CAAP: Class-Dependent Automatic Data Augmentation Based On Adaptive Policies For Time Series

no code implementations • 1 Apr 2024 • Tien-Yu Chang, Hao Dai, Vincent S. Tseng

We propose a novel deep learning-based approach called Class-dependent Automatic Adaptive Policies (CAAP) framework to overcome the notable class-dependent bias problem while maintaining the overall improvement in time-series data augmentation.

Data Augmentation Time Series

FLAG: Fast Label-Adaptive Aggregation for Multi-label Classification in Federated Learning

no code implementations • 27 Feb 2023 • Shih-Fang Chang, Benny Wei-Yun Hsu, Tien-Yu Chang, Vincent S. Tseng

Federated learning aims to share private data to maximize the data utility without privacy leakage.

Classification Federated Learning +2