Quantum Technology Initiative Journal Club

Thursday 6 Jun 2024, 16:00 → 17:00 Europe/Zurich

513/R-070 - Openlab Space (CERN)

Alice Barthe (Leiden University (NL)), Michele Grossi (CERN), Su Yeon Chang (EPFL - Ecole Polytechnique Federale Lausanne (CH))

Weekly Journal Club meetings organised in the framework of the CERN Quantum Technology Initiative (QTI) to present and discuss scientific papers in the field of quantum science and technology. The goal is to help researchers keep track of current findings and walk away with ideas for their own research. Some previous knowledge of quantum physics would be helpful, but is not required to follow the talks.

To propose a paper for discussion, contact: michele.grossi@cern.ch

16:00 → 17:00 CERN QTI Journal CLUB: Permutation-equivariant quantum convolutional neural networks

Convener: Dr Michele Grossi (CERN)

16:00 Saverio Monaco (DESY)

Permutation-equivariant quantum convolutional neural networks

Link to the paper: https://arxiv.org/abs/2404.18198

Abstract:
The Symmetric group Sn manifests itself in large classes of quantum systems as the invariance of certain characteristics of a quantum state with respect to permuting the qubits. The subgroups of Sn arise, among many other contexts, to describe label symmetry of classical images with respect to spatial transformations, e.g. reflection or rotation. Equipped with the formalism of geometric quantum machine learning, in this work we propose the architectures of equivariant quantum convolutional neural networks (EQCNNs) adherent to Sn and its subgroups. We demonstrate that a careful choice of pixel-to-qubit embedding order can facilitate easy construction of EQCNNs for small subgroups of Sn. Our novel EQCNN architecture corresponding to the full permutation group Sn is built by applying all possible QCNNs with equal probability, which can also be conceptualized as a dropout strategy in quantum neural networks. For subgroups of Sn, our numerical results using MNIST datasets show better classification accuracy than non-equivariant QCNNs. The Sn-equivariant QCNN architecture shows significantly improved training and test performance than non-equivariant QCNN for classification of connected and non-connected graphs. When trained with sufficiently large number of data, the Sn-equivariant QCNN shows better average performance compared to Sn-equivariant QNN . These results contribute towards building powerful quantum machine learning architectures in permutation-symmetric systems.

Speaker: Saverio Monaco

jc (1).pdf

jc (1).pptx

recording