Research map / Federated learning and privacy / Personalized and heterogeneous FL
Robust Federated Learning via Collaborative Machine Teaching
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CoMT collaborative teaching instead of training on trusted plus corrupted data (TI+Noise) | L2-LR · IJCNN label flipping 80% | AUC: 0.12 -> 0.89 | Helped |
| use CoMT instead of independent per-teacher DUTI | federated learner · IJCNN feature corruption dx=4.50 | AUC: 0.66 -> 0.89 | Helped |
| use CoMT instead of robust aggregation (GeoMed, RSA) under pervasive noise | federated learner · SUSY label flipping 80% | AUC: 0.22 -> 0.75 | Helped |
| use CoMT instead of TI+Noise on regression | Ridge Regression · CPUSMALL feature corruption dx=4.50 | R-squared: 0.18 -> 0.69 | Helped |
| use CoMT dual coordinate descent instead of DUTI bi-level retraining | teaching procedure · SUSY run time | run time (s): 359.75 vs more than 1000s | Helped |
Closest papers by meaning
- Towards Trustworthy Federated Learning with Untrusted Participants (ICML 2025 · similarity 0.89)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.87)
- Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping (CVPR 2024 · similarity 0.87)
- Federated Learning via Input-Output Collaborative Distillation (AAAI 2024 · similarity 0.86)
- Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts (ICML 2025 · similarity 0.86)
- Scalable and Trustworthy Learning in Heterogeneous Networks (AAAI 2025 · similarity 0.86)
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.