English
Related papers

Related papers: Analyzing Redundancy in Pretrained Transformer Mod…

200 papers

Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and…

Machine Learning · Computer Science 2021-03-05 Lucas Liebenwein , Cenk Baykal , Brandon Carter , David Gifford , Daniela Rus

Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribution (OOD) generalization for seven NLP datasets by…

Computation and Language · Computer Science 2020-04-17 Dan Hendrycks , Xiaoyuan Liu , Eric Wallace , Adam Dziedzic , Rishabh Krishnan , Dawn Song

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

Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and…

Machine Learning · Computer Science 2022-04-22 Jonathan Pilault , Amine Elhattami , Christopher Pal

Transfer learning, in which a network is trained on one task and re-purposed on another, is often used to produce neural network classifiers when data is scarce or full-scale training is too costly. When the goal is to produce a model that…

Machine Learning · Computer Science 2020-02-24 Ali Shafahi , Parsa Saadatpanah , Chen Zhu , Amin Ghiasi , Christoph Studer , David Jacobs , Tom Goldstein

One aim shared by multiple settings, such as continual learning or transfer learning, is to leverage previously acquired knowledge to converge faster on the current task. Usually this is done through fine-tuning, where an implicit…

Machine Learning · Computer Science 2023-10-17 Tudor Berariu , Wojciech Czarnecki , Soham De , Jorg Bornschein , Samuel Smith , Razvan Pascanu , Claudia Clopath

There is growing evidence that pretrained language models improve task-specific fine-tuning not just for the languages seen in pretraining, but also for new languages and even non-linguistic data. What is the nature of this surprising…

Computation and Language · Computer Science 2021-04-20 Zhengxuan Wu , Nelson F. Liu , Christopher Potts

Purpose: Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally network performance should be optimized by drawing the training and testing data from the same domain. In practice, however,…

Computer Vision and Pattern Recognition · Computer Science 2019-05-07 Salman Ul Hassan Dar , Muzaffer Özbey , Ahmet Burak Çatlı , Tolga Çukur

Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often…

Computer Vision and Pattern Recognition · Computer Science 2021-11-01 Shehryar Malik , Muhammad Umair Haider , Omer Iqbal , Murtaza Taj

Transfer learning from ImageNet is the go-to approach when applying deep learning to medical images. The approach is either to fine-tune a pre-trained model or use it as a feature extractor. Most modern architecture contain batch…

Computer Vision and Pattern Recognition · Computer Science 2021-02-11 Fahdi Kanavati , Masayuki Tsuneki

We propose a randomized neural network approach called RaNNDy for learning transfer operators and their spectral decompositions from data. The weights of the hidden layers of the neural network are randomly selected and only the output…

Machine Learning · Computer Science 2025-09-25 Mohammad Tabish , Benedict Leimkuhler , Stefan Klus

Overparameterized neural networks often contain many removable neurons, yet what makes a neuron redundant remains poorly understood. Existing pruning criteria commonly rely on local quantities such as weight magnitude, activation strength,…

Machine Learning · Computer Science 2026-05-21 Yongyu Wang

It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pre-trained on large datasets as preprocessors. Typically, the last layer is replaced by a shallow learning machine of sorts; the…

Machine Learning · Computer Science 2023-10-03 Haozhe Sun , Isabelle Guyon , Felix Mohr , Hedi Tabia

Deep neural networks (DNNs) have become ubiquitous thanks to their remarkable ability to model complex patterns across various domains such as computer vision, speech recognition, robotics, etc. While large DNN models are often more…

Machine Learning · Computer Science 2025-11-18 Omkar Shende , Gayathri Ananthanarayanan , Marcello Traiola

Transfer learning is widely used to adapt large pretrained models to new tasks with only a small amount of new data. However, a challenge persists -- the features from the original task often do not fully cover what is needed for unseen…

Machine Learning · Computer Science 2026-02-10 Xingyu Alice Yang , Jianyu Zhang , Léon Bottou

Randomized Neural Networks explore the behavior of neural systems where the majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical examples of such systems consist of multi-layered neural network…

Machine Learning · Computer Science 2021-02-03 Claudio Gallicchio , Simone Scardapane

Modern neural machine translation (NMT) models employ a large number of parameters, which leads to serious over-parameterization and typically causes the underutilization of computational resources. In response to this problem, we…

Computation and Language · Computer Science 2020-10-07 Yong Wang , Longyue Wang , Victor O. K. Li , Zhaopeng Tu

Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and obtaining the high-quality training data for all tasks is…

Computation and Language · Computer Science 2025-11-11 Shambhavi Krishna , Atharva Naik , Chaitali Agarwal , Sudharshan Govindan , Taesung Lee , Haw-Shiuan Chang

Deep neural network models have been very successfully applied to Natural Language Processing (NLP) and Image based tasks. Their application to network analysis and management tasks is just recently being pursued. Our interest is in…

Networking and Internet Architecture · Computer Science 2022-06-22 Franck Le , Davis Wertheimer , Seraphin Calo , Erich Nahum

While neural network-based models have achieved impressive performance on a large body of NLP tasks, the generalization behavior of different models remains poorly understood: Does this excellent performance imply a perfect generalization…

Computation and Language · Computer Science 2020-01-14 Jinlan Fu , Pengfei Liu , Qi Zhang , Xuanjing Huang