Research map / Federated learning and privacy / Communication-efficient FL
Ripple Shapley: Data Influence Attribution in One Federated Training Run
Dewen Zeng, Wenlong Tian, Haozhao Wang, Jianfeng Lu, Weijun Xiao, Zhiyong Xu
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 |
|---|---|---|---|
| use Ripple Shapley instead of AFedSV+ for contribution evaluation | federated learning attribution · MNIST and CIFAR-10, 100 rounds | cumulative computation time (s): 61437.57 -> 984.98 | Improved |
| use Ripple Shapley instead of S-FedAvg | federated learning attribution · MNIST and CIFAR-10, 100 rounds | cumulative computation time (s): 4531.91 -> 984.98 | Improved |
| add Ripple Shapley attribution on top of plain training | FedAvg · MNIST and CIFAR-10, 100 rounds | computation time (s): 480.91 -> 984.98 | Hurt |
| use Ripple Shapley aggregation weighting instead of baseline aggregation | federated aggregation · open-set label noise | accuracy: over 10% average accuracy improvement | Improved |
| use Ripple Shapley weighting on other poisoning settings | federated aggregation · long-tailed, data noise (MNIST, CIFAR-10) | accuracy | No clear effect |
| increase ripple propagation depth beyond 20 (ablation) | Ripple Shapley · 100-round trajectories of representative samples | ripple value | No clear effect |
| add ripple term and low-rank Jacobian propagation to the drop term | Ripple Shapley · dynamic participation in FL | attribution validity | Improved |
Closest papers by meaning
- Fair and Efficient Contribution Valuation for Vertical Federated Learning (ICLR 2024 · similarity 0.89)
- DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation (NeurIPS 2024 · similarity 0.85)
- Data Valuation and Detections in Federated Learning (CVPR 2024 · similarity 0.84)
- Data Shapley in One Training Run (ICLR 2025 · similarity 0.84)
- You Get What You Give: Reciprocally Fair Federated Learning (ICML 2025 · similarity 0.84)
- Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution (CVPR 2025 · 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.
