# An Investigation into Mini-Batch Rule Learning

arXiv: https://arxiv.org/abs/2106.10202 · HTML: https://mlsanity.com/paper/2106.10202/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 8 references that are in the map.
- First posted on arXiv 18 Jun 2021.

## Builds on (most cited first, 2 of 2)

- [Learning Gradient Boosted Multi-label Classification Rules](https://mlsanity.com/paper/2006.13346/) (2020)
- [Differentiable Learning of Logical Rules for Knowledge Base Reasoning](https://mlsanity.com/paper/1702.08367/) (2017)

## Built on by (most cited first, 1 of 1)

- [Differentiable Rule Induction with Learned Relational Features](https://mlsanity.com/paper/2201.06515/) (2022)

## Abstract (arXiv)

We investigate whether it is possible to learn rule sets efficiently in a network structure with a single hidden layer using iterative refinements over mini-batches of examples. A first rudimentary version shows an acceptable performance on all but one dataset, even though it does not yet reach the performance levels of Ripper.