Layered Quantum Architecture Search for 3D Point Cloud Classification

2026-03-20

AI Summary

This work addresses the lack of effective architectures and inductive biases in parameterized quantum circuits (PQCs) for 3D point cloud classification by proposing a Layered Quantum Architecture Search (Layered-QAS) method. Inspired by classical network morphism, Layered-QAS adaptively constructs PQC structures through a hierarchical growth mechanism, marking the first effort to employ PQCs as end-to-end classification backbones rather than mere feature extractors, while embedding task-specific inductive biases. Coupled with a classical–quantum hybrid training strategy, the approach effectively mitigates the barren plateau problem. Evaluated on the ModelNet dataset, the proposed method achieves state-of-the-art performance among PQC-based models, significantly outperforming baseline approaches based on local search and evolutionary quantum architecture search.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

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.

Problem

• Quantum Architecture Search
• 3D Point Cloud Classification
• Parametrised Quantum Circuit
• Barren Plateau
• Inductive Bias

Innovation

• Layered Quantum Architecture Search
• Parametrised Quantum Circuit
• 3D Point Cloud Classification
• Barren Plateau Mitigation
• Quantum Neural Architecture