Research map / Graph learning / Graph algorithms and clustering
gOCCF: Graph-Theoretic One-Class Collaborative Filtering Based on Uninteresting Items
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 |
|---|---|---|---|
| add uninteresting items (negative graph) to RWR (ablation) | separateRWR vs RWR · MovieLens | nDCG@10: 0.352 (7.3%) | Helped |
| add uninteresting items to signed BP (ablation) | signedBP vs BP · MovieLens | nDCG@10: 0.438 (27.0%) | Helped |
| add uninteresting items to signed BP (ablation) | signedBP vs BP · Watcha | nDCG@10: 0.190 (41.8%) | Helped |
| add uninteresting items to separateRWR (ablation) | separateRWR vs RWR · CiteULike | nDCG@10: 0.202 (18.2%) | Helped |
| add uninteresting items to signed BP (ablation) | signedBP vs BP · CiteULike | nDCG@10: 0.138 (2.3%) | Helped |
| set number of U-items equal to number of positive links (R-region) instead of far fewer or far more (ablation) | separateRWR and signedBP · MovieLens | nDCG@10 | Helped |
| use too many U-items (D-region) in signed BP (ablation) | signedBP · MovieLens | nDCG@10 | Hurt |
| use gOCCF signedBP instead of WRMF on sparse dataset | signedBP · Watcha | nDCG@10: 0.182 -> 0.190 | Helped |
| use gOCCF signedBP instead of WRMF on dense dataset | signedBP · MovieLens | nDCG@10: 0.460 -> 0.438 | Hurt |
| use separateRWR instead of best OCCF baseline BPRMF | separateRWR · CiteULike | nDCG@10: 0.136 -> 0.202 | Helped |
| apply naive zero-injection to SVD/PMF CF in one-class setting with varying theta | SVD/PMF CF · CiteULike | MRR | Mixed |
Closest papers by meaning
- How Does Message Passing Improve Collaborative Filtering? (NeurIPS 2024 · similarity 0.87)
- From Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking (AAAI 2025 · similarity 0.86)
- Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation (ICML 2024 · similarity 0.86)
- Adaptive Hardness Negative Sampling for Collaborative Filtering (AAAI 2024 · similarity 0.86)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.86)
- Social Recommendation via Graph-Level Counterfactual Augmentation (AAAI 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.