Research map / Label-efficient and robust learning / Recognition and long-tail
Discrete Social Recommendation
Chenghao Liu, Xin Wang, Tao Lu, Wenwu Zhu, Jianling Sun, Steven Hoi
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 |
|---|---|---|---|
| learn binary codes directly with balanced and uncorrelated constraints (DSR) instead of round-off binarizing CFSR (CFSRB) (ablation) | CFSRB · CiaoDVD, Epinions, FilmTrust in-matrix | NDCG@K | Improved |
| add social information (DSR vs DCF) (ablation) | discrete collaborative filtering (DCF) · CiaoDVD, Epinions, FilmTrust in-matrix | NDCG@K | Improved |
| binarize latent vectors (DSR vs real-valued CFSR) at code length 32 | CFSR · in-matrix and out-matrix recommendation | NDCG@K / Recall@K | No clear effect |
| binarize latent vectors (DSR vs real-valued CFSR) at short code lengths | CFSR · in-matrix recommendation | NDCG@K | Hurt |
| binarize latent vectors (DSR vs real-valued CFSR) | CFSR · CiaoDVD, FilmTrust, Epinions | model memory: 14.57MB -> 407KB (x37) | Improved |
| binarize latent vectors (DSR vs real-valued CFSR) | CFSR · CiaoDVD, FilmTrust, Epinions | test time cost: nearly 5 times faster | Improved |
| initialize DSR from relaxed real-valued solution (ablation) | DSR · CiaoDVD r=16 | objective convergence | Improved |
| increase social weight alpha0 (ablation) | DSR · CiaoDVD, FilmTrust, Epinions | NDCG@10 | Mixed |
Closest papers by meaning
- Multi-Feature Discrete Collaborative Filtering for Fast Cold-Start Recommendation (AAAI 2020 · similarity 0.88)
- Discrete Personalized Ranking for Fast Collaborative Filtering from Implicit Feedback (AAAI 2017 · similarity 0.87)
- Social Collaborative Filtering by Trust (TPAMI 2016 · similarity 0.87)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.85)
- Optimizing Recall in Deep Graph Hashing Framework for Item Retrieval (Student Abstract) (AAAI 2024 · similarity 0.85)
- Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation (ICML 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.
