English
Related papers

Related papers: Optimal Subarchitecture Extraction For BERT

200 papers

Transformer architectures are designed by trial and error: the number of attention heads, the depth, and the head size are fixed before training begins, with no mathematical principle to guide the choice. The result is systematic structural…

Machine Learning · Computer Science 2026-04-14 Giansalvo Cirrincione

Neural information retrieval architectures based on transformers such as BERT are able to significantly improve system effectiveness over traditional sparse models such as BM25. Though highly effective, these neural approaches are very…

Information Retrieval · Computer Science 2022-04-26 Antonio Mallia , Joel Mackenzie , Torsten Suel , Nicola Tonellotto

Large pretrained language models such as BERT suffer from slow inference and high memory usage, due to their huge size. Recent approaches to compressing BERT rely on iterative pruning and knowledge distillation, which, however, are often…

Computation and Language · Computer Science 2025-02-07 Hyemin Lim , Jaeyeon Lee , Dong-Wan Choi

The recent advent of automated neural network architecture search led to several methods that outperform state-of-the-art human-designed architectures. However, these approaches are computationally expensive, in extreme cases consuming GPU…

Machine Learning · Computer Science 2019-03-11 Martin Wistuba , Tejaswini Pedapati

Pre-trained contextualized language models such as BERT have shown great effectiveness in a wide range of downstream Natural Language Processing (NLP) tasks. However, the effective representations offered by the models target at each token…

Computation and Language · Computer Science 2020-08-04 Yian Li , Hai Zhao

We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of…

Neural and Evolutionary Computing · Computer Science 2016-06-13 Audrūnas Gruslys , Remi Munos , Ivo Danihelka , Marc Lanctot , Alex Graves

Parameter-efficient tuning (PET) methods fit pre-trained language models (PLMs) to downstream tasks by either computing a small compressed update for a subset of model parameters, or appending and fine-tuning a small number of new model…

Computation and Language · Computer Science 2023-05-29 Neal Lawton , Anoop Kumar , Govind Thattai , Aram Galstyan , Greg Ver Steeg

We present BlockBERT, a lightweight and efficient BERT model for better modeling long-distance dependencies. Our model extends BERT by introducing sparse block structures into the attention matrix to reduce both memory consumption and…

Computation and Language · Computer Science 2020-11-03 Jiezhong Qiu , Hao Ma , Omer Levy , Scott Wen-tau Yih , Sinong Wang , Jie Tang

Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to…

Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use…

Machine Learning · Computer Science 2020-06-12 Peiye Liu , Bo Wu , Huadong Ma , Mingoo Seok

Fine-tuning BERT-based models is resource-intensive in memory, computation, and time. While many prior works aim to improve inference efficiency via compression techniques, e.g., pruning, these works do not explicitly address the…

Computation and Language · Computer Science 2022-08-04 Danilo Vucetic , Mohammadreza Tayaranian , Maryam Ziaeefard , James J. Clark , Brett H. Meyer , Warren J. Gross

Pretrained transformer-encoder models like DeBERTaV3 and ModernBERT introduce architectural advancements aimed at improving efficiency and performance. Although the authors of ModernBERT report improved performance over DeBERTaV3 on several…

Computation and Language · Computer Science 2025-11-17 Wissam Antoun , Benoît Sagot , Djamé Seddah

Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Zhaohui Yang , Yunhe Wang , Xinghao Chen , Boxin Shi , Chao Xu , Chunjing Xu , Qi Tian , Chang Xu

We consider the problem of finding the set of architectural parameters for a chosen deep neural network which is optimal under three metrics: parameter size, inference speed, and error rate. In this paper we state the problem formally, and…

Machine Learning · Computer Science 2020-10-19 Adrian de Wynter

Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and…

Machine Learning · Computer Science 2021-09-29 Prakhar Ganesh , Yao Chen , Xin Lou , Mohammad Ali Khan , Yin Yang , Hassan Sajjad , Preslav Nakov , Deming Chen , Marianne Winslett

Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous computation resources and extremely long training time for both…

Computation and Language · Computer Science 2021-06-09 Xiaohan Chen , Yu Cheng , Shuohang Wang , Zhe Gan , Zhangyang Wang , Jingjing Liu

Although large pre-trained models of code have delivered significant advancements in various code processing tasks, there is an impediment to the wide and fluent adoption of these powerful models in software developers' daily workflow:…

Software Engineering · Computer Science 2022-09-07 Jieke Shi , Zhou Yang , Bowen Xu , Hong Jin Kang , David Lo

Training vision or language models on large datasets can take days, if not weeks. We show that averaging the weights of the k latest checkpoints, each collected at the end of an epoch, can speed up the training progression in terms of loss…

Machine Learning · Computer Science 2022-10-07 Jean Kaddour

This paper presents the design and evaluation of a GPU-accelerated inference pipeline for transformer models using NVIDIA TensorRT with mixed-precision optimization. We evaluate BERT-base (110M parameters) and GPT-2 (124M parameters) across…

Machine Learning · Computer Science 2026-03-31 Soutrik Mukherjee , Sangwhan Cha

Despite the great success in Natural Language Processing (NLP) area, large pre-trained language models like BERT are not well-suited for resource-constrained or real-time applications owing to the large number of parameters and slow…

Computation and Language · Computer Science 2021-07-02 Keli Xie , Siyuan Lu , Meiqi Wang , Zhongfeng Wang