Research map / Graph learning / Graph algorithms and clustering
Binary Rating Estimation with Graph Side Information
Kwangjun Ahn, Kangwook Lee, Hyunseung Cha, Changho Suh
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 |
|---|---|---|---|
| Add social graph side information when users outnumber items enough (n=2m, Is = c log(2n)/n) | optimal sample complexity for binary rating recovery · two-cluster binary rating model | sample complexity: reduced by a multiplicative factor of c/2 | Improved |
| Add social graph side information when n = m^2 | optimal sample complexity · two-cluster binary rating model | sample complexity: order-wise reduction to n^(2-c) log n | Improved |
| Add social graph side information when users are few relative to items (2n log n <= 4 gamma m log m) | optimal sample complexity · two-cluster binary rating model | sample complexity | No clear effect |
| Increase graph quality Is beyond saturation threshold | optimal sample complexity · two-cluster binary rating model | sample complexity | No clear effect |
| Use graph-aware algorithm instead of 7 recommendation baselines (user/item average, kNN, SoReg, biased MF, TrustSVD) | proposed algorithm · Poliblog and Facebook graphs with synthetic ratings | MAE | Improved |
Closest papers by meaning
- Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information (ICML 2021 · similarity 0.89)
- Negative Sampling From the Ground Up: A Redesign for Recommendation (ICML 2026 · similarity 0.86)
- Matrix Completion with Hierarchical Graph Side Information (NeurIPS 2020 · similarity 0.85)
- Graph Resistance and Learning from Pairwise Comparisons (ICML 2019 · similarity 0.83)
- gOCCF: Graph-Theoretic One-Class Collaborative Filtering Based on Uninteresting Items (AAAI 2018 · similarity 0.83)
- Adaptive Hardness Negative Sampling for Collaborative Filtering (AAAI 2024 · similarity 0.82)
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.
