English
Related papers

Related papers: Optimal Subarchitecture Extraction For BERT

200 papers

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…

Machine Learning · Computer Science 2023-01-25 Muralidhar Andoorveedu , Zhanda Zhu , Bojian Zheng , Gennady Pekhimenko

Transformer neural networks, particularly Bidirectional Encoder Representations from Transformers (BERT), have shown remarkable performance across various tasks such as classification, text summarization, and question answering. However,…

Machine Learning · Computer Science 2025-02-18 Matteo Bonino , Giorgia Ghione , Giansalvo Cirrincione

In graph instance representation learning, both the diverse graph instance sizes and the graph node orderless property have been the major obstacles that render existing representation learning models fail to work. In this paper, we will…

Machine Learning · Computer Science 2020-02-11 Jiawei Zhang

Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy…

Computer Vision and Pattern Recognition · Computer Science 2021-03-17 Wuyang Chen , Xinyu Gong , Zhangyang Wang

Bloom filters are a fundamental data structure for approximate membership queries, with applications ranging from data analytics to databases and genomics. Several variants have been proposed to accommodate parallel architectures. GPUs,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-18 Daniel Jünger , Kevin Kristensen , Yunsong Wang , Xiangyao Yu , Bertil Schmidt

BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the…

Computation and Language · Computer Science 2019-08-28 Nils Reimers , Iryna Gurevych

Many mission-critical systems are based on GPU for inference. It requires not only high recognition accuracy but also low latency in responding time. Although many studies are devoted to optimizing the structure of deep models for efficient…

Computer Vision and Pattern Recognition · Computer Science 2020-08-13 Ming Lin , Hesen Chen , Xiuyu Sun , Qi Qian , Hao Li , Rong Jin

Bit-serial architectures can handle Neural Networks (NNs) with different weight precisions, achieving higher resource efficiency compared with bit-parallel architectures. Besides, the weights contain abundant zero bits owing to the fault…

Hardware Architecture · Computer Science 2023-02-02 Wenhao Sun , Zhiwei Zou , Deng Liu , Wendi Sun , Song Chen , Yi Kang

Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks. However, these models contain a large amount of parameters. The emergence of even…

Computation and Language · Computer Science 2021-12-20 Ofir Zafrir , Guy Boudoukh , Peter Izsak , Moshe Wasserblat

Sampling-based planning has become a de facto standard for complex robots given its superior ability to rapidly explore high-dimensional configuration spaces. Most existing optimal sampling-based planning algorithms are sequential in nature…

Robotics · Computer Science 2020-09-10 R. Connor Lawson , Linda Wills , Panagiotis Tsiotras

In this paper we explore the parameter efficiency of BERT arXiv:1810.04805 on version 2.0 of the Stanford Question Answering dataset (SQuAD2.0). We evaluate the parameter efficiency of BERT while freezing a varying number of final…

Computation and Language · Computer Science 2020-03-04 Eric Hulburd

Most feature selection algorithms, especially wrapper methods, run inefficiently on CPU based platforms because of their high computational complexity. This inefficiency makes them unsuitable for processing large scale datasets. To address…

Machine Learning · Computer Science 2026-05-12 Xurui Li , Zhiguo Gan , Jiaming Zhang , Zheng Liu , Diannan Lu

In recent years, deep neural networks have had great success in machine learning and pattern recognition. Architecture size for a neural network contributes significantly to the success of any neural network. In this study, we optimize the…

Machine Learning · Computer Science 2021-01-19 Yigit Alparslan , Ethan Jacob Moyer , Isamu Mclean Isozaki , Daniel Schwartz , Adam Dunlop , Shesh Dave , Edward Kim

In the realm of neural architecture design, achieving high performance is largely reliant on the manual expertise of researchers. Despite the emergence of Neural Architecture Search (NAS) as a promising technique for automating this…

Machine Learning · Computer Science 2025-01-07 Yannis Y. He

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation…

Machine Learning · Computer Science 2019-12-02 Julia El Zini , Yara Rizk , Mariette Awad

This study explores the effectiveness of layer pruning for developing more efficient BERT models tailored to specific downstream tasks in low-resource languages. Our primary objective is to evaluate whether pruned BERT models can maintain…

Computation and Language · Computer Science 2025-01-03 Mayur Shirke , Amey Shembade , Madhushri Wagh , Pavan Thorat , Raviraj Joshi

In neural network topologies, algorithms are running on batches of data tensors. The batches of data are typically scheduled onto the computing cores which execute in parallel. For the algorithms running on batches of data, an optimal batch…

Performance · Computer Science 2020-02-18 Phani Kumar Nyshadham , Mohit Sinha , Biswajit Mishra , H S Vijay

In this work we provide new insights into the transformer architecture, and in particular, its best-known variant, BERT. First, we propose a method to measure the degree of non-linearity of different elements of transformers. Next, we focus…

Computation and Language · Computer Science 2021-05-10 Sumu Zhao , Damian Pascual , Gino Brunner , Roger Wattenhofer

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We…

Computation and Language · Computer Science 2020-04-28 Ji Xin , Raphael Tang , Jaejun Lee , Yaoliang Yu , Jimmy Lin

Neural architecture search (NAS) recently attracts much research attention because of its ability to identify better architectures than handcrafted ones. However, many NAS methods, which optimize the search process in a discrete search…

Machine Learning · Computer Science 2019-11-22 Quanming Yao , Ju Xu , Wei-Wei Tu , Zhanxing Zhu