Inductive Logic Programming

By Gerson Zaverucha, Vítor Santos Costa, Aline Paes. 2014

719 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Knowledge Graphs & Representation

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

In Computational Theory and Mathematics

In Knowledge Graphs & Representation

Citations in the corpus

Neural Logic Machines (2019, background): “Inductive logic programming (ILP) (Muggleton, 1991; 1996; Fried-man et al., 1999) is a paradigm for learning logic rules derived from a limited set of rule templates from examples.”
Integrating Learning and Reasoning with Deep Logic Models (2019, background): “DLMs also open up the possibility to iteratively integrate rule induction mechanisms like the ones proposed by the Inductive Logic Programming community [17, 25].”
Towards Deep Symbolic Reinforcement Learning (2016, methodology): “First, the incorporation of inductive logic programming [34] would enable a more powerful form of gener-alisation to be applied to the Q function [35].”
Learning Optimized Or's of And's (2015, methodology): “The closest work to ours are that of Hauser et al. (2010) in the marketing literature, and Wang et al. (2015) on Bayesian modeling of DNF formulae.”
End-to-end Differentiable Proving (2017, methodology): “While these ILP systems operate on symbols and search over the discrete space of logical rules, NTPs work with subsymbolic representations and induce rules using gradient descent.”
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (2019, methodology): “Thus, we follow Rocktäschel and Riedel (2017) and use rule templates to perform Inductive Logic Programming (ILP) (Muggleton, 1991), which allows NLP ROLOG to learn rules from training data.”
Holographic Embeddings of Knowledge Graphs (2015, background): “Hence, learning from and with relational knowledge representations has long been considered an important task in artiﬁcial intelligence (see e.g., Getoor and Taskar (2007); Muggleton (1991); Gentner (1983); Kemp et al. (2006); Xu et al. (2006); Richardson and Domingos (2006)).”
Neurosymbolic AI: the 3rd wave (2020, neutral): “Pearl’s hierarchy may unintentionally give the impression that machine learning is confined to this bottom layer, since no reference is made in [58] to the body of work on symbolic machine learning which is unequivocally not confined to association rules [55, 70].”
Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME (2018, background): “Inductive Logic Programming (ILP) (Muggleton 1991) is a subfield of machine learning that learns models in the form of logic programming rules (Horn Clauses) that are comprehensible to humans.”
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning (2017, background): “Symbolic representations have also been integrated with machine learning especially in statistical relational learning (Muggleton et al., 1992; Getoor & Taskar, 2007; Kok & Domingos, 2007; Lao et al., 2011), but due to poor generalization performance, these approaches have largely been superceded…”
Tunneling Neural Perception and Logic Reasoning through Abductive Learning (2018, background): “Owing to its comprehensibility and the power of performing ﬁrst-order logical inferences, logic programming is widely used in symbolic AI systems such as expert systems [5], inductive logic programming [31], abductive logic programming [21], and so on.”
Inventing Relational State and Action Abstractions for Effective and Efficient Bilevel Planning (2022, methodology): “Inspired by prior work [16, 17, 29], we approach the predicate invention problem from a program synthesis perspective [30, 31, 32, 33].”
Autonomous agents modelling other agents: A comprehensive survey and open problems (2017, methodology): “Inductive logic programming [200] is used to automatically select a feature representation from these sequences.”
On a Convex Logic Fragment for Learning and Reasoning (2018, background): “For instance the Bayesian ILP setting [15] assumes a prior probability distribution deﬁned over the hypothesis space.”
Artificial General Intelligence: Concept, State of the Art, and Future Prospects (2009, background): “Perhaps the most impressive successes of symbolic methods on learning problems have occurred in the areas of Genetic Programming (GP) (Koza, 1992), Inductive Logic Programming (Muggleton, 1991), and probabilistic learning methods such as Markov Logic Networks (MLN) (Richardson and Domingos, 2006).”
Synthesizing data structure transformations from input-output examples (2015, positive): “Specifically, we build on the tradition of inductive programming [15, 18, 20], where the goal is to synthesize functional or logic programs from examples.”
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis (2018, methodology): “As a result, the use of Machine Learning methods have been proposed, based on Bayesian probabilistic models (Liang et al., 2010) or Inductive Logic programming (Muggleton, 1991; Muggleton et al., 2014) to automatically generate programs based on examples.”
Recursive Feature Generation for Knowledge-based Learning (2018, methodology): “ILP methods start from single relation formulae and add additional relational constraints using the knowledge base, until formulae that separate the training set into positive and negative examples are found.”
Learning Multi-Agent Communication through Structured Attentive Reasoning (2020, background): “The core idea of relational reinforcement learning (RRL) combines inductive logic programming [21, 22] and reinforcement learning to perform reasoning steps iterated over entities in the environment.”