node embeddings
Node embeddings are vector representations of nodes in a graph that capture their structural and relational features. In AI, they allow for the application of machine learning techniques to graph-based data and improve tasks like link prediction and clustering.
- Future Link Prediction Without Memory or Aggregation
- Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection
- Subgraph Federated Learning via Spectral Methods
- TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction
- Understanding and Enhancing Message Passing on Heterophilic Graphs via Compatibility Matrix