English
Related papers

Related papers: How to prepare your task head for finetuning

200 papers

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

The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two major ways to mitigate this problem: either preserving…

Computer Vision and Pattern Recognition · Computer Science 2019-07-24 Shivangi Srivastava , Maxim Berman , Matthew B. Blaschko , Devis Tuia

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…

A recent family of techniques, dubbed lightweight fine-tuning methods, facilitates parameter-efficient transfer learning by updating only a small set of additional parameters while keeping the parameters of the pretrained language model…

Computation and Language · Computer Science 2022-12-09 Mozhdeh Gheini , Xuezhe Ma , Jonathan May

With the rise of powerful foundation models, a pre-training-fine-tuning paradigm becomes increasingly popular these days: A foundation model is pre-trained using a huge amount of data from various sources, and then the downstream users only…

Machine Learning · Computer Science 2025-04-16 Meiqi Liu , Zhuoqun Huang , Yue Xing

An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…

Machine Learning · Computer Science 2024-03-19 Yihao Xue , Eric Gan , Jiayi Ni , Siddharth Joshi , Baharan Mirzasoleiman

This work offers a heuristic evaluation of the effects of variations in machine learning training regimes and learning paradigms on the energy consumption of computing, especially HPC hardware with a life-cycle aware perspective. While…

Machine Learning · Computer Science 2024-10-08 Daniel Geißler , Bo Zhou , Mengxi Liu , Sungho Suh , Paul Lukowicz

Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models are often fine-tuned to improve zero-shot performance on…

Computation and Language · Computer Science 2026-02-27 Chungpa Lee , Jy-yong Sohn , Kangwook Lee

Large language models are first pre-trained on trillions of tokens and then instruction-tuned or aligned to specific preferences. While pre-training remains out of reach for most researchers due to the compute required, fine-tuning has…

Computation and Language · Computer Science 2024-06-10 Megh Thakkar , Quentin Fournier , Matthew D Riemer , Pin-Yu Chen , Amal Zouaq , Payel Das , Sarath Chandar

Transformer-based pre-trained language models have demonstrated superior performance on various natural language processing tasks. However, it remains unclear how the skills required to handle these tasks distribute among model parameters.…

Computation and Language · Computer Science 2022-11-15 Xiaozhi Wang , Kaiyue Wen , Zhengyan Zhang , Lei Hou , Zhiyuan Liu , Juanzi Li

Although CNNs have gained the ability to transfer learned knowledge from source task to target task by virtue of large annotated datasets but consume huge processing time to fine-tune without GPU. In this paper, we propose a new…

Computer Vision and Pattern Recognition · Computer Science 2019-03-28 Tasfia Shermin , Manzur Murshed , Guojun Lu , Shyh Wei Teng

We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing only a few, potentially noisy, data points per instance.…

Machine Learning · Computer Science 2026-02-04 Zishi Zhang , Jinhui Han , Ming Hu , Yijie Peng

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

Top-down attention allows neural networks, both artificial and biological, to focus on the information most relevant for a given task. This is known to enhance performance in visual perception. But it remains unclear how attention brings…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Freddie Bickford Smith , Brett D Roads , Xiaoliang Luo , Bradley C Love

Intermediate-task transfer can benefit a wide range of NLP tasks with properly selected source datasets. However, it is computationally infeasible to experiment with all intermediate transfer combinations, making choosing a useful source…

Computation and Language · Computer Science 2022-10-24 Wangchunshu Zhou , Canwen Xu , Julian McAuley

For many machine learning algorithms, predictive performance is critically affected by the hyperparameter values used to train them. However, tuning these hyperparameters can come at a high computational cost, especially on larger datasets,…

The superior performance of some of today's state-of-the-art deep learning models is to some extent owed to extensive (self-)supervised contrastive pretraining on large-scale datasets. In contrastive learning, the network is presented with…

Machine Learning · Computer Science 2022-07-20 Shervin Ardeshir , Navid Azizan

Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large…

Software Engineering · Computer Science 2023-04-12 Ensheng Shi , Yanlin Wang , Hongyu Zhang , Lun Du , Shi Han , Dongmei Zhang , Hongbin Sun

The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models. However, the impact of fine-tuning strategies on long-tail learning performance remains unexplored. In…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Jiang-Xin Shi , Tong Wei , Yu-Feng Li

The goal of multi-task learning is to learn diverse tasks within a single unified network. As each task has its own unique objective function, conflicts emerge during training, resulting in negative transfer among them. Earlier research…

Machine Learning · Computer Science 2024-06-06 Wooseong Jeong , Kuk-Jin Yoon