Kumo Relational

Kumo Relational is NVIDIA's pretrained foundation model for classification and regression across related tables using in-context learning. It is based on KumoRFM-2 and combines row embeddings with relational message passing.

Getting Started

Install structured-data-models for inference:

pip install structured-data-models

Load the pretrained model and predict class probabilities:

import sdm

model = sdm.models.KumoRelational(task="classification", device="cuda")
probs = model(
    x_context=x_context,
    y_context=y_context,
    x_query=x_query,
    related_context_tables=related_context,
    related_query_tables=related_query,
    num_estimators=8,
)

To learn more, visit structured-data-models.

License and Third-Party Notice

Kumo Relational weights are released under OpenMDW 1.1.

Kumo Relational finetunes pretrained TabICLv2 weights, licensed under BSD-3-Clause. The upstream attribution, copyright notice, and complete BSD 3-Clause license text are preserved in THIRD-PARTY-NOTICES.txt.