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
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 |
|---|---|---|---|
| Quorus-Layerwise instead of Q-HeteroFL | federated quantum classifier · MNIST 0/1 capacity 2L | test accuracy (%): 90.3 -> 97.0 | Improved |
| Quorus-Layerwise instead of Q-HeteroFL at capacity 6L | federated quantum classifier · MNIST 4/9 | test accuracy (%): 73.9 -> 83.1 | Improved |
| Quorus-Layerwise instead of Vanilla QFL for smallest clients | federated quantum classifier · Fashion-MNIST Bag/Sandal capacity 2L | test accuracy (%): 91.9 -> 86.1 | Hurt |
| Quorus-Layerwise instead of Vanilla QFL at capacity 6L | federated quantum classifier · MNIST 4/9 | test accuracy (%): 80.0 -> 83.1 | Improved |
| Quorus-Funnel instead of Quorus-Layerwise | Quorus · MNIST 4/9 capacity 6L | test accuracy (%): 83.1 -> 85.2 | Improved |
| Quorus-Ancilla/Blocking instead of Layerwise | Quorus · MNIST 4/9 capacity 6L | test accuracy (%): 83.1 -> 82.2 | No clear effect |
| V-shape ansatz instead of Staircase (ablation) | Quorus-Layerwise · Pullover/Coat capacity 2L | test accuracy (%): 66.9 -> 76.3 | Improved |
| V-shape ansatz instead of Alternating (ablation) | Quorus-Layerwise · Pullover/Coat capacity 6L | test accuracy (%): 75.3 -> 78.8 | Improved |
| V-shape ansatz instead of Staircase (ablation) | Quorus-Layerwise · Bag/Sandal capacity 2L | test accuracy (%): 93.4 -> 86.1 | Hurt |
| raise smallest client from 1 layer to 2 layers (ablation) | Quorus-Layerwise · MNIST 0/1 | test accuracy (%): 59.5 -> 97.0 | Improved |
| increase client layers from 6 to 10 (ablation) | Quorus-Layerwise · MNIST 4/9 | test accuracy (%): 83.1 -> 83.9 | No clear effect |
| add layerwise losses with reverse distillation | Quorus · gradient norms | gradient norm | Improved |
Closest papers by meaning
- On the Relation between Trainability and Dequantization of Variational Quantum Learning Models (ICLR 2025 · similarity 0.86)
- Exponential Quantum Communication Advantage in Distributed Inference and Learning (NeurIPS 2024 · similarity 0.85)
- Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices (CVPR 2024 · similarity 0.84)
- Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm (NeurIPS 2026 · similarity 0.83)
- Limitations of measure-first protocols in quantum machine learning (ICML 2025 · similarity 0.83)
- QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning Baseline (ICML 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.
