Black-box time-series domain adaptation via cross-prompt foundation model

Furqon, Muhammad Tanzil (avtor), Pratama, Mahardhika (avtor), Škrjanc, Igor (avtor), Liu, Lin (avtor), Habibullah, Habibullah (avtor), Dogancay, Kutluyil (avtor)

The black-box domain adaptation (BBDA) topic is developed to address the privacy and security issues where only an application programming interface (API) of the source model is available for domain adaptations. Although the BBDA topic has attracted growing research attentions, existing works mostly target the vision applications and are not directly applicable to the time-series applications possessing unique spatio-temporal characteristics. In addition, none of existing approaches have explored the strength of foundation model for black box time-series domain adaptation (BBTSDA). This paper proposes a concept of Cross-Prompt Foundation Model (CPFM) for the BBTSDA problems. CPFM is constructed under a dual branch network structure where each branch is equipped with a unique prompt to capture different characteristics of data distributions. In the domain adaptation phase, the reconstruction learning phases in the prompt and input levels are developed. All of which are built upon a time-series foundation model to overcome the spatio-temporal dynamic. Our rigorous experiments substantiate the advantage of CPFM achieving improved results with noticeable margins from its competitors in three time-series datasets of different application domains.

• Jezik: Angleški jezik
• Ključne besede: transfer learning, domain adaptation, black-box domain adaptation, time-series
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FE - Fakulteta za elektrotehniko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2026
• Št. strani: 13 str.
• Številčenje: Vol. 351, part B, [article no.] 116674
• PID: 20.500.12556/RUL-185274
• UDK: 004.852
• ISSN pri članku: 0950-7051
• DOI: 10.1016/j.knosys.2026.116674
• COBISS.SI-ID: 286442499
• Datum objave v RUL: 30.07.2026

Gradivo je del revije

• Naslov: Knowledge-based systems
• Skrajšan naslov: Knowl.-based syst.
• Založnik: Butterworth Scientific Ltd.
• ISSN: 0950-7051
• COBISS.SI-ID: 15019525

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: prenosno učenje, prilagajanje domeni, prilagajanje domeni pri modelu črne škatle, časovne vrste