A simulator study reports that QNNs hold accuracy under label flipping better than a large MLP and unlearn faster, but the claimed fundamental advantage is not established without regularized classical baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Superior resilience to poisoning and amenability to unlearning in quantum machine learning
A simulator study reports that QNNs hold accuracy under label flipping better than a large MLP and unlearn faster, but the claimed fundamental advantage is not established without regularized classical baselines.