tuna , Ferhat Ozgur Catak , M. Taner Eskil

Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian…

Machine Learning · Computer Science 2023-02-09 Boqi Li , Weiwei Liu

Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because it requires a prior knowledge or experience to design the…

Machine Learning · Computer Science 2018-06-06 Sheng-Jun Huang , Jia-Wei Zhao , Zhao-Yang Liu

Obtaining labeled data to train a model for a task of interest is often expensive. Prior work shows training models on multitask data augmented with task descriptions (prompts) effectively transfers knowledge to new tasks. Towards…

Computation and Language · Computer Science 2023-05-26 Hamish Ivison , Noah A. Smith , Hannaneh Hajishirzi , Pradeep Dasigi

In this study, we propose the integration of competitive learning into convolutional neural networks (CNNs) to improve the representation learning and efficiency of fine-tuning. Conventional CNNs use back propagation learning, and it…

Machine Learning · Computer Science 2018-04-27 Takashi Shinozaki

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang

Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization. Such desirable properties are…

Machine Learning · Computer Science 2020-12-22 Alessandro Achille , Aditya Golatkar , Avinash Ravichandran , Marzia Polito , Stefano Soatto

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva