EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FT-AFM: A Hybrid Transformer-Factorization Framework for Interpretable Click-Through Rate Prediction

Bubacarr Jallow, Jin-Taek Seong

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.

AbstractBibliografische AngabenZitierenVerwandte Studien

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}
}
Kostenlos starten →