Research map / Probabilistic and scientific modeling / Molecules and proteins
Counterfactual Implicit Feedback Modeling
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.
Proposes a counterfactual modeling approach for implicit feedback in recommendation that addresses positive-unlabeled and missing-not-at-random challenges.
Problem
Relevance prediction from implicit feedback in recommender systems faces positive-unlabeled ambiguity (negative feedback does not imply low relevance) and missing-not-at-random exposure bias (popular or frequently recommended items get more clicks).
Approach
Uses counterfactual reasoning over implicit feedback to correct for the PU and MNAR biases when predicting relevance; the abstract gives no further method detail.
Closest papers by meaning
- Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation (NeurIPS 2024 · similarity 0.85)
- Alleviating Dual Biases in Recommendation (Student Abstract) (AAAI 2025 · similarity 0.85)
- Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning (ICML 2025 · similarity 0.84)
- CoreRec: A Counterfactual Correlation Inference for Next Set Recommendation (AAAI 2024 · similarity 0.83)
- Counterfactual Task-augmented Meta-learning for Cold-start Sequential Recommendation (AAAI 2025 · similarity 0.83)
- Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings (NeurIPS 2025 · 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.