Research map / Federated learning and privacy / Privacy attacks and secure learning
FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training
Yuyuan Li, Junjie Fang, Fengyuan Yu, Xichun Sheng, Tianyu Du, Xuyang Teng, Shaowei Jiang, Linbo Jiang, Jianan Lin, Chaochao 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 |
|---|---|---|---|
| use FedAU2 attribute unlearning instead of no unlearning | FedNCF and FedVAE · ML-1M, ML-100K, LastFM | BAcc: average BAcc reduction 26.42% vs 11.5% for APM | Improved |
| use FedAU2 on a personalized model | FedRAP · three datasets | BAcc: 14.09% vs 9.24% for APM | Improved |
| FedAU2 versus APM on recommendation quality | FedRecs · three datasets | NDCG@10: -4.51% (FedAU2) vs -20.05% (APM) | Improved |
| add SUT instead of Global adversarial training (ablation) | FedAU2 · ML-1M (gender) | NDCG@10 | Improved |
| use SUT instead of Pretrain for adversarial model (ablation) | FedAU2 · ML-1M (gender) | BAcc | Improved |
| use DSVAE instead of original MLP adversary (ablation) | FedVAE · ML-1M (gender), gradient attack | attack accuracy: 90% -> 58% | Improved |
| use plain VAE instead of original MLP adversary (ablation) | FedVAE · ML-1M (gender), gradient attack | attack accuracy: 90% -> 89% | No clear effect |
| increase stochasticity coefficient lambda (ablation) | DSVAE · ML-1M (gender), FedVAE | BAcc / NDCG@10 | Mixed |
| FedAU2 on FedRAP recommendation | FedRAP · three datasets | HR@10/NDCG@10: ML-1M gender NDCG@10 0.2381 -> 0.2437 | No clear effect |
Closest papers by meaning
- Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach (AAAI 2025 · similarity 0.86)
- Federated Recommendation with Additive Personalization (ICLR 2024 · similarity 0.86)
- NoT: Federated Unlearning via Weight Negation (CVPR 2025 · similarity 0.86)
- CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence (NeurIPS 2024 · similarity 0.86)
- Attribute Inference Attacks for Federated Regression Tasks (AAAI 2025 · similarity 0.85)
- Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients (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.
