Research map / Architectures and efficiency / Pruning and efficient tuning
Obliviate: Efficient Unlearning in Recommender Systems
Tushar Prakash, Brijraj Singh, Niranjan Pedanekar, Narayan Chaturvedi
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 |
|---|---|---|---|
| add LUA low-rank downdate stage (ablation) | Obliviate · ML-1M MF-BPR | Recall@20: 0.1921 -> 0.1932 | Improved |
| add LAC calibration stage (ablation) | Obliviate · Yelp LightGCN | Recall@20: 0.0518 -> 0.0530 | Improved |
| add distillation loss in LAC (ablation) | Obliviate · Amazon MF-BPR | Recall@20: 0.0228 -> 0.0232 | Improved |
| add distillation loss in LAC (ablation) | Obliviate · ML-1M LightGCN | Recall@20: 0.2319 -> 0.2332 | Improved |
| use Obliviate unlearning vs IFRU | Obliviate · Yelp LightGCN | Recall@20: 0.0444 -> 0.0530 | Improved |
| use Obliviate unlearning vs full retraining on time | Obliviate · ML-1M MF-BPR | time (s): 533.50 -> 19.95 | Improved |
| use Obliviate instead of sharding (SISA) for unlearning time | Obliviate · Yelp LightGCN | time (s): 1922.82 -> 57.23 | Improved |
| increase LAC calibration steps | Obliviate · hard unlearning setting | completeness | Improved |
| use Obliviate vs RRL | Obliviate · Amazon MF-BPR | Recall@20: 0.0226 -> 0.0232 | Improved |
| use Obliviate vs RRL on unlearning time | Obliviate · ML-1M MF-BPR | time (s): 18.23 vs 19.95 | No clear effect |
Closest papers by meaning
- CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence (NeurIPS 2024 · similarity 0.90)
- Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens (ICML 2025 · similarity 0.85)
- Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints (AAAI 2025 · similarity 0.85)
- Influential Exemplar Replay for Incremental Learning in Recommender Systems (AAAI 2024 · similarity 0.85)
- LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling (NeurIPS 2026 · similarity 0.84)
- Tree of Preferences for Diversified Recommendation (NeurIPS 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.
