FISformer: Replacing Self-Attention With a Fuzzy Inference System in Transformer Models for Time Series Forecasting
IEEE TRANSACTIONS ON FUZZY SYSTEMS, cilt.34, sa.8, ss.2437-2450, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 34 Sayı: 8
- Basım Tarihi: 2026
- Doi Numarası: 10.1109/tfuzz.2026.3690012
- Dergi Adı: IEEE TRANSACTIONS ON FUZZY SYSTEMS
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Compendex, INSPEC, zbMATH, Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Sayfa Sayıları: ss.2437-2450
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Erciyes Üniversitesi Adresli: Hayır
Özet
Transformers have achieved remarkable progress in time series forecasting, yet their reliance on deterministic dot-product attention limits their capacity to model uncertainty and nonlinear dependencies across multivariate temporal dimensions. To address this limitation, we propose a fuzzy inference system-driven Transformer (FISformer) that replaces conventional attention with a FIS interaction mechanism. In this framework, each query-key pair undergoes a fuzzy inference process for every feature dimension, where learnable membership functions and rule-based reasoning estimate tokenwise relational strengths. These FIS-derived interaction weights capture uncertainty and provide interpretable, continuous mappings between tokens. A softmax operation is applied along the token axis to normalize these weights, which are then combined with the corresponding value features through elementwise multiplication to yield the final context-enhanced token representations. This design fuses the interpretability and uncertainty modeling of fuzzy logic with the representational power of Transformers. Extensive experiments on multiple benchmark datasets demonstrate that FISformer achieves superior forecasting accuracy, noise robustness, and interpretability compared to state-of-the-art Transformer variants, establishing fuzzy inference as an effective alternative to conventional attention mechanisms.