Accenture / Accenture/AmpliGraph
Implement NodePieces
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.2k
- Forks
- 257
- PR merge metrics
- No merged PRs in 30d
Description
*Background and Context
Hey guys,
would be awesome if you could also implement the inductive version of NodePieces (https://github.com/migalkin/NodePiece).
Description
Background: i have a task where i want to find the most similar nodes/entities to a given, unseen node/entity in the graph.
Best regards
Chris
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 reading the linked NodePiece reference and examining AmpliGraph’s existing Python representation-learning structure. Define the scope for inductive support, including how unseen nodes are handled, and consider how completion would be verified for similarity queries involving unseen entities.
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
- 25/100