# NeuralFastLAS: Fast Logic-Based Learning from Raw Data

arXiv: https://arxiv.org/abs/2310.05145 · HTML: https://mlsanity.com/paper/2310.05145/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 8 Oct 2023.

## Builds on (most cited first, 7 of 7)

- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [A Semantic Loss Function for Deep Learning with Symbolic Knowledge](https://mlsanity.com/paper/1711.11157/) (2017)
- [NeurASP: Embracing Neural Networks into Answer Set Programming](https://mlsanity.com/paper/2307.07700/) (2023)
- [Neural Arithmetic Logic Units](https://mlsanity.com/paper/1808.00508/) (2018)
- [Neural-Symbolic Integration: A Compositional Perspective](https://mlsanity.com/paper/2010.11926/) (2020)
- [Abductive Knowledge Induction From Raw Data](https://mlsanity.com/paper/2010.03514/) (2020)

## Built on by (most cited first, 2 of 2)

- [The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning](https://mlsanity.com/paper/2402.01889/) (2024)
- [Explaining Weather Bulletins via ILP](https://mlsanity.com/paper/2607.21184/) (2026)

## Abstract (arXiv)

Symbolic rule learners generate interpretable solutions, however they require the input to be encoded symbolically. Neuro-symbolic approaches overcome this issue by mapping raw data to latent symbolic concepts using a neural network. Training the neural and symbolic components jointly is difficult, due to slow and unstable learning, hence many existing systems rely on hand-engineered rules to train the network. We introduce NeuralFastLAS, a scalable and fast end-to-end approach that trains a neural network jointly with a symbolic learner. For a given task, NeuralFastLAS computes a relevant set of rules, proved to contain an optimal symbolic solution, trains a neural network using these rules, and finally finds an optimal symbolic solution to the task while taking network predictions into account. A key novelty of our approach is learning a posterior distribution on rules while training the neural network to improve stability during training. We provide theoretical results for a sufficient condition on network training to guarantee correctness of the final solution. Experimental results demonstrate that NeuralFastLAS is able to achieve state-of-the-art accuracy in arithmetic and logical tasks, with a training time that is up to two orders of magnitude faster than other jointly trained neuro-symbolic methods.