Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Manifold Learning (FML): Tackling Domain Heterogeneity with Structural Knowledge Transfer
Xutong Mu, Yanbiao Ma, Jia Shi, Xueli Geng, Fengkai Xiang, Tao Zhang, Ke Cheng, Yulong Shen
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 |
|---|---|---|---|
| add manifold approximation loss only (ablation) | FML · Digits | AVG accuracy: 79.44 -> 82.04 | Improved |
| add manifold separation loss only (ablation) | FML · Digits | AVG accuracy: 79.44 -> 81.24 | Improved |
| combine both manifold losses (ablation) | FML · Digits | AVG accuracy: 82.04 -> 82.91 | Improved |
| add manifold approximation loss only (ablation) | FML · Office31 | AVG accuracy: 50.48 -> 54.75 | Improved |
| add manifold separation loss only (ablation) | FML · Office31 | AVG accuracy: 50.48 -> 51.53 | Improved |
| combine both manifold losses (ablation) | FML · Office31 | AVG accuracy: 54.75 -> 58.72 | Improved |
| replace class prototypes with compressed attention-fused manifolds | FML vs prototype FPL · Digits | AVG accuracy: 80.62 -> 82.91 | Improved |
| replace class prototypes with compressed manifolds | FML · Office31 | AVG accuracy: 52.25 -> 58.72 | Improved |
| use MOON contrastive regularization | MOON · Digits | AVG accuracy: 79.44 -> 71.90 | Hurt |
| use prototype-based FPL on Office31 | FPL · Office31 | AVG accuracy: 50.48 -> 46.83 | Hurt |
| raise MML coefficient gamma to 0.9 on Digits (ablation) | FML · Digits | AVG accuracy: 82.54 -> 84.14 | Improved |
| choose compression size r near 10 (ablation) | PMC · Digits and Office31 | IEI | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FedCD — FedCD: Federated Semi-Supervised Learning with Class Awareness Balance via Dual Teachers (AAAI 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning (CVPR 2025 · similarity 0.86)
- Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data (NeurIPS 2024 · similarity 0.85)
- FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning (AAAI 2024 · similarity 0.85)
- Federated Model Heterogeneous Matryoshka Representation Learning (NeurIPS 2024 · similarity 0.85)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.85)
- Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients (ICML 2024 · similarity 0.84)
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.
