Research map / Learning theory and algorithms / Prediction and decision losses
Unveiling Extraneous Sampling Bias with Data Missing-Not-At-Random
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies selection bias in recommender-style data where missingness is not at random, identifying an extraneous sampling bias that arises beyond exact matching of units.
Problem
Selection bias from users' selective interactions with items undermines unbiased evaluation and learning; existing doubly robust methods only handle simple exact-matching scenarios.
Approach
Extends doubly robust debiasing beyond exact matching to a setting with extraneous sampling bias under missing-not-at-random data; the abstract indicates the work targets this broader matching scenario, but details are not available in the provided text.
Experimental setup
Builds on: doubly robust estimation
Closest papers by meaning
- Relaxing the Accurate Imputation Assumption in Doubly Robust Learning for Debiased Collaborative Filtering (ICML 2024 · similarity 0.90)
- Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random (NeurIPS 2024 · similarity 0.88)
- SEBRA : Debiasing through Self-Guided Bias Ranking (ICLR 2025 · similarity 0.85)
- Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation (NeurIPS 2024 · similarity 0.85)
- Mitigating Spurious Correlations via Disagreement Probability (NeurIPS 2024 · similarity 0.85)
- Debiased Collaborative Filtering with Kernel-Based Causal Balancing (ICLR 2024 · 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.