A Comprehensive Study of Real-World Bugs in Machine Learning Model Optimization-Reference-Cited by-同舟云学术

A Comprehensive Study of Real-World Bugs in Machine Learning Model Optimization

Published:2023-05 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)
language:
Short-container-title:

Author:

Guan Hao¹,Xiao Ying²,Li Jiaying³,Liu Yepang²,Bai Guangdong¹

Affiliation:

1. The University of Queensland,Brisbane,Australia

2. Southern University of Science and Technology,Shenzhen,China

3. Microsoft Software Technology Center Asia,Beijing,China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10172484/10172342/10172690.pdf?arnumber=10172690

Reference54 articles.

1. Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning

2. Quantized neural networks: Training neural networks with low precision weights and activations;hubara;The Journal of Machine Learning Research,2017

3. ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression

4. The Deep Learning Compiler: A Comprehensive Survey

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Compatibility Issues in Deep Learning Systems: Problems and Opportunities;Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering;2023-11-30

2. Towards an Effective and Interpretable Refinement Approach for DNN Verification;2023 IEEE 23rd International Conference on Software Quality, Reliability, and Security (QRS);2023-10-22

3. Enhancing Federated Learning Robustness Using Data-Agnostic Model Pruning;Advances in Knowledge Discovery and Data Mining;2023