Exploring Explainability in Quantum Machine Learning via Parameter-Shift Saliency
Session Number
2
Advisor(s)
Mr. Doug Strain, IMSA
Location
IN2 Alpha Design Studio
Discipline
Business
Start Date
15-4-2026 11:10 AM
End Date
15-4-2026 11:55 AM
Abstract
Variational quantum classifiers (VQCs) are a leading approach for near-term quantum machine learning, but explaining their specific decisions remains a growing challenge. Classical ML has established tools for self-explanation, such as gradient-based heatmaps. However, quantum circuits trained on real hardware cannot use classical backpropagation, requiring quantum-native methods instead. This study applies one such method, the parameter-shift rule, to compute input gradients, resulting in saliency scores using two circuit evaluations per input feature. Using a small, controlled 2x2 image classification task with known ground-truth pixels, this study evaluates whether the model's explanations align with the features truly driving its predictions. The trained 4-qubit VQC achieves 100% test accuracy and identifies the correct causal pixels in 62.5% of test cases. To assess faithfulness more directly, ablation experiments show that masking saliency-identified pixels reduces model confidence by 3.97%, compared to 0.014% for random masking, a raw improvement of roughly 274x. Additional multi-seed analyses suggest the method remains reasonably consistent across different model initializations, helping show that explanation results are not from just one lucky training run. Overall, these results suggest that input parameter-shift saliency is a promising approach for Quantum explainability and motivate testing it on larger, more complex datasets.
Exploring Explainability in Quantum Machine Learning via Parameter-Shift Saliency
IN2 Alpha Design Studio
Variational quantum classifiers (VQCs) are a leading approach for near-term quantum machine learning, but explaining their specific decisions remains a growing challenge. Classical ML has established tools for self-explanation, such as gradient-based heatmaps. However, quantum circuits trained on real hardware cannot use classical backpropagation, requiring quantum-native methods instead. This study applies one such method, the parameter-shift rule, to compute input gradients, resulting in saliency scores using two circuit evaluations per input feature. Using a small, controlled 2x2 image classification task with known ground-truth pixels, this study evaluates whether the model's explanations align with the features truly driving its predictions. The trained 4-qubit VQC achieves 100% test accuracy and identifies the correct causal pixels in 62.5% of test cases. To assess faithfulness more directly, ablation experiments show that masking saliency-identified pixels reduces model confidence by 3.97%, compared to 0.014% for random masking, a raw improvement of roughly 274x. Additional multi-seed analyses suggest the method remains reasonably consistent across different model initializations, helping show that explanation results are not from just one lucky training run. Overall, these results suggest that input parameter-shift saliency is a promising approach for Quantum explainability and motivate testing it on larger, more complex datasets.