Research map / Adversarial robustness and security / Attacks on text and graphs
Quantum Wasserstein Generative Adversarial Networks
Shouvanik Chakrabarti, Huang Yiming, Tongyang Li, Soheil Feizi, Xiaodi Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use qWGAN rather than a 2nd-order product-formula circuit for the Heisenberg-model approximation | 1-d 3-qubit Heisenberg model circuit approximation · 1-d 3-qubit Heisenberg model | gate count: ~11900 -> 52 gates | Improved |
| Use qWGAN rather than the 2nd-order product-formula circuit | 1-d 3-qubit Heisenberg model circuit approximation · 1-d 3-qubit Heisenberg model | worst-case error: 0.001 -> 0.15 | Hurt |
| Use qWGAN rather than the superconducting-circuit quantum GAN | 1-qubit pure-state learning · 1-qubit pure state | iterations to fidelity approaching 1: 220 iterations -> 150-160 iterations | Improved |
| Use qWGAN rather than the superconducting-circuit quantum GAN | 1-qubit mixed-state learning · 1-qubit mixed state | iterations to fidelity approaching 1: 120 iterations -> ~120 iterations | No clear effect |
| Add measurement noise | qWGAN 4-qubit pure-state learning · 4-qubit pure state | epochs before successful learning | Hurt |
| Increase the learned pure-state system size to 8 qubits | qWGAN · Pure-state learning | training progress: within 900 iterations | Improved |
Closest papers by meaning
- Generating Universal Adversarial Perturbations for Quantum Classifiers (AAAI 2024 · similarity 0.85)
- Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machine (NeurIPS 2026 · similarity 0.84)
- Exponential Hardness of Optimization from the Locality in Quantum Neural Networks (AAAI 2024 · similarity 0.84)
- MG-Net: Learn to Customize QAOA with Circuit Depth Awareness (NeurIPS 2024 · similarity 0.83)
- QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation (NeurIPS 2024 · similarity 0.83)
- QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm Design (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
