Research map / Label-efficient and robust learning / Knowledge distillation
Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender Systems
Zhangchi Zhu, Wei Zhang
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 |
|---|---|---|---|
| Compute CE only on teacher's top items (vanilla CE) vs RCE-KD's split-and-sample scheme | CE-based KD for recommenders · CiteULike/Gowalla/Yelp2018 | Recall/NDCG: RCE-KD best in all 12 metrics per setting; e.g. Gowalla MF->MF R@20 0.1427 -> 0.1525 vs best baseline | Improved |
| Add separate losses for the two teacher-top-item subsets (ablation) | RCE-KD · Gowalla, Yelp2018 | Recall/NDCG | Improved |
| Use adaptive gamma weight instead of constant (ablation) | RCE-KD · Gowalla, Yelp2018 | Recall/NDCG | Improved |
| Include student's top items (not only teacher's top items) in the CE item set (ablation) | RCE-KD · Gowalla, Yelp2018 | Recall/NDCG | Improved |
| RCE-KD sampled subset vs full-item CE (ablation) | RCE-KD · Gowalla, Yelp2018 | Recall/NDCG | No clear effect |
| Use RCE-KD instead of other KD methods, training cost | Student MF on Gowalla · Gowalla | training time per epoch (s): RCE-KD 99.30 vs RRD 132.37, HetComp 137.62, Student 27.33 | Mixed |
Closest papers by meaning
- PLD: A Choice-Theoretic List-Wise Knowledge Distillation (NeurIPS 2025 · similarity 0.86)
- Influential Exemplar Replay for Incremental Learning in Recommender Systems (AAAI 2024 · similarity 0.84)
- Towards Unbiased Information Extraction and Adaptation in Cross-Domain Recommendation (AAAI 2025 · similarity 0.84)
- Enhancing Logits Distillation with Plug&Play Kendall's $\tau$ Ranking Loss (ICML 2025 · similarity 0.84)
- Domain-Level Disentanglement Framework Based on Information Enhancement for Cross-Domain Cold-Start Recommendation (AAAI 2025 · similarity 0.83)
- Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation (AAAI 2024 · 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.
