Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Comprehensive Recommender Systems: Time-Aware Unified Recommendations Based on Listwise Ranking of Implicit Cross-Network Data
Dilruk Perera, Roger Zimmermann
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 |
|---|---|---|---|
| Use the time-aware unified cross-network model instead of the evaluated baselines | YouTube recommendations using Twitter auxiliary data · CrossNet | HR@10 | Improved |
| Use cross-network information rather than single-network models | YouTube recommendations · CrossNet | HR@10 | Improved |
| Incorporate temporal information | Unified cross-network recommendation · CrossNet | HR@10 | Improved |
| Use the proposed listwise loss instead of pointwise or pairwise optimization | MF · MovieLens | AUC | Improved |
| Use short-term and long-short-term preferences rather than relying only on long-term preferences | Proposed recommender · CrossNet | novelty | Improved |
| Use short-term and long-short-term preferences rather than relying only on long-term preferences | Proposed recommender · CrossNet | diversity | Improved |
| Add long-term preferences (ablation) | Proposed recommender · CrossNet | accuracy | Improved |
| Add long-short-term preferences (ablation) | Proposed recommender · CrossNet | accuracy | Improved |
| Add short-term preferences (ablation) | Proposed recommender · CrossNet | accuracy | Improved |
| Add all three temporal preference components (ablation) | Proposed recommender · CrossNet | accuracy | Improved |
| Use biweekly rather than monthly training intervals | Proposed recommender · CrossNet | HR@10 | Improved |
| Use a larger training set | Evaluated recommendation models · CrossNet | HR@10 | Improved |
Closest papers by meaning
- Infinite Recommendation Networks: A Data-Centric Approach (NeurIPS 2022 · similarity 0.87)
- Graph Heterogeneous Multi-Relational Recommendation (AAAI 2021 · similarity 0.86)
- KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation (NeurIPS 2026 · similarity 0.86)
- A Hybrid Collaborative Filtering Model with Deep Structure for Recommender Systems (AAAI 2017 · similarity 0.86)
- SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback (AAAI 2020 · similarity 0.85)
- Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations (ICML 2024 · 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.
