Quantum Federated Learning with Entanglement Controlled Circuits and Superposition Coding
This work addresses the problem of efficient quantum federated learning for researchers in quantum computing and machine learning, though it appears incremental by building on existing QFL methods with specific architectural enhancements.
The paper tackles the challenge of enabling quantum federated learning under varying channel conditions by developing a depth-controllable entangled slimmable quantum neural network architecture and proposing an entangled slimmable QFL method with superposition coding. It demonstrates effectiveness in image classification tasks, showing improvements in prediction accuracy, fidelity, and entropy compared to Vanilla QFL across different conditions.
While witnessing the noisy intermediate-scale quantum (NISQ) era and beyond, quantum federated learning (QFL) has recently become an emerging field of study. In QFL, each quantum computer or device locally trains its quantum neural network (QNN) with trainable gates, and communicates only these gate parameters over classical channels, without costly quantum communications. Towards enabling QFL under various channel conditions, in this article we develop a depth-controllable architecture of entangled slimmable quantum neural networks (eSQNNs), and propose an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eS-QNNs. Compared to the existing depth-fixed QNNs, training the depth-controllable eSQNN architecture is more challenging due to high entanglement entropy and inter-depth interference, which are mitigated by introducing entanglement controlled universal (CU) gates and an inplace fidelity distillation (IPFD) regularizer penalizing inter-depth quantum state differences, respectively. Furthermore, we optimize the superposition coding power allocation by deriving and minimizing the convergence bound of eSQFL. In an image classification task, extensive simulations corroborate the effectiveness of eSQFL in terms of prediction accuracy, fidelity, and entropy compared to Vanilla QFL as well as under different channel conditions and various data distributions.