Distributed Quantum Neural Networks via Partitioned Features Encoding
This work addresses scalability issues in quantum machine learning for near-term quantum devices, though it appears incremental as it builds on prior distributed quantum neural network ideas.
The authors tackled the challenges of vanishing gradients and limited expressibility in quantum neural networks by proposing a distributed approach that partitions features across multiple small quantum neural networks and uses ensemble predictions. They demonstrated this method on the Semeion and MNIST datasets, achieving over 96% accuracy on MNIST for ten-class classification while reducing hardware requirements.
Quantum neural networks are expected to be a promising application in near-term quantum computing, but face challenges such as vanishing gradients during optimization and limited expressibility by a limited number of qubits and shallow circuits. To mitigate these challenges, an approach using distributed quantum neural networks has been proposed to make a prediction by approximating outputs of a large circuit using multiple small circuits. However, the approximation of a large circuit requires an exponential number of small circuit evaluations. Here, we instead propose to distribute partitioned features over multiple small quantum neural networks and use the ensemble of their expectation values to generate predictions. To verify our distributed approach, we demonstrate ten class classification of the Semeion and MNIST handwritten digit datasets. The results of the Semeion dataset imply that while our distributed approach may outperform a single quantum neural network in classification performance, excessive partitioning reduces performance. Nevertheless, for the MNIST dataset, we succeeded in ten class classification with exceeding 96\% accuracy. Our proposed method not only achieved highly accurate predictions for a large dataset but also reduced the hardware requirements for each quantum neural network compared to a large single quantum neural network. Our results highlight distributed quantum neural networks as a promising direction for practical quantum machine learning algorithms compatible with near-term quantum devices. We hope that our approach is useful for exploring quantum machine learning applications.