relational

relationalai.semantics.reasoners.predictive.estimators

GNN and RelFM: Graph-driven (relational-schema) predictive estimators.

Both build on the shared PredictiveEstimator base in this package’s base module. Counterpart to relfm_tabular, which handles the single flat-table case instead (and does not share this base — it has no relational schema/join concerns to share).

Classes

Classes exposed by this module.

GNNTrain, load, register and predict with a Graph Neural Network. Re-exported from relationalai.semantics.reasoners.predictive.estimators.relational.gnn.

RelFMPredict in-context with RelFM — a foundation model that requires no training. Re-exported from relationalai.semantics.reasoners.predictive.estimators.relational.relfm.

Modules and Subpackages

Submodules and subpackages available under this namespace.

relfmRelFM estimator: zero-shot, in-context prediction with no training step.

gnnGNN estimator for training, loading, registering and predicting with Graph Neural Networks.