Research map / Label-efficient and robust learning / Recognition and long-tail
Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction
Tianwei Cao, Qianqian Xu, Zhiyong Yang, Qingming Huang
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 |
|---|---|---|---|
| add attentive feature selector (C1) to the base predictor (ablation) | Base model · five CTR datasets | AUC | Improved |
| add the auxiliary feature-selection loss (C2) to the attentive selector (ablation) | M1 · five CTR datasets | AUC | Improved |
| add the GDmax wrapper with N=1 (C3) without the second term (ablation) | M2 · five CTR datasets | AUC | Hurt |
| add the second meta-learned term (C4) with N=1 (ablation) | M3 · five CTR datasets | AUC | Improved |
| use second-order crossing models over high-order ones (Wide&Deep, PNN, DeepFM vs xDeepFM, FGCNN) | feature-crossing baselines · Electronics | AUC: 0.7979 vs 0.7800 | Improved |
| replace general feature selection (AutoFIS) with attention (DIN) | user-behavior CTR models · Books | AUC: 0.7789 -> 0.7818 | Improved |
| replace DIN with Meta-Wrapper | DIN · Books | AUC: 0.7818 -> 0.8237 | Improved |
| add attentive feature selector to base model on noisy synthetic data | Base · synthetic noisy data | AUC | Hurt |
| add L2 weight decay or dropout to the feature selector model | FS · synthetic noisy data | AUC | No clear effect |
| replace FS with Meta-Wrapper | FS · synthetic noisy data | AUC | Improved |
Closest papers by meaning
- From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models (ICML 2025 · similarity 0.89)
- Addressing Cold-Start Problem in Click-Through Rate Prediction via Supervised Diffusion Modeling (AAAI 2025 · similarity 0.86)
- AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction (AAAI 2024 · similarity 0.86)
- Generalize for Future: Slow and Fast Trajectory Learning for CTR Prediction (AAAI 2024 · similarity 0.84)
- Long-Sequence Recommendation Models Need Decoupled Embeddings (ICLR 2025 · similarity 0.83)
- Plug-In Diffusion Model for Sequential Recommendation (AAAI 2024 · similarity 0.82)
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.
