Research map / Federated learning and privacy / Personalized and heterogeneous FL
SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning
Yi-Chung Chen, Hsi-Wen Chen, Shun-Guei Wang, Ming-Syan Chen
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 |
|---|---|---|---|
| single-round amalgamation instead of GTG-Shapley | SPACE · MNIST | communication cost (MB): 35.2 -> 1.76 | Improved |
| SPACE instead of TMC-Shapley | SPACE · MNIST | execution time (s): 84796 -> 160 | Improved |
| SPACE instead of DIG-FL | SPACE · MNIST Non-IID | Pearson correlation: 0.8715 -> 0.9448 | Improved |
| SPACE instead of GTG-Shapley | SPACE · CIFAR10 Mislabel | Pearson correlation: 0.4148 -> 0.9641 | Improved |
| knowledge amalgamation instead of FedAvg aggregation (ablation) | SPACE · MNIST Non-IID | Pearson correlation: 0.9713 -> 0.9448 | Hurt |
| knowledge amalgamation instead of FedAvg aggregation (ablation) | SPACE · MNIST | execution time (s): 294 -> 160 | Improved |
| knowledge amalgamation instead of FedAvg aggregation (ablation) | SPACE · Tiny-ImageNet | execution time (s): 252 -> 453 | Hurt |
| hierarchical amalgamation with G=2 (ablation) | SPACE · MNIST | runtime (s): 160 -> 633 | Hurt |
| hierarchical amalgamation with G=2 (ablation) | SPACE · MNIST Mislabel | Pearson correlation: 0.9612 -> 0.9726 | No clear effect |
| hierarchical amalgamation with G=2 (ablation) | SPACE · CIFAR10 Non-IID | Pearson correlation: 0.9290 -> 0.9333 | No clear effect |
| replace labeled validation set with unlabeled data (ablation) | SPACE · MNIST Non-IID | Pearson correlation: 0.9448 -> 0.8772 | Hurt |
| replace labeled validation set with unlabeled data (ablation) | SPACE · CIFAR10 Mislabel | Pearson correlation: 0.9641 -> 0.9641 | No clear effect |
Closest papers by meaning
- Fair and Efficient Contribution Valuation for Vertical Federated Learning (ICLR 2024 · similarity 0.84)
- Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning (CVPR 2025 · similarity 0.83)
- Convergence Analysis of Split Federated Learning on Heterogeneous Data (NeurIPS 2024 · similarity 0.83)
- Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis (NeurIPS 2024 · similarity 0.83)
- FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants (AAAI 2024 · similarity 0.83)
- FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler (ICML 2024 · 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.
