# Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation

arXiv: https://arxiv.org/abs/2408.11367 · HTML: https://mlsanity.com/paper/2408.11367/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 21 Aug 2024.

## Builds on (most cited first, 16 of 16)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning](https://mlsanity.com/paper/1905.06088/) (2019)
- [Inductive logic programming at 30: a new introduction](https://mlsanity.com/paper/2008.07912/) (2020)
- [Learning programs by learning from failures](https://mlsanity.com/paper/2005.02259/) (2020)
- [From Statistical Relational to Neuro-Symbolic Artificial Intelligence](https://mlsanity.com/paper/2003.08316/) (2020)
- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [Turning 30: New Ideas in Inductive Logic Programming](https://mlsanity.com/paper/2002.11002/) (2020)
- [Abductive Knowledge Induction From Raw Data](https://mlsanity.com/paper/2010.03514/) (2020)
- [Learning MDL logic programs from noisy data](https://mlsanity.com/paper/2308.09393/) (2023)
- [Structure Learning of Probabilistic Logic Programs by Searching the Clause Space](https://mlsanity.com/paper/1309.2080/) (2013)
- [V-LoL: A Diagnostic Dataset for Visual Logical Learning](https://mlsanity.com/paper/2306.07743/) (2023)

## Built on by (most cited first, 5 of 5)

- [GLIDR: Graph-Like Inductive Logic Programming with Differentiable Reasoning](https://mlsanity.com/paper/2508.06716/) (2025)
- [Efficient rule induction by ignoring pointless rules](https://mlsanity.com/paper/2502.01232/) (2025)
- [Honey, I shrunk the hypothesis space (through logical preprocessing)](https://mlsanity.com/paper/2506.06739/) (2025)
- [Symmetry breaking for inductive logic programming](https://mlsanity.com/paper/2508.06263/) (2025)
- [Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach](https://mlsanity.com/paper/2604.06838/) (2026)

## Abstract (arXiv)

Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and probabilistic background knowledge by extending ILP with a combination of neurosymbolic inference, a continuous criterion for hypothesis selection (BCE) and a relaxation of the hypothesis constrainer (NoisyCombo). For relational patterns in noisy images, Propper can learn programs from as few as 8 examples. It outperforms binary ILP and statistical models such as a Graph Neural Network.