FT-AFM: A Hybrid Transformer-Factorization Framework for Interpretable Click-Through Rate Prediction
IEEE Access · 2026 · 14 · 97559-97574
DOI: 10.1109/access.2026.3695521 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Bubacarr Jallow und 1 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Korean Government.
Abstract (Originalsprache)
Click-through rate (CTR) prediction requires balancing predictive performance with model interpretability, which is essential for accountability in industrial advertising systems. While transformer-based architectures achieve high accuracy through implicit learning of complex feature interactions, they often operate as black boxes with limited transparency in decision-making. This paper presents FT-AFM, a hybrid framework that combines a transformer-based feature tokenization backbone for context-aware representation learning with an Attentional Factorization Machine (AFM) for explicit attention-weighted pairwise interaction modeling. Through shared embeddings across two coordinated branches, FT-AFM captures global field-wise dependencies while revealing the relative importance of individual feature interactions. Evaluations on three large-scale benchmarks—Criteo, Outbrain, and Avazu—show that FT-AFM achieves competitive AUC scores of 0.8076, 0.7003, and 0.7386, respectively, while remaining close to strong transformer-based baselines. We further introduce a deletion-based inference-time sensitivity protocol to examine whether the learned attention weights are meaningfully related to prediction behavior under interaction masking. Results suggest that FT-AFM offers a practical accuracy–interpretability trade-off for large-scale CTR prediction by enabling explicit interaction-level analysis while maintaining competitive predictive performance.
Förderung
- National Research Foundation of Korea
- Korean Government
Zitieren
APA
Jallow, B., & Seong, J. (2026). FT-AFM: A Hybrid Transformer-Factorization Framework for Interpretable Click-Through Rate Prediction. IEEE Access, 14, 97559-97574. https://doi.org/10.1109/access.2026.3695521
Vancouver
Jallow B, Seong J. FT-AFM: A Hybrid Transformer-Factorization Framework for Interpretable Click-Through Rate Prediction. IEEE Access. 2026;14:97559-97574. doi:10.1109/access.2026.3695521
BibTeX
@article{Jallow2026,
author = {Jallow, Bubacarr and Seong, Jin-Taek},
title = {FT-AFM: A Hybrid Transformer-Factorization Framework for Interpretable Click-Through Rate Prediction},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {97559--97574},
doi = {10.1109/access.2026.3695521}
}
EUVIMED