mlsanityData to 14 Oct 2026

Layered Quantum Architecture Search for 3D Point Cloud Classification

arXiv 2603.20024 ↗First posted 20 Mar 2026quant-ph cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce layered Quantum Architecture Search (layered-QAS), a strategy inspired by classical network morphism that designs Parametrised Quantum Circuit (PQC) architectures by progressively growing and adapting them. PQCs offer strong expressiveness with relatively few parameters, yet they lack standard architectural layers (e.g., convolution, attention) that encode inductive biases for a given learning task. To assess the effectiveness of our method, we focus on 3D point cloud classification as a challenging yet highly structured problem. Whereas prior work on this task has used PQCs only as feature extractors for classical classifiers, our approach uses the PQC as the main building block of the classification model. Simulations show that our layered-QAS mitigates barren plateau, outperforms quantum-adapted local and evolutionary QAS baselines, and achieves state-of-the-art results among PQC-based methods on the ModelNet dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 60 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

31 of 60 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018Supervised learning with quantum enhanced feature spacescited by 665
  3. 2018Barren plateaus in quantum neural network training landscapescited by 630
  4. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  5. 2020The effect of data encoding on the expressive power of variational quantum machine learning modelscited by 333
  6. 2016Quantum Machine Learningcited by 326
  7. 2023Challenges and Opportunities in Quantum Machine Learningcited by 203
  8. 2018Efficient Multi-objective Neural Architecture Search via Lamarckian Evolutioncited by 153
  9. 2024Barren Plateaus in Variational Quantum Computingcited by 133
  10. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  11. 2021QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuitscited by 98
  12. 2020Layerwise learning for quantum neural networkscited by 88
19 more
  1. 2024Better than classical? The subtle art of benchmarking quantum machine learning modelscited by 85
  2. 2020Quantum circuit architecture search for variational quantum algorithmscited by 82
  3. 2021Reinforcement learning for optimization of variational quantum circuit architecturescited by 77
  4. 2021Quantum Architecture Search via Deep Reinforcement Learningcited by 60
  5. 2023Quantum machine learning for image classificationcited by 57
  6. 2024KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Searchcited by 37
  7. 2021Capacity and quantum geometry of parametrized quantum circuitscited by 32
  8. 2024Quantum Architecture Search: A Surveycited by 32
  9. 2020Deeper Insights into Weight Sharing in Neural Architecture Searchcited by 24
  10. 2023Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlookcited by 24
  11. 2021Quantum Architecture Search via Continual Reinforcement Learningcited by 22
  12. 2020Exploring the Loss Landscape in Neural Architecture Searchcited by 20
  13. 2024A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentationcited by 14
  14. 2024Quantum Machine Learning Architecture Search via Deep Reinforcement Learningcited by 13
  15. 2021RGB Image Classification with Quantum Convolutional Ansaetzecited by 6
  16. 2025Quantum-enhanced Computer Vision: Going Beyond Classical Algorithmscited by 5
  17. 2023Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradientscited by 3
  18. 2022Traffic Sign Classification Using Deep and Quantum Neural Networkscited by 2
  19. 2024Quantum Circuit Training with Growth-Based Architecturescited by 1

Built on by

Not cited yet.