Research map / Label-efficient and robust learning / Recognition and long-tail
DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System
Zhi-Hong Deng, Ling Huang, Chang-Dong Wang, Jian-Huang Lai, Philip S. Yu
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 |
|---|---|---|---|
| combine representation learning and matching function learning components | CFNet · ml-1m | HR@10: 0.7210 -> 0.7253 | Improved |
| combine representation learning and matching function learning components | CFNet · lastfm | HR@10: 0.8868 -> 0.8995 | Improved |
| combine representation learning and matching function learning components | CFNet · AMusic | HR@10: 0.3891 -> 0.4116 | Improved |
| combine representation learning and matching function learning components | CFNet · AToy | HR@10: 0.3650 -> 0.4150 | Improved |
| replace cosine similarity with element-wise product and a learned output layer | CFNet-rl · implicit-feedback datasets | HR@10 | Improved |
| add pre-training of CFNet-rl and CFNet-ml (ablation) | CFNet · ml-1m | HR: 0.6962 -> 0.7253 | Improved |
| add pre-training of CFNet-rl and CFNet-ml (ablation) | CFNet · lastfm | HR: 0.8685 -> 0.8995 | Improved |
| add pre-training of CFNet-rl and CFNet-ml (ablation) | CFNet · AMusic | HR: 0.3530 -> 0.4116 | Improved |
| add pre-training of CFNet-rl and CFNet-ml (ablation) | CFNet · AToy | HR: 0.3067 -> 0.4150 | Improved |
| increase predictive-vector dimensions from 8 to 64 (ablation) | CFNet · ml-1m | HR@10: 0.6820 -> 0.7253 | Improved |
| increase predictive-vector dimensions from 8 to 64 (ablation) | CFNet · lastfm | HR@10: 0.8840 -> 0.8995 | Improved |
| increase predictive-vector dimensions from 8 to 64 (ablation) | CFNet · AMusic | HR@10: 0.4003 -> 0.4116 | Mixed |
Closest papers by meaning
- A Hybrid Collaborative Filtering Model with Deep Structure for Recommender Systems (AAAI 2017 · similarity 0.89)
- FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens (NeurIPS 2025 · similarity 0.86)
- Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach (ICML 2021 · similarity 0.86)
- Language Representations Can be What Recommenders Need: Findings and Potentials (ICLR 2025 · similarity 0.84)
- Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach (AAAI 2025 · similarity 0.83)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 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.
