LAMBO: Large AI Model Empowered Edge Intelligence
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911975659798528 |
|---|---|
| author | Dong, Li Jiang, Feibo Peng, Yubo Wang, Kezhi Yang, Kun Pan, Cunhua Schober, Robert |
| author_facet | Dong, Li Jiang, Feibo Peng, Yubo Wang, Kezhi Yang, Kun Pan, Cunhua Schober, Robert |
| contents | Next-generation edge intelligence is anticipated to benefit various applications via offloading techniques. However, traditional offloading architectures face several issues, including heterogeneous constraints, partial perception, uncertain generalization, and lack of tractability. In this paper, we propose a Large AI Model-Based Offloading (LAMBO) framework with over one billion parameters for solving these problems. We first use input embedding (IE) to achieve normalized feature representation with heterogeneous constraints and task prompts. Then, we introduce a novel asymmetric encoder-decoder (AED) as the decision-making model, which is an improved transformer architecture consisting of a deep encoder and a shallow decoder for global perception and decision. Next, actor-critic learning (ACL) is used to pre-train the AED for different optimization tasks under corresponding prompts, enhancing the AED's generalization in multi-task scenarios. Finally, we propose an active learning from expert feedback (ALEF) method to fine-tune the decoder of the AED for tracking changes in dynamic environments. Our simulation results validate the advantages of the proposed LAMBO framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_15078 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | LAMBO: Large AI Model Empowered Edge Intelligence Dong, Li Jiang, Feibo Peng, Yubo Wang, Kezhi Yang, Kun Pan, Cunhua Schober, Robert Artificial Intelligence Networking and Internet Architecture Next-generation edge intelligence is anticipated to benefit various applications via offloading techniques. However, traditional offloading architectures face several issues, including heterogeneous constraints, partial perception, uncertain generalization, and lack of tractability. In this paper, we propose a Large AI Model-Based Offloading (LAMBO) framework with over one billion parameters for solving these problems. We first use input embedding (IE) to achieve normalized feature representation with heterogeneous constraints and task prompts. Then, we introduce a novel asymmetric encoder-decoder (AED) as the decision-making model, which is an improved transformer architecture consisting of a deep encoder and a shallow decoder for global perception and decision. Next, actor-critic learning (ACL) is used to pre-train the AED for different optimization tasks under corresponding prompts, enhancing the AED's generalization in multi-task scenarios. Finally, we propose an active learning from expert feedback (ALEF) method to fine-tune the decoder of the AED for tracking changes in dynamic environments. Our simulation results validate the advantages of the proposed LAMBO framework. |
| title | LAMBO: Large AI Model Empowered Edge Intelligence |
| topic | Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2308.15078 |