Goal-oriented Communications based on Recursive Early Exit Neural Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916543662653440 |
|---|---|
| author | Pomponi, Jary Merluzzi, Mattia Devoto, Alessio Mota, Mateus Pontes Di Lorenzo, Paolo Scardapane, Simone |
| author_facet | Pomponi, Jary Merluzzi, Mattia Devoto, Alessio Mota, Mateus Pontes Di Lorenzo, Paolo Scardapane, Simone |
| contents | This paper presents a novel framework for goal-oriented semantic communications leveraging recursive early exit models. The proposed approach is built on two key components. First, we introduce an innovative early exit strategy that dynamically partitions computations, enabling samples to be offloaded to a server based on layer-wise recursive prediction dynamics that detect samples for which the confidence is not increasing fast enough over layers. Second, we develop a Reinforcement Learning-based online optimization framework that jointly determines early exit points, computation splitting, and offloading strategies, while accounting for wireless conditions, inference accuracy, and resource costs. Numerical evaluations in an edge inference scenario demonstrate the method's adaptability and effectiveness in striking an excellent trade-off between performance, latency, and resource efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19587 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Goal-oriented Communications based on Recursive Early Exit Neural Networks Pomponi, Jary Merluzzi, Mattia Devoto, Alessio Mota, Mateus Pontes Di Lorenzo, Paolo Scardapane, Simone Machine Learning This paper presents a novel framework for goal-oriented semantic communications leveraging recursive early exit models. The proposed approach is built on two key components. First, we introduce an innovative early exit strategy that dynamically partitions computations, enabling samples to be offloaded to a server based on layer-wise recursive prediction dynamics that detect samples for which the confidence is not increasing fast enough over layers. Second, we develop a Reinforcement Learning-based online optimization framework that jointly determines early exit points, computation splitting, and offloading strategies, while accounting for wireless conditions, inference accuracy, and resource costs. Numerical evaluations in an edge inference scenario demonstrate the method's adaptability and effectiveness in striking an excellent trade-off between performance, latency, and resource efficiency. |
| title | Goal-oriented Communications based on Recursive Early Exit Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2412.19587 |