Skip to content
This repository was archived by the owner on Nov 18, 2023. It is now read-only.

Commit 2c8c0cd

Browse files
authored
Update README.md
1 parent 0a73f04 commit 2c8c0cd

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed

README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -4,10 +4,10 @@
44
[![Stack Overflow](https://img.shields.io/badge/stackoverflow-typedb-796de3.svg)](https://stackoverflow.com/questions/tagged/typedb)
55
[![Stack Overflow](https://img.shields.io/badge/stackoverflow-typeql-3dce8c.svg)](https://stackoverflow.com/questions/tagged/typeql)
66

7-
# TypeDB ML
7+
# TypeDB-ML
88
_Previously known as KGLIB._
99

10-
**TypeDB ML provides tools to enable graph algorithms and machine learning with [TypeDB](https://github.com/vaticle/typedb).**
10+
**TypeDB-ML provides tools to enable graph algorithms and machine learning with [TypeDB](https://github.com/vaticle/typedb).**
1111

1212
There are integrations for [NetworkX](https://networkx.org) and for [PyTorch Geometric (PyG)](https://github.com/pyg-team/pytorch_geometric).
1313

@@ -22,7 +22,7 @@ There are integrations for [NetworkX](https://networkx.org) and for [PyTorch Geo
2222
- Query a TypeDB instance and combine many results across many queries into a single graph (`build_graph_from_queries`).
2323
### PyTorch Geometric
2424
- A `DataSet` object to lazily load graphs from a TypeDB instance. Each graph is converted to a PyG `Data` object.
25-
- It's most natural to work with `HeteroData` objects since all data in TypeDB has a type. This conversion is available by default in PyG, but TypeDB-ML provides `store_concepts_by_type` to map concepts by type so that they can be re-associated after learning is finished.
25+
- It's most natural to work with PyG `HeteroData` objects since all data in TypeDB has a type. Conversion from `Data` to `HeteroData`is available in PyG, but it loses node ordering information. To remedy this, TypeDB-ML provides `store_concepts_by_type` to store concepts consistent with a `HeteroData` object. This enables concepts to be properly re-associated with predictions after learning is finished.
2626
- A `FeatureEncoder` to orchestrate encoders to generate features for graphs.
2727
- Encoders for Continuous and Categorical values to apply encodings/embedding spaces to the types and attribute values present in TypeDB data.
2828
- A [full example for link prediction](examples/diagnosis)

0 commit comments

Comments
 (0)