DCN-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 SystemsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Recommendation Systems | 2 | 22.22% |
Image Generation | 1 | 11.11% |
Sentence | 1 | 11.11% |
Ensemble Learning | 1 | 11.11% |
Medical Object Detection | 1 | 11.11% |
Object Detection | 1 | 11.11% |
Click-Through Rate Prediction | 1 | 11.11% |
Learning-To-Rank | 1 | 11.11% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |