TY - JOUR
T1 - Time and frequency synergy for source-free time-series domain adaptations
AU - Furqon, Muhammad Tanzil
AU - Pratama, Mahardhika
AU - Shiddiqi, Ary
AU - Liu, Lin
AU - Habibullah, Habibullah
AU - Dogancay, Kutluyil
N1 - Publisher Copyright:
© 2024 The Author(s)
PY - 2025/3
Y1 - 2025/3
N2 - Notwithstanding that source-free domain adaptation (SFDA) has gained its prominence due to privacy protections of source samples in domain adaptations, very few works have been devoted to address time-series problems possessing temporal characteristics. Besides, existing works of source-free time-series domain adaptation (SFTSDA) have not exploited the potential of frequency features offering complementary information to boost the performances. This paper proposes time frequency domain adaptation (TFDA) to overcome the SFTSDA problems. TFDA fully utilizes time and frequency information via a dual branch network structure comprising time and frequency encoders. Consistencies of time and frequency domains are forced via the contrastive learning strategies in the time, frequency and time-frequency domains while applying the self-distillation concept to maintain the same. To further improve the performance, TFDA implements the uncertainty reduction strategy to combat the issue of domain shift and the curriculum learning strategy to deal with the noisy pseudo labels. Rigorous experiments with 3 time series datasets of different application domains confirm the advantage of TFDA over prior arts with noticeable margins. In addition, the theoretical analysis is provided to show the generalization bound of our approach.
AB - Notwithstanding that source-free domain adaptation (SFDA) has gained its prominence due to privacy protections of source samples in domain adaptations, very few works have been devoted to address time-series problems possessing temporal characteristics. Besides, existing works of source-free time-series domain adaptation (SFTSDA) have not exploited the potential of frequency features offering complementary information to boost the performances. This paper proposes time frequency domain adaptation (TFDA) to overcome the SFTSDA problems. TFDA fully utilizes time and frequency information via a dual branch network structure comprising time and frequency encoders. Consistencies of time and frequency domains are forced via the contrastive learning strategies in the time, frequency and time-frequency domains while applying the self-distillation concept to maintain the same. To further improve the performance, TFDA implements the uncertainty reduction strategy to combat the issue of domain shift and the curriculum learning strategy to deal with the noisy pseudo labels. Rigorous experiments with 3 time series datasets of different application domains confirm the advantage of TFDA over prior arts with noticeable margins. In addition, the theoretical analysis is provided to show the generalization bound of our approach.
KW - Source free domain adaptation
KW - Time-series analysis
KW - Unsupervised domain adaptation
UR - http://www.scopus.com/inward/record.url?scp=85211077269&partnerID=8YFLogxK
U2 - 10.1016/j.ins.2024.121734
DO - 10.1016/j.ins.2024.121734
M3 - Article
AN - SCOPUS:85211077269
SN - 0020-0255
VL - 695
JO - Information Sciences
JF - Information Sciences
M1 - 121734
ER -