Curator's Take
This work represents a significant milestone in practical quantum machine learning, demonstrating that today's noisy intermediate-scale quantum devices can actually outperform classical methods on real-world problems. The researchers cleverly leveraged the unique architecture of neutral atom systems, where atoms can be positioned anywhere in 2D space using optical tweezers, making them naturally suited for graph problems unlike gate-based quantum computers that require complex graph embedding schemes. What's particularly noteworthy is that they achieved these results on the 256-qubit Aquila system available through AWS, showing that cloud-accessible quantum hardware is now powerful enough for meaningful machine learning applications beyond toy problems. The fact that their quantum approach slightly outperformed classical kernels on the PROTEINS dataset, despite hardware noise, suggests we may finally be entering an era where quantum advantage in machine learning becomes practically achievable.
— Mark Eatherly
Summary
Neutral atom platforms are analogue quantum simulators that offer the possibility to map graphs onto a 2D qubit register using programmable Rubidium atoms arrays, whose valence electrons' energy state is used as qubits, using optical tweezers. This makes it possible to implement algorithms for solving graph combinatorial optimization and Quantum Machine Learning (QML) tasks, such as graph classification. However, the restrictions of real hardware, as well as the very low number of publicly available machines, make such implementation non-trivial. In this work, we manage to compute the Quantum Evolution Kernel (QEK) to extract the features from graphs of the PROTEINS dataset using the 256-qubits Aquila platform (available through AWS) and then we apply classical Machine Learning (ML) techniques for the final classification. The method is benchmarked against classical kernels, resulting in slightly better performance, proving the effectiveness of the method, even in the case of a noisy quantum simulator.