End-to-end prior-guided graph attention network with differentiable structural priors for interpretable mobile interface layout scoring
Computer Science and Information Systems · 2026 · (00) · 52-52
DOI: 10.2298/csis260330052z ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Science and Information Systems, 2026. Verfasst von Long Zeng und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Automated assessment of mobile-interface aesthetics remains difficult because professional judgments depend on spatial relations among components, whereas image-only models mainly summarize global appearance. This study develops an interpretable end-to-end scorer for static mobile screenshots. The proposed prior-guided graph attention network combines a YOLOv10 component detector, a ResNet-50 visual stream, and a graph stream whose attention is modulated by differentiable priors for proximity, alignment, white space, and touchtarget accessibility. Comparisons with convolutional, graph, and transformer baselines were conducted on app-level splits of the MUD and CLAY datasets. On MUD, the method obtained a weighted root mean square error of 0.387 and a Spearman rank correlation of 0.856, improving the strongest convolutional baseline by 14.3%. Ablation, detector-sensitivity, cross-dataset, and expert blind-test analyses showed that the structural priors improve accuracy, transferability, and diagnostic agreement while retaining end-to-end latency of 35 milliseconds per screen.
Zitieren
APA
Zeng, L., Wang, Z., Zuo, W., & Chan, J. (2026). End-to-end prior-guided graph attention network with differentiable structural priors for interpretable mobile interface layout scoring. Computer Science and Information Systems, 52-52. https://doi.org/10.2298/csis260330052z
Vancouver
Zeng L, Wang Z, Zuo W, Chan J. End-to-end prior-guided graph attention network with differentiable structural priors for interpretable mobile interface layout scoring. Computer Science and Information Systems. 2026:52-52. doi:10.2298/csis260330052z
BibTeX
@article{Zeng2026,
author = {Zeng, Long and Wang, Zi and Zuo, Wen and Chan, Jun},
title = {End-to-end prior-guided graph attention network with differentiable structural priors for interpretable mobile interface layout scoring},
journal = {Computer Science and Information Systems},
year = {2026},
number = {00},
pages = {52--52},
doi = {10.2298/csis260330052z}
}
EUVIMED