Toward Trustworthy On-Device AI: A Quantization-Robust Parameterized Hybrid Neural Filtering Framework

Sangwoo Hong, Seung-Wook Kim, Seunghyun Moon and Seowon Ji ()
Additional contact information
Sangwoo Hong: Department of Computer Science and Engineering, Konkuk University, Seoul 05029, Republic of Korea
Seung-Wook Kim: Division of Electrical and Communication Engineering, Pukyong National University, Busan 48513, Republic of Korea
Seunghyun Moon: Department of Electrical and Electronics Engineering, Konkuk University, Seoul 05029, Republic of Korea
Seowon Ji: Department of Computer Science and Engineering, Konkuk University, Seoul 05029, Republic of Korea

Mathematics, 2025, vol. 13, issue 21, 1-19

Abstract: Recent advances in deep learning have led to a proliferation of AI services for the general public. Consequently, constructing trustworthy AI systems that operate on personal devices has become a crucial challenge. While on-device processing is critical for privacy-preserving and latency-sensitive applications, conventional deep learning approaches often suffer from instability under quantization and high computational costs. Toward a trustworthy and efficient on-device solution for image processing, we present a hybrid neural filtering framework that combines the representational power of lightweight neural networks with the stability of classical filters. In our framework, the neural network predicts a low-dimensional parameter map that guides the filter’s behavior, effectively decoupling parameter estimation from the final image synthesis. This design enables a truly trustworthy AI system by operating entirely on-device, which eliminates the reliance on servers and significantly reduces computational cost. To ensure quantization robustness, we introduce a basis-decomposed parameterization, a design mathematically proven to bound reconstruction errors. Our network predicts a set of basis maps that are combined via fixed coefficients to form the final guidance. This architecture is intrinsically robust to quantization and supports runtime-adaptive precision without retraining. Experiments on depth map super-resolution validate our approach. Our framework demonstrates exceptional quantization robustness, exhibiting no performance degradation under 8-bit quantization, whereas a baseline suffers a significant 1.56 dB drop. Furthermore, our model’s significantly lower Mean Squared Error highlights its superior stability, providing a practical and mathematically grounded pathway toward trustworthy on-device AI.

Keywords: trustworthy AI; on-device AI; hybrid neural filtering; basis decomposition (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/21/3447/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/21/3447/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:21:p:3447-:d:1782158

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().