FedMIL: Federated-Multiple Instance Learning for Video Analysis with Optimized DPP Scheduling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910382992392192 |
|---|---|
| author | Bastola, Ashish Wang, Hao Chen, Xiwen Razi, Abolfazl |
| author_facet | Bastola, Ashish Wang, Hao Chen, Xiwen Razi, Abolfazl |
| contents | Many AI platforms, including traffic monitoring systems, use Federated Learning (FL) for decentralized sensor data processing for learning-based applications while preserving privacy and ensuring secured information transfer. On the other hand, applying supervised learning to large data samples, like high-resolution images requires intensive human labor to label different parts of a data sample. Multiple Instance Learning (MIL) alleviates this challenge by operating over labels assigned to the 'bag' of instances. In this paper, we introduce Federated Multiple-Instance Learning (FedMIL). This framework applies federated learning to boost the training performance in video-based MIL tasks such as vehicle accident detection using distributed CCTV networks. However, data sources in decentralized settings are not typically Independently and Identically Distributed (IID), making client selection imperative to collectively represent the entire dataset with minimal clients. To address this challenge, we propose DPPQ, a framework based on the Determinantal Point Process (DPP) with a quality-based kernel to select clients with the most diverse datasets that achieve better performance compared to both random selection and current DPP-based client selection methods even with less data utilization in the majority of non-IID cases. This offers a significant advantage for deployment on edge devices with limited computational resources, providing a reliable solution for training AI models in massive smart sensor networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17331 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedMIL: Federated-Multiple Instance Learning for Video Analysis with Optimized DPP Scheduling Bastola, Ashish Wang, Hao Chen, Xiwen Razi, Abolfazl Distributed, Parallel, and Cluster Computing Information Theory Many AI platforms, including traffic monitoring systems, use Federated Learning (FL) for decentralized sensor data processing for learning-based applications while preserving privacy and ensuring secured information transfer. On the other hand, applying supervised learning to large data samples, like high-resolution images requires intensive human labor to label different parts of a data sample. Multiple Instance Learning (MIL) alleviates this challenge by operating over labels assigned to the 'bag' of instances. In this paper, we introduce Federated Multiple-Instance Learning (FedMIL). This framework applies federated learning to boost the training performance in video-based MIL tasks such as vehicle accident detection using distributed CCTV networks. However, data sources in decentralized settings are not typically Independently and Identically Distributed (IID), making client selection imperative to collectively represent the entire dataset with minimal clients. To address this challenge, we propose DPPQ, a framework based on the Determinantal Point Process (DPP) with a quality-based kernel to select clients with the most diverse datasets that achieve better performance compared to both random selection and current DPP-based client selection methods even with less data utilization in the majority of non-IID cases. This offers a significant advantage for deployment on edge devices with limited computational resources, providing a reliable solution for training AI models in massive smart sensor networks. |
| title | FedMIL: Federated-Multiple Instance Learning for Video Analysis with Optimized DPP Scheduling |
| topic | Distributed, Parallel, and Cluster Computing Information Theory |
| url | https://arxiv.org/abs/2403.17331 |