English
Related papers

Related papers: Optimizing Deeper Transformers on Small Datasets

200 papers

Transformer-based large language models have remarkable potential to accelerate design optimization for applications such as drug development and materials discovery. Self-supervised pretraining of transformer models requires large-scale…

Machine Learning · Computer Science 2023-10-27 Pei Zhang , Logan Kearney , Debsindhu Bhowmik , Zachary Fox , Amit K. Naskar , John Gounley

Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute. However, as frameworks specialize performance optimization to patterns in popular networks, they…

Machine Learning · Computer Science 2022-08-31 Oliver Rausch , Tal Ben-Nun , Nikoli Dryden , Andrei Ivanov , Shigang Li , Torsten Hoefler

Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-based models have…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Nithin Gopalakrishnan Nair , Jeya Maria Jose Valanarasu , Vishal M. Patel

Modern Deep Learning (DL) architectures based on transformers (e.g., BERT, RoBERTa) are exhibiting performance improvements across a number of natural language tasks. While such DL models have shown tremendous potential for use in software…

Software Engineering · Computer Science 2023-06-02 Agnieszka Ciborowska , Kostadin Damevski

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Computation and Language · Computer Science 2020-06-24 Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , Joseph E. Gonzalez

Pretrained transformer models have achieved state-of-the-art results in many tasks and benchmarks recently. Many state-of-the-art Language Models (LMs), however, do not scale well above the threshold of 512 input tokens. In specialized…

Computation and Language · Computer Science 2022-12-01 Joel Niklaus , Daniele Giofré

Skip connections and normalisation layers form two standard architectural components that are ubiquitous for the training of Deep Neural Networks (DNNs), but whose precise roles are poorly understood. Recent approaches such as Deep Kernel…

Machine Learning · Computer Science 2023-02-22 Bobby He , James Martens , Guodong Zhang , Aleksandar Botev , Andrew Brock , Samuel L Smith , Yee Whye Teh

We study the capabilities of the transformer architecture with varying depth. Specifically, we designed a novel set of sequence learning tasks to systematically evaluate and comprehend how the depth of transformer affects its ability to…

Machine Learning · Computer Science 2024-04-03 Xingwu Chen , Difan Zou

Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Martin Kišš , Michal Hradiš

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

Computer Vision and Pattern Recognition · Computer Science 2019-09-20 Tasfia Shermin , Shyh Wei Teng , Manzur Murshed , Guojun Lu , Ferdous Sohel , Manoranjan Paul

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very…

Machine Learning · Computer Science 2016-08-01 Gao Huang , Yu Sun , Zhuang Liu , Daniel Sedra , Kilian Weinberger

To analyze the scaling potential of deep tabular representation learning models, we introduce a novel Transformer-based architecture specifically tailored to tabular data and cross-table representation learning by utilizing table-specific…

Machine Learning · Computer Science 2023-10-02 Maximilian Schambach , Dominique Paul , Johannes S. Otterbach

Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time. This process necessitates storing copies of the model over time for each task that the pre-trained model is…

Computer Vision and Pattern Recognition · Computer Science 2023-09-22 Chaitanya Devaguptapu , Samarth Sinha , K J Joseph , Vineeth N Balasubramanian , Animesh Garg

Overparameterized transformer networks have obtained state of the art results in various natural language processing tasks, such as machine translation, language modeling, and question answering. These models contain hundreds of millions of…

Machine Learning · Computer Science 2019-09-26 Angela Fan , Edouard Grave , Armand Joulin

Transformers have achieved extraordinary success in modern machine learning due to their excellent ability to handle sequential data, especially in next-token prediction (NTP) tasks. However, the theoretical understanding of their…

Machine Learning · Computer Science 2024-10-01 Ruiquan Huang , Yingbin Liang , Jing Yang

Deep learning models need large amounts of data for training. In video recognition and classification, significant advances were achieved with the introduction of new large databases. However, the creation of large-databases for training is…

Computer Vision and Pattern Recognition · Computer Science 2021-07-05 Miguel Rodríguez Santander , Juan Hernández Albarracín , Adín Ramírez Rivera

While the availability of large datasets is perceived to be a key requirement for training deep neural networks, it is possible to train such models with relatively little data. However, compensating for the absence of large datasets…

Artificial Intelligence · Computer Science 2021-11-02 Mohammad Motamedi , Nikolay Sakharnykh , Tim Kaldewey

Scaling transformers has led to significant breakthroughs in many domains, leading to a paradigm in which larger versions of existing models are trained and released on a periodic basis. New instances of such models are typically trained…

Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance. However, residual connections may make the model…

Computation and Language · Computer Science 2024-04-05 Hongfei Xu , Yang Song , Qiuhui Liu , Josef van Genabith , Deyi Xiong

Deep learning (DL) techniques have been used to support several code-related tasks such as code summarization and bug-fixing. In particular, pre-trained transformer models are on the rise, also thanks to the excellent results they achieved…