Logical Rule Induction and Theory Learning Using Neural Theorem Proving
By Andres Campero, Aldo Pareja, Tim Klinger, Josh Tenenbaum, Sebastian Riedel. 2018
45 citations recorded by the source corpus.
A hallmark of human cognition is the ability to continually acquire and distill observations of the world into meaningful, predictive theories. In this paper we present a new mechanism for logical theory acquisition which takes a set of observed facts and learns to extract from them a set of logical rules and a small set of core facts which together entail the observations. Our approach is neuro-symbolic in the sense that the rule pred- icates and core facts are given dense vector representations. The rules are applied to the core facts using a soft unification procedure to infer additional facts. After k steps of forward inference, the consequences are compared to the initial observations and the rules and core facts are then encouraged towards representations that more faithfully generate the observations through inference. Our approach is based on a novel neural forward-chaining differentiable rule induction network. The rules are interpretable and learned compositionally from their predicates, which may be invented. We demonstrate the efficacy of our approach on a variety of ILP rule induction and domain theory learning datasets.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Michael Spranger
- Luciano Serafini
- Samy Badreddine
- A.S. d'Avila Garcez
- Denny Zhou
- Jiayuan Mao
- Tian Lin
- Chong Wang
In Natural Language Processing
- Jiayuan Mao
- Luciano Serafini
- Michael Spranger
- Samy Badreddine
- Tian Lin
- Chong Wang
- Masataro Asai
- A.S. d'Avila Garcez
Citations in the corpus
- Neural Logic Machines (2019, background): “The key of Rocktäschel & Riedel (2017) and Campero et al. (2018) is to learn subsymbolic embeddings of entities and predicates for efficient KB completion, which differs from our focus.”
- Unsupervised Grounding of Plannable First-Order Logic Representation from Images (2019, background): “(Rocktäschel and Riedel 2017; Sourek et al. 2018; Campero et al. 2018; Manhaeve et al. 2018) learn to reason about logical relations.”
- Logic Tensor Networks (2020, methodology): “Furthermore, in [52, 10] neural networks are used to learn reasoning strategies and logical rule induction.”