Research map / Probabilistic and scientific modeling / Molecules and proteins
A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations
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 |
|---|---|---|---|
| combine time-specific meta-learning with time-evolving RNN | Netflix recommendation · Netflix | RMSE: 0.9213$\pm$0.05 -> 0.8925$\pm$0.03 | Helped |
| combine time-specific meta-learning with time-evolving RNN | Netflix recommendation · Netflix | NDCG: 0.3246 -> 0.3472 | Helped |
| combine time-specific meta-learning with time-evolving RNN | Last.fm recommendation · Last.fm | RMSE: 1.2408$\pm$0.24 -> 1.2203$\pm$0.16 | Helped |
| combine time-specific meta-learning with time-evolving RNN | Last.fm recommendation · Last.fm | NDCG: 0.3142 -> 0.3385 | Helped |
| combine time-specific meta-learning with time-evolving RNN | MovieLens-1M recommendation · MovieLens-1M | RMSE: 1.0483$\pm$0.03 -> 0.9945$\pm$0.08 | Helped |
| combine time-specific meta-learning with time-evolving RNN | MovieLens-1M recommendation · MovieLens-1M | NDCG: 0.3244 -> 0.3351 | Helped |
| add time-evolving RNN to time-specific meta-learning (ablation) | Ours · Netflix | RMSE: 0.9380$\pm$0.02 -> 0.8925$\pm$0.03 | Helped |
| add time-evolving RNN to time-specific meta-learning (ablation) | Ours · Last.fm | RMSE: 1.2791$\pm$0.12 -> 1.2203$\pm$0.16 | Helped |
| add time-evolving RNN to time-specific meta-learning (ablation) | Ours · MovieLens-1M | RMSE: 1.0935$\pm$0.07 -> 0.9945$\pm$0.08 | Helped |
| add time-specific meta-learning to time-evolving RNN (ablation) | Ours · Netflix | NDCG: 0.3011 -> 0.3472 | Helped |
| add time-specific meta-learning to time-evolving RNN (ablation) | Ours · Last.fm | NDCG: 0.2910 -> 0.3385 | Helped |
| add time-specific meta-learning to time-evolving RNN (ablation) | Ours · MovieLens-1M | NDCG: 0.3162 -> 0.3351 | Helped |
Closest papers by meaning
- Temporally and Distributionally Robust Optimization for Cold-Start Recommendation (AAAI 2024 · similarity 0.90)
- Counterfactual Task-augmented Meta-learning for Cold-start Sequential Recommendation (AAAI 2025 · similarity 0.90)
- Addressing Cold-Start Problem in Click-Through Rate Prediction via Supervised Diffusion Modeling (AAAI 2025 · similarity 0.86)
- Preference Aware Dual Contrastive Learning for Item Cold-Start Recommendation (AAAI 2024 · similarity 0.86)
- Influential Exemplar Replay for Incremental Learning in Recommender Systems (AAAI 2024 · similarity 0.86)
- Ready for You When You Are Back: Content-Driven Session-Based Recommendation for Continuity of Experience (AAAI 2025 · similarity 0.85)
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.