Logical and relational learning

By Luc De Raedt. Cognitive Technologies, 2008

491 citations recorded by the source corpus.

Subfields: Developmental and Educational Psychology

View Paper: https://www.semanticscholar.org/paper/4e11ebdc3e4f30d774458fab9e4b45ff0d0aa971

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Developmental and Educational Psychology

Citations in the corpus

Multi-Relational Learning with Gaussian Processes (2009, background): “There have been many research efforts in multi-relational learning [Getoor and Taskar, 2007; De Raedt, 2008].”
The Graph Neural Network Model (2009, unknown): “Traditionally, data relationships exploitation has been the subject of many studies in the community of inductive logic programming and, recently, this research theme has been evolving in different directions [8], also because of the applications of”
A Review of Relational Machine Learning for Knowledge Graphs (2015, unknown): “For further information on SRL, see [1]–[3].”
Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings (2020, background): “To remedy (2) one could impute missing relations (Koller et al., 2007; Džeroski, 2009; De Raedt, 2008; Nickel et al., 2016) but that would only make the KG denser, which would further exacerbate issue (1) (Dalvi & Suciu, 2007; Krompaß et al., 2014).”
Fast relational learning using bottom clause propositionalization with artificial neural networks (2013, unknown): “Relational learning can be described as the task of learning a first-order logic theory from examples (Džeroski and Lavrač, 2001; De Raedt, 2008).”
Statistical Relational Learning of Object Affordances for Robotic Manipulation (2011, background): “This can be done by the use of SRL in a multiple object scenario, which allows for the generalization over objects and actions by allowing the use of already learned one and two object models together with known logical rules to be used for inference.”
Cluster-grouping: from subgroup discovery to clustering (2004, methodology): “We have already employed the basic principles of CG in a different domain, tree-structured data [7] and the cluster-grouping paradigm could also be extended into the area of logical and relational learning [13].”
Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures (2018, background): “The idea is that useful latent relational concepts emerge from the gradient descent based weight learning process, rather than by explicit enumeration, in contrast to propositional approaches and ILP (De Raedt, 2008).”
Playgol: learning programs through play (2019, methodology): “However, to clearly explain our theoretical and empirical re-sults, we formalise the problem in an ILP setting [ Raedt, 2008 ] using meta-interpretive learning (MIL) [ Muggleton et al. , 2015; Cropper and Muggleton, 2016a ] .”
Neuro-Symbolic = Neural + Logical + Probabilistic (2019, methodology): “Based on our experience in upgrading machine learning systems towards the use of (probabilistic) logical and relational representations [De Raedt, 2008; Muggleton et al., 2012], we argue that a first desirable property of frameworks that integrate two other frameworks A and B, is to have the origina”
Solving Relational and First-Order Logical Markov Decision Processes: A Survey (2012, methodology): “However, the last decade logical and probabilistic approaches are merging in the field of statistical relational learning (SRL) (De Raedt, 2008).”