shenweichen / shenweichen/DeepCTR-Torch
Custom Loss Function within xDeepFM API
Open
Nobody has claimed this yet.
question
- Dominant language
- Python
- Stars
- 3.5k
- Forks
- 733
- PR merge metrics
- No merged PRs in 30d
Description
Describe the question(问题描述)
I noticed that the xDeepFM model API within this repo only supports 2 task
- "binary" for binary log loss
- "regression" for regression loss
Does the package supports the integration of other loss function? e.g. Ranking related losses such as Hinge loss
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the xDeepFM API and the task/loss handling it exposes; the issue names no file or test. Determine whether custom and ranking losses are intended to be supported, then define the required API behavior and validation before implementation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100