How to Make Zero-Training Tabular Predictions with NVIDIA Structured Data Models

In this tutorial, we implement Structured Data Models, NVIDIA's new library that puts several pretrained foundation models for tables behind one PyTorch interface, and use it to make predictions without training. The library wraps TabICLv2 and KumoTabular for single tables and KumoRelational for whole relational databases. Each model answers by in-context learning: we hand the model a set of labeled rows and the rows we want predicted, and it returns probabilities or a full predictive distribution in one forward pass.

We start with the library's typed table tensors and compare the two tabular models against trained scikit-learn baselines. We then reuse an encoded context across many queries, read calibrated prediction intervals off a regression, and scale to twenty classes. Next, we examine the places where the defaults quietly do the wrong thing: a preprocessing recipe that drops timestamp and text columns, and an explainer with two traps in it. Finally, we build a small three-table shop database and predict customer activity from it directly, including the one argument that separates an honest relational model from a leaky one.

Check out the Full code here: nvidiastructureddatamodelszerotrainingtablesrelationalMarktechpost.ipynb

import os
import sys
import time
import textwrap
import traceback
import subprocess

RESULTS = {}


def banner(t...

via MarkTechPost