Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Defa, Huang, Hongzhi, Huang, Zihao, Zeng, Yutao, Mao, Yunyao, Wu, Banggu, Min, Qiyang, Zhou, Xun
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2409.19606
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910879571771392
author Zhu, Defa
Huang, Hongzhi
Huang, Zihao
Zeng, Yutao
Mao, Yunyao
Wu, Banggu
Min, Qiyang
Zhou, Xun
author_facet Zhu, Defa
Huang, Hongzhi
Huang, Zihao
Zeng, Yutao
Mao, Yunyao
Wu, Banggu
Min, Qiyang
Zhou, Xun
contents We present hyper-connections, a simple yet effective method that can serve as an alternative to residual connections. This approach specifically addresses common drawbacks observed in residual connection variants, such as the seesaw effect between gradient vanishing and representation collapse. Theoretically, hyper-connections allow the network to adjust the strength of connections between features at different depths and dynamically rearrange layers. We conduct experiments focusing on the pre-training of large language models, including dense and sparse models, where hyper-connections show significant performance improvements over residual connections. Additional experiments conducted on vision tasks also demonstrate similar improvements. We anticipate that this method will be broadly applicable and beneficial across a wide range of AI problems.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19606
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hyper-Connections
Zhu, Defa
Huang, Hongzhi
Huang, Zihao
Zeng, Yutao
Mao, Yunyao
Wu, Banggu
Min, Qiyang
Zhou, Xun
Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
We present hyper-connections, a simple yet effective method that can serve as an alternative to residual connections. This approach specifically addresses common drawbacks observed in residual connection variants, such as the seesaw effect between gradient vanishing and representation collapse. Theoretically, hyper-connections allow the network to adjust the strength of connections between features at different depths and dynamically rearrange layers. We conduct experiments focusing on the pre-training of large language models, including dense and sparse models, where hyper-connections show significant performance improvements over residual connections. Additional experiments conducted on vision tasks also demonstrate similar improvements. We anticipate that this method will be broadly applicable and beneficial across a wide range of AI problems.
title Hyper-Connections
topic Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
url https://arxiv.org/abs/2409.19606