NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required
NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required
NVIDIA Kumo Relational is a pre-trained relational foundation model that makes predictions directly on enterprise databases. Given a predictive query, it gathers up to 10,000 historical examples as context and predicts outcomes such as churn, demand, or fraud in a single forward pass. It needs no task-specific training, no feature engineering, and no flattening of tables.
Selection record
AdmittedSum of both 150 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：NVIDIA预训练关系基础模型，免训练预测
- Why it was chosen
- Covers the pre-trained relational model's results beating supervised learning on 41 benchmarks, and how it is used by querying databases directly with no training.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co