Research map / Learning theory and algorithms / Prediction and decision losses
CARE: Adaptive Calibration for Reliable Recommendations
Nitin Bisht, Huan Huo, Xiuwen Gong, Guandong 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 |
|---|---|---|---|
| wrap NeuMF with CARE adaptive calibration | NeuMF · Book-Crossing | MRR / Recall@10: MRR 0.246 -> 0.289; Recall 0.502 -> 0.557 | Improved |
| wrap FMLP-Rec with CARE | FMLP-Rec · Book-Crossing | MRR / Recall@10: 0.335 -> 0.357; 0.599 -> 0.628 | Improved |
| wrap SASRec with CARE | SASRec · Last.fm | Recall@10: 0.766 -> 0.799 | Improved |
| wrap CASER with CARE | CASER · Last.fm | NDCG@10: 0.367 -> 0.385 | Improved |
| use CARE-wrapped backbone instead of preference-aware Oracle4Rec | Oracle4Rec · Book-Crossing | Recall@10: 0.603 -> 0.628 (FMLP-Rec + CARE) | Improved |
| use CARE instead of fixed-threshold Split Conformal | Split Conformal · Book-Crossing, alpha=0.10, SASRec | coverage: 0.835 -> 0.908 | Improved |
| use CARE instead of EnbPI fixed-window calibration | EnbPI · Book-Crossing, alpha=0.10, SASRec | set size: 47 -> 43 | Improved |
| use CARE instead of Online Conformal | Online Conformal · Book-Crossing, alpha=0.10, FMLP-Rec | set size: 45 -> 42 | Improved |
| use CARE instead of Split Conformal on NeuMF | Split Conformal · Book-Crossing, alpha=0.10, NeuMF | set size: 44 -> 46 | Hurt |
| add CARE online calibration phase to backbone training | SASRec · Book-Crossing training time (minutes) | training time: 35.2 -> 36.5 | Hurt |
Closest papers by meaning
- Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems (NeurIPS 2022 · similarity 0.86)
- On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders (NeurIPS 2025 · similarity 0.86)
- Influential Exemplar Replay for Incremental Learning in Recommender Systems (AAAI 2024 · similarity 0.86)
- Would You Like Your Data to Be Trained? A User Controllable Recommendation Framework (AAAI 2024 · similarity 0.85)
- Ready for You When You Are Back: Content-Driven Session-Based Recommendation for Continuity of Experience (AAAI 2025 · similarity 0.85)
- LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · 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.
