# Abductive Knowledge Induction From Raw Data

arXiv: https://arxiv.org/abs/2010.03514 · HTML: https://mlsanity.com/paper/2010.03514/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 30 of 38)

- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts](https://mlsanity.com/paper/2402.12240/) (2024)
- [Language Models as Inductive Reasoners](https://mlsanity.com/paper/2212.10923/) (2022)
- [ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT](https://mlsanity.com/paper/2304.11107/) (2023)
- [Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions](https://mlsanity.com/paper/2208.11561/) (2022)
- [A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts](https://mlsanity.com/paper/2406.10368/) (2024)
- [FF-NSL: Feed-Forward Neural-Symbolic Learner](https://mlsanity.com/paper/2106.13103/) (2021)
- [Learning MDL logic programs from noisy data](https://mlsanity.com/paper/2308.09393/) (2023)
- [On Learning Latent Models with Multi-Instance Weak Supervision](https://mlsanity.com/paper/2306.13796/) (2023)
- [Neuro-Symbolic Learning of Answer Set Programs from Raw Data](https://mlsanity.com/paper/2205.12735/) (2022)
- [Learning Differentiable Logic Programs for Abstract Visual Reasoning](https://mlsanity.com/paper/2307.00928/) (2023)
- [The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning](https://mlsanity.com/paper/2402.01889/) (2024)
- [Learning logic programs by combining programs](https://mlsanity.com/paper/2206.01614/) (2022)
- [Neuro-symbolic Rule Learning in Real-world Classification Tasks](https://mlsanity.com/paper/2303.16674/) (2023)
- [Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees](https://mlsanity.com/paper/2308.10487/) (2023)
- [Generalisation Through Negation and Predicate Invention](https://mlsanity.com/paper/2301.07629/) (2023)
- [Learning by Applying: A General Framework for Mathematical Reasoning via Enhancing Explicit Knowledge Learning](https://mlsanity.com/paper/2302.05717/) (2023)
- [Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation](https://mlsanity.com/paper/2408.11367/) (2024)
- [Abductive Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models](https://mlsanity.com/paper/2509.21874/) (2025)
- [NeuralFastLAS: Fast Logic-Based Learning from Raw Data](https://mlsanity.com/paper/2310.05145/) (2023)
- [Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings](https://mlsanity.com/paper/2310.17451/) (2023)
- [Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models](https://mlsanity.com/paper/2405.06724/) (2024)
- [Nonground Abductive Logic Programming with Probabilistic Integrity Constraints](https://mlsanity.com/paper/2108.03033/) (2021)
- [A Hybrid System for Systematic Generalization in Simple Arithmetic Problems](https://mlsanity.com/paper/2306.17249/) (2023)
- [Learning logic programs by discovering higher-order abstractions](https://mlsanity.com/paper/2308.08334/) (2023)
- [Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques](https://mlsanity.com/paper/2308.15899/) (2023)
- [Boolean Matrix Logic Programming on the GPU](https://mlsanity.com/paper/2408.10369/) (2024)
- [Efficiently Learning Probabilistic Logical Models by Cheaply Ranking Mined Rules](https://mlsanity.com/paper/2409.16238/) (2024)
- [Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models](https://mlsanity.com/paper/2605.18202/) (2026)
- [Automated Biodesign Engineering by Abductive Meta-Interpretive Learning](https://mlsanity.com/paper/2105.07758/) (2021)

## Abstract (arXiv)

For many reasoning-heavy tasks involving raw inputs, it is challenging to design an appropriate end-to-end learning pipeline. Neuro-Symbolic Learning, divide the process into sub-symbolic perception and symbolic reasoning, trying to utilise data-driven machine learning and knowledge-driven reasoning simultaneously. However, they suffer from the exponential computational complexity within the interface between these two components, where the sub-symbolic learning model lacks direct supervision, and the symbolic model lacks accurate input facts. Hence, most of them assume the existence of a strong symbolic knowledge base and only learn the perception model while avoiding a crucial problem: where does the knowledge come from? In this paper, we present Abductive Meta-Interpretive Learning (MetaAbd) that unites abduction and induction to learn neural networks and induce logic theories jointly from raw data. Experimental results demonstrate that MetaAbd not only outperforms the compared systems in predictive accuracy and data efficiency but also induces logic programs that can be re-used as background knowledge in subsequent learning tasks. To the best of our knowledge, MetaAbd is the first system that can jointly learn neural networks from scratch and induce recursive first-order logic theories with predicate invention.