Quantum federated learning forgets data using classical shadows
Federated Unlearning of Quantum Data via Classical Shadows
Distributed, Parallel, and Cluster ComputingNetworking and Internet Architecture
Summary
Quantum data cannot be copied or replayed, making it hard to erase information from quantum machine learning models. The authors propose a method called SHADE, where classical snapshots of quantum states taken during training are saved. This lets the system estimate and remove the effect of specific data later without needing the original quantum data. In tests, SHADE erased data from a quantum neural network almost as accurately and quickly as retraining from scratch.
What this means in practice
- •For quantum software engineers: Remove specific training data effects from quantum neural networks in federated settings without accessing original quantum states.
- •For edge device integrators: Enable quick data forgetting on devices running federated quantum learning by transmitting only classical measurement data.
Authors
Zihao Ding, Jun Huang, Cong-cong Xing
Abstract
Quantum federated learning trains a quantum neural network (QNN) across nodes that hold quantum data, such as the states of quantum sensors. To forget data, unlearning methods for quantum models replay them, and federated unlearning from stored updates removes whole nodes only. Quantum data cannot be replayed, since a state is consumed when measured and cannot be cloned. We propose Shadow-based Data Erasure (SHADE), in which each node records a classical shadow of every training state, a few randomized single-qubit measurements taken at training time. The gradient and curvature of a QNN on a state are expectations of observables, so SHADE estimates them for the forget data from the shadows at any later parameters and removes their effect by a federated Newton correction. Only classical estimates cross the network. We prove that the shadow size needed for a target unlearning error grows exponentially in the size of the backward light cone of the measured observable and not in the number of qubits. In simulation with 50 nodes and on edge boards, SHADE matches the forget accuracy of retraining within 0.5 points, without replay and in under 0.2 s.