Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| 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 |