AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

QKSAN: A Quantum Kernel Self-Attention Network

Ren-Xin Zhao, Jinjing Shi, Xuelong Li

TPAMI 2024 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 93 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use QKSAN AmHE (amplitude encoding, hardware-efficient ansatz) as best of four sub-models (ablation)QKSAN · MNIST binarytest accuracy: 99Improved
use QKSAN AmHE on Fashion MNIST (ablation)QKSAN · Fashion MNIST binarytest accuracy: 98.05Improved
QKSAN AmHE versus QSAN: 11 parameters and 6 layers on 4 qubits versus 9 parameters, 26 layers, 8 qubitsQKSAN AmHE · MNIST/Fashion MNIST binaryqubits and layers: 4 vs 8 qubits; 6 vs 26 layersImproved
QKSAN AmHE versus QSAN convergence speedQKSAN AmHE · MNIST binaryconvergence steps: trails QSAN by 42 stepsHurt
QKSAN AmHE versus QSAN convergence speedQKSAN AmHE · Fashion MNIST binaryconvergence steps: trails QSAN by 50 stepsHurt
add bit flip or amplitude damping noise at probability 0.1 (ablation)QKSAN AmHE · MNIST binary (noisy simulation)learning accuracy: probability 0.1No clear effect
increase noise error probability beyond 0.1 (ablation)QKSAN AmHE · MNIST binary (noisy simulation)learning accuracyHurt
amplitude damping error versus bit flip error (ablation)QKSAN AmHE · MNIST binary (noisy simulation)loss functionImproved
use deferred measurement principle with conditional operationQKSAN · QKSAN circuitquantum resources: half of quantum resourcesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy