AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus

Jason Han, Nicholas S. DiBrita, Daniel Leeds, Jianqiang Li, Jason Ludmir, Tirthak Patel

ICLR 2026 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 2 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
Quorus-Layerwise instead of Q-HeteroFLfederated quantum classifier · MNIST 0/1 capacity 2Ltest accuracy (%): 90.3 -> 97.0Improved
Quorus-Layerwise instead of Q-HeteroFL at capacity 6Lfederated quantum classifier · MNIST 4/9test accuracy (%): 73.9 -> 83.1Improved
Quorus-Layerwise instead of Vanilla QFL for smallest clientsfederated quantum classifier · Fashion-MNIST Bag/Sandal capacity 2Ltest accuracy (%): 91.9 -> 86.1Hurt
Quorus-Layerwise instead of Vanilla QFL at capacity 6Lfederated quantum classifier · MNIST 4/9test accuracy (%): 80.0 -> 83.1Improved
Quorus-Funnel instead of Quorus-LayerwiseQuorus · MNIST 4/9 capacity 6Ltest accuracy (%): 83.1 -> 85.2Improved
Quorus-Ancilla/Blocking instead of LayerwiseQuorus · MNIST 4/9 capacity 6Ltest accuracy (%): 83.1 -> 82.2No clear effect
V-shape ansatz instead of Staircase (ablation)Quorus-Layerwise · Pullover/Coat capacity 2Ltest accuracy (%): 66.9 -> 76.3Improved
V-shape ansatz instead of Alternating (ablation)Quorus-Layerwise · Pullover/Coat capacity 6Ltest accuracy (%): 75.3 -> 78.8Improved
V-shape ansatz instead of Staircase (ablation)Quorus-Layerwise · Bag/Sandal capacity 2Ltest accuracy (%): 93.4 -> 86.1Hurt
raise smallest client from 1 layer to 2 layers (ablation)Quorus-Layerwise · MNIST 0/1test accuracy (%): 59.5 -> 97.0Improved
increase client layers from 6 to 10 (ablation)Quorus-Layerwise · MNIST 4/9test accuracy (%): 83.1 -> 83.9No clear effect
add layerwise losses with reverse distillationQuorus · gradient normsgradient normImproved

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