← Back to all news
arXiv Machine Learning By Antonio Greco, Riccardo Paoletti, Roberto Cappuccio, Mario Onorato

From IceCube to IT-Sphere: A Hybrid Quantum-Classical GNN for Banking IT Root Cause Analysis

Read the original on arXiv Machine Learning →

The paper introduces Hybrid Quantum Root Cause Analysis (HQ‑RCA), a workflow that applies a hybrid Quantum Graph Neural Network (QGNN) to banking IT operations. HQ‑RCA replaces the classification head of the classical DynEdge GNN with a Variational Quantum Circuit, achieving comparable F1 performance to the strongest classical baseline while simplifying the quantum readout to a single Pauli‑Z expectation. Experiments on 13 k anonymised alarm clusters from a major European bank demonstrate that the quantum component can be executed on NISQ hardware without error mitigation, using a gradient‑free grid scan for optimisation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 20

How Quantum Is the Advantage? A Fair, Calibration- and Noise-Aware Benchmark and Attribution Audit of Quantum Machine Learning for Network Intrusion Detection

The study evaluates quantum machine learning (QML) models for network intrusion detection against well-tuned classical baselines across four standard datasets, using a leakage-controlled protocol and noise simulation. It introduces a quantum-attribution audit to determine whether any performance gains are truly due to quantum effects. While most tuned classical models match or surpass QML, two quantum approaches— a quantum-kernel SVM and a small hybrid circuit—show statistically significant advantages on specific metrics and tasks.

By Syeda Anshrah Gillani, Mirza Samad Ahmed Baig, Shahid Munir Shah, Asher Ali, Hamzah Siddiqui
benchmarks
More like this →
arXiv Machine Learning
Aug 19

Dynamic Entanglement-Weighted Pruning for Quantum Federated Unlearning in Supply-Chain Risk Prediction

The paper proposes Entanglement-Weighted Pruning (EWP), a method for unlearning a client’s contribution from a federated quantum classifier without retraining from scratch. EWP scores each trainable circuit parameter by combining a Fisher‑information estimate on the target client’s data with a structural entanglement weight, pruning the lowest‑scoring parameters and optionally fine‑tuning the remaining ones. Experiments on a four‑qubit data‑re‑uploading ansatz trained with FedAvg across five simulated supply‑chain‑risk clients show that EWP achieves accuracy comparable to full retraining while reducing forgetting and wall‑clock time by about sixteenfold, outperforming random, Fisher‑only, or entanglement‑only pruning.

By Aditya Kumar, Sumit Chongder
fine-tuningefficiencybenchmarks
More like this →