Research map / Learning theory and algorithms / Prediction and decision losses
Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems
Jia-Qi Yang, De-Chuan Zhan
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 |
|---|---|---|---|
| set alpha to zero (remove sample-complexity weight) (ablation) | GDFM · Criteo | AUC: 0.8349 -> 0.8333 | Hurt |
| set beta to zero (remove temporal weight) (ablation) | GDFM · Criteo | PR-AUC: 0.6311 -> 0.6314 | No clear effect |
| set lambda to zero (remove regularizer) (ablation) | GDFM · Criteo | NLL: 0.3960 -> 0.3988 | Hurt |
| add synthetic action informative with p=0.5 | GDFM · Criteo | AUC: 0.8349 -> 0.835 | No clear effect |
| raise informativeness of added action from p=0.5 to p=0.95 | GDFM · Criteo | AUC: 0.835 -> 0.840 | Improved |
| raise informativeness of added action from p=0.5 to p=0.95 | GDFM · Criteo | NLL: 0.396 -> 0.391 | Improved |
| raise informativeness of added action from p=0.5 to p=0.95 | GDFM · Criteo | PR-AUC: 0.631 -> 0.641 | Improved |
| use FNW instead of GDFM | FNW · Taobao | NLL: -361 | Hurt |
| use ES-DFM instead of GDFM | ES-DFM · Taobao | NLL: -214 | Hurt |
| use MM-DFM instead of GDFM | MM-DFM · Criteo | PR-AUC: 68.1 -> 39.2 | Hurt |
| use Vanilla instead of GDFM | Vanilla · Criteo | AUC: 74.9 -> 25.2 | Hurt |
| use ES-DFM instead of GDFM | ES-DFM · Taobao | PR-AUC: 80.7 -> 19.6 | Hurt |
Closest papers by meaning
- Addressing Cold-Start Problem in Click-Through Rate Prediction via Supervised Diffusion Modeling (AAAI 2025 · similarity 0.86)
- Would You Like Your Data to Be Trained? A User Controllable Recommendation Framework (AAAI 2024 · similarity 0.85)
- AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction (AAAI 2024 · similarity 0.85)
- Entire-Space Variational Information Exploitation for Post-Click Conversion Rate Prediction (AAAI 2025 · similarity 0.84)
- Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation (NeurIPS 2025 · similarity 0.84)
- Enhancing Sequential Recommendation with Global Diffusion (AAAI 2025 · 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.
