Academic Journal
Beyond Classical Positional Encodings: A Learnable QFT-Inspired Framework for Transformer Language Models.
| Τίτλος: | Beyond Classical Positional Encodings: A Learnable QFT-Inspired Framework for Transformer Language Models. |
|---|---|
| Συγγραφείς: | Tehsin, Sara, Akram, Tallha, Naqvi, Syed Rameez, Alharbi, Meshal, Alabduljabbar, Abdulrahman |
| Πηγή: | Computers, Materials & Continua; 2026, Vol. 88 Issue 3, p1-24, 24p |
| Θεματικοί όροι: | Fourier transforms, Encoding, Natural language processing, Language models, Machine learning, Artificial neural networks |
| Περίληψη: | Transformers have become the dominant architecture for sequence modeling in natural language processing; however, their effectiveness critically depends on how positional information is encoded. Conventional positional encodings, while effective, may have limited structural flexibility for capturing complex global sequence relationships. Recent quantum-inspired approaches have sought to address this limitation, yet many either oversimplify quantum principles or introduce substantial computational or hardware overhead. We introduce a novel Quantum Fourier Transform (QFT)-inspired positional encoding scheme for transformers, motivated by the structured frequency representation of the QFT. Unlike prior approaches that either emulate quantum operations superficially or require complex circuit constructions, the proposed method provides a learnable hybrid encoding that preserves quantum-inspired structure while remaining aligned with hardware-efficient circuit primitives and structurally compatible with future near-term quantum implementations. Experiments on WikiText-103 indicate that the proposed encoding achieves competitive perplexity, improved robustness to input scrambling, and stable training behavior relative to alternative quantum-inspired baselines under the evaluated settings. Preliminary circuit-level simulations further suggest favorable noise resilience of the associated encoding primitives. These findings support the potential utility of incorporating quantum-inspired design principles into deep learning architectures and provide a foundation for future exploration at the interface of quantum computing and transformer-based natural language processing (NLP). [ABSTRACT FROM AUTHOR] |
| Copyright of Computers, Materials & Continua is the property of Tech Science Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Βάση Δεδομένων: | Complementary Index |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 195844847 RelevancyScore: 1082 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1082.42749023438 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Beyond Classical Positional Encodings: A Learnable QFT-Inspired Framework for Transformer Language Models. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Tehsin%2C+Sara%22">Tehsin, Sara</searchLink><br /><searchLink fieldCode="AR" term="%22Akram%2C+Tallha%22">Akram, Tallha</searchLink><br /><searchLink fieldCode="AR" term="%22Naqvi%2C+Syed+Rameez%22">Naqvi, Syed Rameez</searchLink><br /><searchLink fieldCode="AR" term="%22Alharbi%2C+Meshal%22">Alharbi, Meshal</searchLink><br /><searchLink fieldCode="AR" term="%22Alabduljabbar%2C+Abdulrahman%22">Alabduljabbar, Abdulrahman</searchLink> – Name: TitleSource Label: Source Group: Src Data: Computers, Materials & Continua; 2026, Vol. 88 Issue 3, p1-24, 24p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Fourier+transforms%22">Fourier transforms</searchLink><br /><searchLink fieldCode="DE" term="%22Encoding%22">Encoding</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing%22">Natural language processing</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Transformers have become the dominant architecture for sequence modeling in natural language processing; however, their effectiveness critically depends on how positional information is encoded. Conventional positional encodings, while effective, may have limited structural flexibility for capturing complex global sequence relationships. Recent quantum-inspired approaches have sought to address this limitation, yet many either oversimplify quantum principles or introduce substantial computational or hardware overhead. We introduce a novel Quantum Fourier Transform (QFT)-inspired positional encoding scheme for transformers, motivated by the structured frequency representation of the QFT. Unlike prior approaches that either emulate quantum operations superficially or require complex circuit constructions, the proposed method provides a learnable hybrid encoding that preserves quantum-inspired structure while remaining aligned with hardware-efficient circuit primitives and structurally compatible with future near-term quantum implementations. Experiments on WikiText-103 indicate that the proposed encoding achieves competitive perplexity, improved robustness to input scrambling, and stable training behavior relative to alternative quantum-inspired baselines under the evaluated settings. Preliminary circuit-level simulations further suggest favorable noise resilience of the associated encoding primitives. These findings support the potential utility of incorporating quantum-inspired design principles into deep learning architectures and provide a foundation for future exploration at the interface of quantum computing and transformer-based natural language processing (NLP). [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Computers, Materials & Continua is the property of Tech Science Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=195844847 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.32604/cmc.2026.081304 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 24 StartPage: 1 Subjects: – SubjectFull: Fourier transforms Type: general – SubjectFull: Encoding Type: general – SubjectFull: Natural language processing Type: general – SubjectFull: Language models Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Artificial neural networks Type: general Titles: – TitleFull: Beyond Classical Positional Encodings: A Learnable QFT-Inspired Framework for Transformer Language Models. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Tehsin, Sara – PersonEntity: Name: NameFull: Akram, Tallha – PersonEntity: Name: NameFull: Naqvi, Syed Rameez – PersonEntity: Name: NameFull: Alharbi, Meshal – PersonEntity: Name: NameFull: Alabduljabbar, Abdulrahman IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: 2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 15462218 Numbering: – Type: volume Value: 88 – Type: issue Value: 3 Titles: – TitleFull: Computers, Materials & Continua Type: main |
| ResultId | 1 |