FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918005800173568 |
|---|---|
| author | Kou, Wei-Bin Zhu, Guangxu Cheng, Bingyang Wang, Shuai Tang, Ming Wu, Yik-Chung |
| author_facet | Kou, Wei-Bin Zhu, Guangxu Cheng, Bingyang Wang, Shuai Tang, Ming Wu, Yik-Chung |
| contents | Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a promising paradigm for enhancing the generalization of AD models through privacy-preserving distributed learning. However, these FL AD models face significant temporal catastrophic forgetting when deployed in dynamically evolving environments, where continuous adaptation causes abrupt erosion of historical knowledge. This paper proposes Federated Exponential Moving Average (FedEMA), a novel framework that addresses this challenge through two integral innovations: (I) Server-side model's historical fitting capability preservation via fusing current FL round's aggregation model and a proposed previous FL round's exponential moving average (EMA) model; (II) Vehicle-side negative entropy regularization to prevent FL models' possible overfitting to EMA-introduced temporal patterns. Above two strategies empower FedEMA a dual-objective optimization that balances model generalization and adaptability. In addition, we conduct theoretical convergence analysis for the proposed FedEMA. Extensive experiments both on Cityscapes dataset and Camvid dataset demonstrate FedEMA's superiority over existing approaches, showing 7.12% higher mean Intersection-over-Union (mIoU). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00318 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving Kou, Wei-Bin Zhu, Guangxu Cheng, Bingyang Wang, Shuai Tang, Ming Wu, Yik-Chung Robotics Machine Learning Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a promising paradigm for enhancing the generalization of AD models through privacy-preserving distributed learning. However, these FL AD models face significant temporal catastrophic forgetting when deployed in dynamically evolving environments, where continuous adaptation causes abrupt erosion of historical knowledge. This paper proposes Federated Exponential Moving Average (FedEMA), a novel framework that addresses this challenge through two integral innovations: (I) Server-side model's historical fitting capability preservation via fusing current FL round's aggregation model and a proposed previous FL round's exponential moving average (EMA) model; (II) Vehicle-side negative entropy regularization to prevent FL models' possible overfitting to EMA-introduced temporal patterns. Above two strategies empower FedEMA a dual-objective optimization that balances model generalization and adaptability. In addition, we conduct theoretical convergence analysis for the proposed FedEMA. Extensive experiments both on Cityscapes dataset and Camvid dataset demonstrate FedEMA's superiority over existing approaches, showing 7.12% higher mean Intersection-over-Union (mIoU). |
| title | FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2505.00318 |