Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference
Author:
Affiliation:
1. Intel Labs,San Diego,USA
2. University of Southern California,Los Angeles,USA
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/10208270/10208119/10208315.pdf?arnumber=10208315
Reference24 articles.
1. DNR
2. Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation
3. and Peter A Beerel. Learning to linearize deep neural networks for secure and efficient private inference;kundu;ICLRE,2023
4. Wide residual networks;zagoruyko,2016
5. AttentionLite: Towards Efficient Self-Attention Models for Vision
Cited by 7 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. Joint learning of video scene detection and annotation via multi-modal adaptive context network;Expert Systems with Applications;2024-09
2. Please Tell Me More: Privacy Impact of Explainability through the Lens of Membership Inference Attack;2024 IEEE Symposium on Security and Privacy (SP);2024-05-19
3. Sensi-Bert: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient Language Model;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
4. Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
5. RNA-ViT: Reduced-Dimension Approximate Normalized Attention Vision Transformers for Latency Efficient Private Inference;2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD);2023-10-28
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3