English
Related papers

Related papers: Optimal Subarchitecture Extraction For BERT

200 papers

In recent times, BERT-based models have been extremely successful in solving a variety of natural language processing (NLP) tasks such as reading comprehension, natural language inference, sentiment analysis, etc. All BERT-based…

Computation and Language · Computer Science 2023-04-06 Sharath Nittur Sridhar , Anthony Sarah

Although pre-trained contextualized language models such as BERT achieve significant performance on various downstream tasks, current language representation still only focuses on linguistic objective at a specific granularity, which may…

Computation and Language · Computer Science 2021-01-01 Yian Li , Hai Zhao

Neural Networks can be effectively compressed through pruning, significantly reducing storage and compute demands while maintaining predictive performance. Simple yet effective methods like magnitude pruning remove less important parameters…

Machine Learning · Computer Science 2025-12-03 Max Zimmer , Megi Andoni , Christoph Spiegel , Sebastian Pokutta

We reproduce the central claims of Test-Time Training on Nearest Neighbors for Large Language Models (Hardt and Sun, 2024), which proposes adapting a language model at inference time by fine-tuning on retrieved nearest-neighbor sequences.…

Computation and Language · Computer Science 2025-11-24 Boyang Zhou , Johan Lindqvist , Lindsey Li

The design of neural network architectures for a new data set is a laborious task which requires human deep learning expertise. In order to make deep learning available for a broader audience, automated methods for finding a neural network…

Machine Learning · Computer Science 2019-06-07 Martin Wistuba

Recent work explored the potential of large-scale Transformer-based pre-trained models, especially Pre-trained Language Models (PLMs) in natural language processing. This raises many concerns from various perspectives, e.g., financial costs…

Computation and Language · Computer Science 2022-05-23 Yuxin Ren , Benyou Wang , Lifeng Shang , Xin Jiang , Qun Liu

This paper investigates the shared-memory Graph Transposition (GT) problem, a fundamental graph algorithm that is widely used in graph analytics and scientific computing. Previous GT algorithms have significant memory requirements that are…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-14 Mohsen Koohi Esfahani , Hans Vandierendonck

With the development of deep learning and Transformer-based pre-trained models like BERT, the accuracy of many NLP tasks has been dramatically improved. However, the large number of parameters and computations also pose challenges for their…

Computation and Language · Computer Science 2022-12-07 Siyuan Lu , Chenchen Zhou , Keli Xie , Jun Lin , Zhongfeng Wang

Transformer based architectures have become de-facto models used for a range of Natural Language Processing tasks. In particular, the BERT based models achieved significant accuracy gain for GLUE tasks, CoNLL-03 and SQuAD. However, BERT…

Computation and Language · Computer Science 2021-04-21 Sheng Shen , Zhen Dong , Jiayu Ye , Linjian Ma , Zhewei Yao , Amir Gholami , Michael W. Mahoney , Kurt Keutzer

Transformer-based models, specifically BERT, have propelled research in various NLP tasks. However, these models are limited to a maximum token limit of 512 tokens. Consequently, this makes it non-trivial to apply it in a practical setting…

Computation and Language · Computer Science 2023-11-01 Aman Jaiswal , Evangelos Milios

In the recent past, the success of Neural Architecture Search (NAS) has enabled researchers to broadly explore the design space using learning-based methods. Apart from finding better neural network architectures, the idea of automation has…

Machine Learning · Computer Science 2019-11-04 Qing Lu , Weiwen Jiang , Xiaowei Xu , Yiyu Shi , Jingtong Hu

Weight sharing is a popular approach to reduce the cost of neural architecture search (NAS) by reusing the weights of shared operators from previously trained child models. However, the rank correlation between the estimated accuracy and…

Computation and Language · Computer Science 2022-07-25 Jin Xu , Xu Tan , Kaitao Song , Renqian Luo , Yichong Leng , Tao Qin , Tie-Yan Liu , Jian Li

Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and…

Computer Vision and Pattern Recognition · Computer Science 2019-05-20 Vladimir Nekrasov , Hao Chen , Chunhua Shen , Ian Reid

Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting…

Artificial Intelligence · Computer Science 2024-11-01 Xuan Shen , Pu Zhao , Yifan Gong , Zhenglun Kong , Zheng Zhan , Yushu Wu , Ming Lin , Chao Wu , Xue Lin , Yanzhi Wang

We propose BERMo, an architectural modification to BERT, which makes predictions based on a hierarchy of surface, syntactic and semantic language features. We use linear combination scheme proposed in Embeddings from Language Models (ELMo)…

Computation and Language · Computer Science 2021-11-01 Sangamesh Kodge , Kaushik Roy

Training deep learning models, particularly Transformer-based architectures such as Large Language Models (LLMs), demands substantial computational resources and extended training periods. While optimal configuration and infrastructure…

Machine Learning · Computer Science 2024-12-30 Alireza Pourali , Arian Boukani , Hamzeh Khazaei

Training CNN for detection is time-consuming due to the large dataset and complex network modules, making it hard to search architectures on detection datasets directly, which usually requires vast search costs (usually tens and even…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Xiaoxing Wang , Jiale Lin , Junchi Yan , Juanping Zhao , Xiaokang Yang

The increasing size of language models necessitates a thorough analysis across multiple dimensions to assess trade-offs among crucial hardware metrics such as latency, energy consumption, GPU memory usage, and performance. Identifying…

We explore efficient neural architecture search methods and show that a simple yet powerful evolutionary algorithm can discover new architectures with excellent performance. Our approach combines a novel hierarchical genetic representation…

Machine Learning · Computer Science 2018-02-26 Hanxiao Liu , Karen Simonyan , Oriol Vinyals , Chrisantha Fernando , Koray Kavukcuoglu

We present a highly parameter efficient approach for Question Answering that significantly reduces the need for extended BERT fine-tuning. Our method uses information from the hidden state activations of each BERT transformer layer, which…

Computation and Language · Computer Science 2022-02-25 Siduo Jiang , Cristopher Benge , William Casey King
‹ Prev 1 4 5 6 7 8 10 Next ›