Guide to Model Architecture Selection for Link Prediction
RHS Model Type | Scoring | Temporal (Add ID-GNN) | Temporal (No ID-GNN) | Static (Add ID-GNN) | Static (No ID-GNN) |
---|---|---|---|---|---|
GNN | Softmax | N/A | N/A | N/A | N/A |
GNN | Contrast | N/A | N/A | N/A | Two-tower module (embedding) |
Shallow | Softmax | ContextGNN module (ranking) | RHSShallow module (embedding) | N/A | RHSShallow module (ranking) |
Shallow | Contrast | N/A | N/A | N/A | N/A |
feature
, lookup
, and fusion
modes are specific to RHSShallow
architectures and is passed to the target_embedding_mode
model parameter.table.entity
that follows after the FOR EACH
statement.table.target
that follows after the PREDICT
statement.Use ContextGNN
if you require temporal modeling and ranking behavior with a shallow RHS.Use RHSShallow
if you’re working with static graphs and want lightweight embedding or ranking models.Use Two-tower
if your goal is contrastive embedding with a static graph and GNN on RHS.