English
Related papers

Related papers: Pretraining Induces a Reusable Spectral Basis for …

200 papers

With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a methodology that jointly…

Machine Learning · Computer Science 2024-02-26 Sebastian Pineda Arango , Fabio Ferreira , Arlind Kadra , Frank Hutter , Josif Grabocka

We study the problem of transfer learning and fine-tuning in linear models for both regression and binary classification. In particular, we consider the use of stochastic gradient descent (SGD) on a linear model initialized with pretrained…

Machine Learning · Computer Science 2025-02-25 Reza Ghane , Danil Akhtiamov , Babak Hassibi

The growth of global consumption has motivated important applications of deep learning to smart manufacturing and machine health monitoring. In particular, analyzing vibration data offers great potential to extract meaningful insights into…

Machine Learning · Computer Science 2024-05-30 Anthony Zhou , Amir Barati Farimani

The dominant paradigm in generative modeling consists of two steps: i) pre-training on a large-scale but unsafe dataset, ii) aligning the pre-trained model with human values via fine-tuning. This practice is considered safe, as no current…

Machine Learning · Computer Science 2024-07-02 Eliahu Horwitz , Jonathan Kahana , Yedid Hoshen

By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Om Khangaonkar , Hamed Pirsiavash

When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient transfer learning (PETL) is proposed, which only tunes a tiny…

Computer Vision and Pattern Recognition · Computer Science 2024-02-05 Minghao Fu , Ke Zhu , Jianxin Wu

In recent years, domains such as natural language processing and image recognition have popularized the paradigm of using large datasets to pretrain representations that can be effectively transferred to downstream tasks. In this work we…

Machine Learning · Computer Science 2023-10-26 David Brandfonbrener , Ofir Nachum , Joan Bruna

Recently, graph neural networks (GNNs) have shown its unprecedented success in many graph-related tasks. However, GNNs face the label scarcity issue as other neural networks do. Thus, recent efforts try to pre-train GNNs on a large-scale…

Machine Learning · Computer Science 2024-03-04 Zhili Wang , Shimin Di , Lei Chen , Xiaofang Zhou

Efficient finetuning of pretrained language transformers is becoming increasingly prevalent for solving natural language processing tasks. While effective, it can still require a large number of tunable parameters. This can be a drawback…

Computation and Language · Computer Science 2023-05-31 Umang Gupta , Aram Galstyan , Greg Ver Steeg

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model…

Machine Learning · Computer Science 2026-05-01 Nghia Bui , Lijing Wang

ImageNet pre-training has enabled state-of-the-art results on many tasks. In spite of its recognized contribution to generalization, we observed in this study that ImageNet pre-training also transfers adversarial non-robustness from…

Computer Vision and Pattern Recognition · Computer Science 2022-12-07 Jiaming Zhang , Jitao Sang , Qi Yi , Yunfan Yang , Huiwen Dong , Jian Yu

In this paper, we use spectral analysis to investigate transfer learning and study model sensitivity to frequency shortcuts in medical imaging. By analyzing the power spectrum density of both pre-trained and fine-tuned model gradients, as…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Yucheng Lu , Dovile Juodelyte , Jonathan D. Victor , Veronika Cheplygina

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Nishant Jain , Harkirat Behl , Yogesh Singh Rawat , Vibhav Vineet

This paper tackles the critical challenge of optimizing multi-modality trackers by effectively adapting pre-trained models for RGB data. Existing fine-tuning paradigms oscillate between excessive flexibility and over-restriction, both…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Zhiwen Chen , Jinjian Wu , Zhiyu Zhu , Yifan Zhang , Guangming Shi , Junhui Hou

Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models. However, fine-tuning reinforcement learning (RL) models remains…

Reinforcement learning (RL) has demonstrated remarkable capability in acquiring robot skills, but learning each new skill still requires substantial data collection for training. The pretrain-and-finetune paradigm offers a promising…

Robotics · Computer Science 2025-03-25 Ziang Zheng , Guojian Zhan , Bin Shuai , Shengtao Qin , Jiangtao Li , Tao Zhang , Shengbo Eben Li

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as the evaluation…

Machine Learning · Computer Science 2022-10-26 Hong Liu , Sang Michael Xie , Zhiyuan Li , Tengyu Ma

We propose a mask pretraining method for Graph Neural Networks (GNNs) to improve their performance on fitting potential energy surfaces, particularly in water systems. GNNs are pretrained by recovering spatial information related to…

Machine Learning · Computer Science 2024-06-21 Zehua Zhang , Zijie Li , Amir Barati Farimani

Accurate uncertainty estimation is vital to trustworthy machine learning, yet uncertainties typically have to be learned for each task anew. This work introduces the first pretrained uncertainty modules for vision models. Similar to…

Computer Vision and Pattern Recognition · Computer Science 2024-02-28 Michael Kirchhof , Mark Collier , Seong Joon Oh , Enkelejda Kasneci

Fine-tuning large pre-trained models has become the de facto strategy for developing both task-specific and general-purpose machine learning systems, including developing models that are safe to deploy. Despite its clear importance, there…

‹ Prev 1 4 5 6 7 8 10 Next ›