English
Related papers

Related papers: LiteTransformerSearch: Training-free Neural Archit…

200 papers

With the flourish of differentiable neural architecture search (NAS), automatically searching latency-constrained architectures gives a new perspective to reduce human labor and expertise. However, the searched architectures are usually…

Computer Vision and Pattern Recognition · Computer Science 2020-08-13 Yibo Hu , Xiang Wu , Ran He

Transferable neural architecture search (TNAS) has been introduced to design efficient neural architectures for multiple tasks, to enhance the practical applicability of NAS in real-world scenarios. In TNAS, architectural knowledge…

Machine Learning · Computer Science 2024-12-19 Xun Zhou , Xingyu Wu , Liang Feng , Zhichao Lu , Kay Chen Tan

We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performance for image…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Boyu Chen , Peixia Li , Chuming Li , Baopu Li , Lei Bai , Chen Lin , Ming Sun , Junjie yan , Wanli Ouyang

The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be slow and expensive;…

Machine Learning · Computer Science 2021-06-14 Joseph Mellor , Jack Turner , Amos Storkey , Elliot J. Crowley

Task-agnostic pre-training followed by task-specific fine-tuning is a default approach to train NLU models. Such models need to be deployed on devices across the cloud and the edge with varying resource and accuracy constraints. For a given…

Machine Learning · Computer Science 2021-10-12 Vinod Ganesan , Gowtham Ramesh , Pratyush Kumar

Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive experiments have shown that, prominent neural architectures,…

Machine Learning · Computer Science 2021-11-18 Yuhong Li , Cong Hao , Pan Li , Jinjun Xiong , Deming Chen

Recently, Neural Architecture Search has achieved great success in large-scale image classification. In contrast, there have been limited works focusing on architecture search for object detection, mainly because the costly ImageNet…

Computer Vision and Pattern Recognition · Computer Science 2019-09-06 Junran Peng , Ming Sun , Zhaoxiang Zhang , Tieniu Tan , Junjie Yan

Sub-billion-parameter Transformer language models are increasingly deployed on edge devices, where the privacy, latency, and operating-cost advantages of on-device inference are constrained by tight memory-bandwidth, energy, and thermal…

Machine Learning · Computer Science 2026-05-19 Xinting Jiang , Junyi Luo , Ruichen Qi , Kauna Lei , Ben Laurie , Gregory Kielian , Mehdi Saligane

Efficient deployment of neural networks (NN) requires the co-optimization of accuracy and latency. For example, hardware-aware neural architecture search has been used to automatically find NN architectures that satisfy a latency constraint…

Machine Learning · Computer Science 2024-03-06 Yash Akhauri , Mohamed S. Abdelfattah

We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS). Different from existing hardware-aware NAS which assumes a fixed hardware design and explores the neural architecture search…

Machine Learning · Computer Science 2020-01-14 Weiwen Jiang , Lei Yang , Edwin Sha , Qingfeng Zhuge , Shouzhen Gu , Sakyasingha Dasgupta , Yiyu Shi , Jingtong Hu

Pareto front profiling in multi-objective optimization (MOO), i.e., finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives that require training a neural network. Typically, in MOO for neural…

Machine Learning · Computer Science 2025-02-06 Rhea Sanjay Sukthanker , Arber Zela , Benedikt Staffler , Samuel Dooley , Josif Grabocka , Frank Hutter

Transformer-based neural models are used in many AI applications. Training these models is expensive, as it takes huge GPU resources and long duration. It is challenging because typical data like sentences have variable lengths, and…

Computation and Language · Computer Science 2022-06-17 Xiaohui Wang , Yang Wei , Ying Xiong , Guyue Huang , Xian Qian , Yufei Ding , Mingxuan Wang , Lei Li

While pre-trained language models (e.g., BERT) have achieved impressive results on different natural language processing tasks, they have large numbers of parameters and suffer from big computational and memory costs, which make them…

Computation and Language · Computer Science 2021-06-01 Jin Xu , Xu Tan , Renqian Luo , Kaitao Song , Jian Li , Tao Qin , Tie-Yan Liu

This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network…

Computation and Language · Computer Science 2025-11-03 Shang Wang , Huanrong Tang , Jianquan Ouyang

Previous works on meta-learning either relied on elaborately hand-designed network structures or adopted specialized learning rules to a particular domain. We propose a universal framework to optimize the meta-learning process automatically…

Machine Learning · Computer Science 2019-09-10 Xinyue Zheng , Peng Wang , Qigang Wang , Zhongchao shi , Feiyu Xu

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

We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL). Existing NAS methods typically define different search spaces according to different tasks. In order to adapt to different task…

Machine Learning · Computer Science 2020-04-01 Yuan Gao , Haoping Bai , Zequn Jie , Jiayi Ma , Kui Jia , Wei Liu

Pre-trained language models (PLMs) have achieved great success in natural language processing. Most of PLMs follow the default setting of architecture hyper-parameters (e.g., the hidden dimension is a quarter of the intermediate dimension…

Computation and Language · Computer Science 2021-07-30 Yichun Yin , Cheng Chen , Lifeng Shang , Xin Jiang , Xiao Chen , Qun Liu

Transformer-based pre-trained language models like BERT and its variants have recently achieved promising performance in various natural language processing (NLP) tasks. However, the conventional paradigm constructs the backbone by purely…

Computation and Language · Computer Science 2022-02-08 Jiahui Gao , Hang Xu , Han Shi , Xiaozhe Ren , Philip L. H. Yu , Xiaodan Liang , Xin Jiang , Zhenguo Li

Neural Architecture Search (NAS) has emerged as one of the effective methods to design the optimal neural network architecture automatically. Although neural architectures have achieved human-level performances in several tasks, few of them…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Caiyang Yu , Xianggen Liu , Yifan Wang , Yun Liu , Wentao Feng , Deng Xiong , Chenwei Tang , Jiancheng Lv