COALA: A Practical and Vision-Centric Federated Learning Platform
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917731041804288 |
|---|---|
| author | Zhuang, Weiming Xu, Jian Chen, Chen Li, Jingtao Lyu, Lingjuan |
| author_facet | Zhuang, Weiming Xu, Jian Chen, Chen Li, Jingtao Lyu, Lingjuan |
| contents | We present COALA, a vision-centric Federated Learning (FL) platform, and a suite of benchmarks for practical FL scenarios, which we categorize into three levels: task, data, and model. At the task level, COALA extends support from simple classification to 15 computer vision tasks, including object detection, segmentation, pose estimation, and more. It also facilitates federated multiple-task learning, allowing clients to tackle multiple tasks simultaneously. At the data level, COALA goes beyond supervised FL to benchmark both semi-supervised FL and unsupervised FL. It also benchmarks feature distribution shifts other than commonly considered label distribution shifts. In addition to dealing with static data, it supports federated continual learning for continuously changing data in real-world scenarios. At the model level, COALA benchmarks FL with split models and different models in different clients. COALA platform offers three degrees of customization for these practical FL scenarios, including configuration customization, components customization, and workflow customization. We conduct systematic benchmarking experiments for the practical FL scenarios and highlight potential opportunities for further advancements in FL. Codes are open sourced at https://github.com/SonyResearch/COALA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16560 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | COALA: A Practical and Vision-Centric Federated Learning Platform Zhuang, Weiming Xu, Jian Chen, Chen Li, Jingtao Lyu, Lingjuan Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing We present COALA, a vision-centric Federated Learning (FL) platform, and a suite of benchmarks for practical FL scenarios, which we categorize into three levels: task, data, and model. At the task level, COALA extends support from simple classification to 15 computer vision tasks, including object detection, segmentation, pose estimation, and more. It also facilitates federated multiple-task learning, allowing clients to tackle multiple tasks simultaneously. At the data level, COALA goes beyond supervised FL to benchmark both semi-supervised FL and unsupervised FL. It also benchmarks feature distribution shifts other than commonly considered label distribution shifts. In addition to dealing with static data, it supports federated continual learning for continuously changing data in real-world scenarios. At the model level, COALA benchmarks FL with split models and different models in different clients. COALA platform offers three degrees of customization for these practical FL scenarios, including configuration customization, components customization, and workflow customization. We conduct systematic benchmarking experiments for the practical FL scenarios and highlight potential opportunities for further advancements in FL. Codes are open sourced at https://github.com/SonyResearch/COALA. |
| title | COALA: A Practical and Vision-Centric Federated Learning Platform |
| topic | Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2407.16560 |