Research map / Learning theory and algorithms / Kernels and regression theory
StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Stable-DR instead of SNIPS | NCF · Coat | MSE: 0.1904 -> 0.1896 | Helped |
| Use Stable-DR instead of SNIPS | NCF · Coat | AUC: 0.7707 -> 0.7712 | Helped |
| Use Stable-DR instead of SNIPS | NCF · Yahoo! R3 | MSE: 0.1694 -> 0.1664 | Helped |
| Use Stable-DR instead of SNIPS | NCF · Yahoo! R3 | N@5: 0.6693 -> 0.6756 | Helped |
| Set stabilization-constraint strength to zero (ablation) | Stable-DR and Stable-MRDR · Coat and Yahoo! R3 | debiasing performance | Mixed |
| Increase stabilization-constraint strength from zero to an appropriate nonzero level (ablation) | Stable-DR and Stable-MRDR · Coat and Yahoo! R3 | debiasing performance | Helped |
| Use the cycle-learning stabilization method rather than DR-JL/MRDR-JL | Stable-DR and Stable-MRDR · Coat and Yahoo! R3; Naive Bayes and logistic regression propensity models | debiasing performance | Helped |
Closest papers by meaning
- Relaxing the Accurate Imputation Assumption in Doubly Robust Learning for Debiased Collaborative Filtering (ICML 2024 · similarity 0.87)
- LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · similarity 0.85)
- Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning (ICML 2025 · similarity 0.84)
- Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random (NeurIPS 2024 · similarity 0.83)
- Deletion-Robust Submodular Maximization with Knapsack Constraints (AAAI 2024 · similarity 0.83)
- Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses (ICML 2024 · similarity 0.83)
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.