AI Paper Atlas

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

NeurIPS 2019 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 55 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use qWGAN rather than a 2nd-order product-formula circuit for the Heisenberg-model approximation1-d 3-qubit Heisenberg model circuit approximation · 1-d 3-qubit Heisenberg modelgate count: ~11900 -> 52 gatesImproved
Use qWGAN rather than the 2nd-order product-formula circuit1-d 3-qubit Heisenberg model circuit approximation · 1-d 3-qubit Heisenberg modelworst-case error: 0.001 -> 0.15Hurt
Use qWGAN rather than the superconducting-circuit quantum GAN1-qubit pure-state learning · 1-qubit pure stateiterations to fidelity approaching 1: 220 iterations -> 150-160 iterationsImproved
Use qWGAN rather than the superconducting-circuit quantum GAN1-qubit mixed-state learning · 1-qubit mixed stateiterations to fidelity approaching 1: 120 iterations -> ~120 iterationsNo clear effect
Add measurement noiseqWGAN 4-qubit pure-state learning · 4-qubit pure stateepochs before successful learningHurt
Increase the learned pure-state system size to 8 qubitsqWGAN · Pure-state learningtraining progress: within 900 iterationsImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy