Research map / Federated learning and privacy / Privacy attacks and secure learning
Wyze Rule: Federated Rule Dataset for Rule Recommendation Benchmarking
Mohammad Mahdi Kamani, Yuhang Yao, Hanjia Lyu, Zhongwei Cheng, Lin Chen, Liangju Li, Carlee Joe-Wong, Jiebo Luo
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 |
|---|---|---|---|
| replace matrix completion (Matrix Factorization) by graph link prediction (GraphRule) | Matrix Factorization · Wyze Rule | Hit Rate @50: 0.8138 -> 0.91 | Improved |
| replace GCMC by GraphRule | GCMC · Wyze Rule | Hit Rate @50: 0.8445 -> 0.91 | Improved |
| distinguish multiple devices of the same type in rules | GraphRule · Wyze Rule | Hit Rate @50: 0.91 -> 0.6396 | Hurt |
| use GraphSAGE instead of GAT or GCN as GNN encoder | GraphRule · Wyze Rule | AUC, Mean Rank, MRR | Improved |
| scale dataset from small to large (GraphRule) | GraphRule · Wyze Rule | Mean Rank: 4.349 -> 10.46 | Hurt |
| scale dataset from small to large (GraphRule) | GraphRule · Wyze Rule | AUC: 0.9768 -> 0.9825 | No clear effect |
| scale dataset from small to large (GraphRule) | GraphRule · Wyze Rule | Test Loss: 0.1997 -> 0.1911 | No clear effect |
| federated (FedRule with FedAvg) instead of centralized training, large dataset | GraphRule · Wyze Rule large | Mean Rank: 10.46 -> 30.92 | Hurt |
| replace FedAvg with FedGate on small dataset | FedRule · Wyze Rule small | Mean Rank: 6.661 -> 4.156 | Improved |
| replace FedAvg with FedGate on large dataset | FedRule · Wyze Rule large | Mean Rank: 30.92 -> 37.99 | Hurt |
| replace FedAvg with FedGate on large dataset | FedRule · Wyze Rule large | AUC: 0.9613 -> 0.9486 | Hurt |
| replace FedAvg with FedGate on small dataset | FedRule · Wyze Rule small | AUC: 0.9521 -> 0.9804 | Improved |
Closest papers by meaning
- RecFlow: An Industrial Full Flow Recommendation Dataset (ICLR 2025 · similarity 0.81)
- Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration (NeurIPS 2024 · similarity 0.81)
- Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized Prompts (AAAI 2025 · similarity 0.81)
- ORBIT - Open Recommendation Benchmark for Reproducible Research with Hidden Tests (NeurIPS 2025 · similarity 0.80)
- Formal Logic Enabled Personalized Federated Learning through Property Inference (AAAI 2024 · similarity 0.79)
- Balancing Similarity and Complementarity for Federated Learning (ICML 2024 · similarity 0.79)
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.
