Research map / Learning theory and algorithms / Prediction and decision losses
Deconvolving Feedback Loops in Recommender Systems
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 |
|---|---|---|---|
| Increase the deconvolution parameter α (ablation) | Deconvolving Feedback Loops · Synthetic recommender system | ROC discrimination | Helped |
| Decrease the deconvolution parameter α (ablation) | Deconvolving Feedback Loops · Synthetic recommender system | ROC performance | Hurt |
| Decrease true-rating sparsity γ (ablation) | Deconvolving Feedback Loops · Synthetic recommender system | ROC performance | Hurt |
| Vary the acceptance exponent e (ablation) | Synthetic recommender system · Synthetic recommender system | Recommendation-effect score | Helped |
| Use the strong social-influence condition rather than the weak condition | MusicLab · MusicLab-Weak and MusicLab-Strong | RS score: 0.1073 -> 0.1509 | Helped |
| Use the later, larger MovieLens dataset | Deconvolving Feedback Loops · MovieLens-100K, MovieLens-1M, MovieLens-10M | RS score: 0.2834 -> 0.3033 -> 0.3821 | Helped |
| Use Netflix rather than MovieLens-10M | Deconvolving Feedback Loops · Netflix and MovieLens-10M | RS score: 0.3821 -> 0.2661 | Hurt |
Closest papers by meaning
- Learning to Recommend from Sparse Data via Generative User Feedback (AAAI 2021 · similarity 0.90)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.87)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.87)
- Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation (NeurIPS 2025 · similarity 0.86)
- Influential Exemplar Replay for Incremental Learning in Recommender Systems (AAAI 2024 · similarity 0.86)
- Tree of Preferences for Diversified Recommendation (NeurIPS 2025 · similarity 0.86)
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.