Research map / Federated learning and privacy / Personalized and heterogeneous FL
Towards Rule-Based Knowledge Sharing in Federated Learning
Zixuan Qin, Qi Shen, Liu Yang, Qilong Wang, Qinghua Hu
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 rule distillation (KD) loss to rule regularization (ablation) | RFL · CIFAR-100 (Dir 0.1) | Accuracy: 56.06 -> 58.25 | Improved |
| add rule regularization loss to KD (ablation) | RFL · CIFAR-100 (Dir 0.1) | Accuracy: 53.59 -> 58.25 | Improved |
| raise KD weight alpha_kd from 0.1 to 0.6 (ablation) | RFL · CIFAR-100 (Dir 0.1) | Accuracy: 55.72 -> 58.17 | Improved |
| raise KD weight alpha_kd from 0.6 to 0.9 (ablation) | RFL · CIFAR-100 (Dir 0.1) | Accuracy: 58.17 -> 57.19 | Hurt |
| raise rule weight alpha_ru from 0.5 to 1.5 (ablation) | RFL · CIFAR-100 (Dir 0.1) | Accuracy: 56.05 -> 58.23 | Improved |
| raise rule weight alpha_ru from 1.5 to 2.0 (ablation) | RFL · CIFAR-100 (Dir 0.1) | Accuracy: 58.23 -> 56.72 | Hurt |
| raise margin m from 0.2 to 0.7 (ablation) | RFL · CIFAR-100 (Dir 0.1) | Accuracy: 55.20 -> 58.21 | Improved |
| raise margin m from 0.7 to 0.9 (ablation) | RFL · CIFAR-100 (Dir 0.1) | Accuracy: 58.21 -> 57.05 | Hurt |
| share rules instead of class prototypes | RFL vs FedTGP · CIFAR-100 (Dir 0.3) | Accuracy: 39.34 -> 43.80 | Improved |
| share rules instead of class prototypes | RFL vs FedProto · CIFAR-100 (Pathological) | Accuracy: 58.92 -> 63.02 | Improved |
| use rule carrier instead of proxy-model carrier | RFL vs FedSCE · CIFAR-100 | Communication cost (MB/round): 265.36 -> 41.98 | Improved |
| use rule carrier instead of proxy-model carrier | RFL vs FedSCE · CIFAR-100 (Dir 0.3) | Accuracy: 44.53 vs 43.80 | No clear effect |
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.
- FedSA — FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning (AAAI 2025) · better on 1 of 1 shared result
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
- Efficient Federated Learning via Clients-to-Server Knowledge Distillation (Student Abstract) (AAAI 2025 · similarity 0.86)
- Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration (NeurIPS 2024 · similarity 0.86)
- An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning (CVPR 2024 · similarity 0.86)
- FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler (ICLR 2024 · similarity 0.85)
- Federated Neuro-Symbolic Learning (ICML 2024 · similarity 0.85)
- FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation (NeurIPS 2024 · similarity 0.85)
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.
