不考虑feature，只训练node的话，是不是encoders.py就没用了呀
Open
- Dominant language
- C++
- Stars
- 2.9k
- Forks
- 553
- PR merge metrics
- No merged PRs in 30d
Description
您好，咨询一下，
如果不考虑融合feature的embedding，只训练node的话，是不是encoders.py就没用了呀？
比如Node2Vec和LINE，不考虑特征的话是不是直接用layer.Embedding(inputs)就行了？
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reading encoders.py and locating the Node2Vec and LINE entry points mentioned in the issue. Check how layer.Embedding is currently used and whether feature embeddings are optional. A complete outcome would need a maintainer decision on the node-only path and its expected implementation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100