Survey On Knowledge Graph For RecSys

Created: 2022-08-12 15:49
#note

A knowledge graph is a heterogeneous graph where nodes represent entities and edges represent relations between entities -> we can map items and their attributes to understand the mutual relations between items.
This can help in case of data sparsity (Cold-start) or performance problems. Another quality of KG-based recommendation is the interpretability.
They are often use to provide side information to recommender systems

KGs can be applied in three ways: the embedding-based method, the path-based method and the unified method.

References

1. Survey

Code

Tags

#TBD