mlsanityData to 14 Oct 2026

PGKET: A Photonic Gaussian Kernel Enhanced Transformer

arXiv 2507.19041 ↗First posted 25 Jul 2025quant-ph cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-Attention Mechanisms (SAMs) enhance model performance by extracting key information but are inefficient when dealing with long sequences. To this end, a photonic Gaussian Kernel Enhanced Transformer (PGKET) is proposed, based on the Photonic Gaussian Kernel Self-Attention Mechanism (PGKSAM). The PGKSAM calculates the Photonic Gaussian Kernel Self-Attention Score (PGKSAS) using photon interferometry and superposition to process multiple inputs in parallel. Experimental results show that PGKET outperforms some state-of-the-art transformers in multi-classification tasks on MedMNIST v2 and CIFAR-10, and is expected to improve performance in complex tasks and accelerate the convergence of Photonic Computing (PC) and machine learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

16 of 29 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  3. 2021Generalization in quantum machine learning from few training datacited by 216
  4. 2019Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernelcited by 213
  5. 2023Challenges and Opportunities in Quantum Machine Learningcited by 203
  6. 2018Do CIFAR-10 Classifiers Generalize to CIFAR-10?cited by 200
  7. 2021SOFT: Softmax-free Transformer with Linear Complexitycited by 128
  8. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  9. 2021Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr"om Methodcited by 63
  10. 2023Understanding quantum machine learning also requires rethinking generalizationcited by 49
  11. 2021AAformer: Auto-Aligned Transformer for Person Re-Identificationcited by 48
  12. 2023The physics of optical computingcited by 33
4 more
  1. 2022Visualizing and Understanding Patch Interactions in Vision Transformercited by 26
  2. 2021Pruning Self-attentions into Convolutional Layers in Single Pathcited by 24
  3. 2025HQViT: Hybrid Quantum Vision Transformer for Image Classificationcited by 7
  4. 2021Gaussian Kernelized Self-Attention for Long Sequence Data and Its Application to CTC-based Speech Recognitioncited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Photonic Quantum-Enhanced Knowledge Distillation
  2. 2023Optical Transformers
  3. 2024Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment
  4. 2026Inverse-designed meta processing units for multi-task near-field photonic computing
  5. 2021A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning
  6. 2025Opto-ViT: Architecting a Near-Sensor Region of Interest-Aware Vision Transformer Accelerator with Silicon Photonics ↗
  7. 2022NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation
  8. 2023SCONNA: A Stochastic Computing Based Optical Accelerator for Ultra-Fast, Energy-Efficient Inference of Integer-Quantized CNNs