Learning to Rank Models
DCN-V2
Introduced by Wang et al. in DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank SystemsDCN-V2 is an architecture for learning-to-rank that improves upon the original DCN model. It first learns explicit feature interactions of the inputs (typically the embedding layer) through cross layers, and then combines with a deep network to learn complementary implicit interactions. The core of DCN-V2 is the cross layers, which inherit the simple structure of the cross network from DCN, however it is significantly more expressive at learning explicit and bounded-degree cross features.
Source: DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Recommendation Systems | 2 | 20.00% |
| Image Generation | 1 | 10.00% |
| Sentence | 1 | 10.00% |
| Ensemble Learning | 1 | 10.00% |
| Fracture detection | 1 | 10.00% |
| Medical Object Detection | 1 | 10.00% |
| Object Detection | 1 | 10.00% |
| Click-Through Rate Prediction | 1 | 10.00% |
| Learning-To-Rank | 1 | 10.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
