kLog: a language for logical and relational learning with kernels
From MaRDI portal
Publication:464624
DOI10.1016/J.ARTINT.2014.08.003zbMATH Open1405.68288arXiv1205.3981OpenAlexW2114190652WikidataQ57931578 ScholiaQ57931578MaRDI QIDQ464624FDOQ464624
Authors: Paolo Frasconi, Fabrizio Costa, Luc De Raedt, Kurt De Grave 
Publication date: 27 October 2014
Published in: Artificial Intelligence (Search for Journal in Brave)
Abstract: We introduce kLog, a novel approach to statistical relational learning. Unlike standard approaches, kLog does not represent a probability distribution directly. It is rather a language to perform kernel-based learning on expressive logical and relational representations. kLog allows users to specify learning problems declaratively. It builds on simple but powerful concepts: learning from interpretations, entity/relationship data modeling, logic programming, and deductive databases. Access by the kernel to the rich representation is mediated by a technique we call graphicalization: the relational representation is first transformed into a graph --- in particular, a grounded entity/relationship diagram. Subsequently, a choice of graph kernel defines the feature space. kLog supports mixed numerical and symbolic data, as well as background knowledge in the form of Prolog or Datalog programs as in inductive logic programming systems. The kLog framework can be applied to tackle the same range of tasks that has made statistical relational learning so popular, including classification, regression, multitask learning, and collective classification. We also report about empirical comparisons, showing that kLog can be either more accurate, or much faster at the same level of accuracy, than Tilde and Alchemy. kLog is GPLv3 licensed and is available at http://klog.dinfo.unifi.it along with tutorials.
Full work available at URL: https://arxiv.org/abs/1205.3981
Recommendations
kernel methodsstatistical relational learningPrologdeductive databaseslogical and relational learning
Learning and adaptive systems in artificial intelligence (68T05) Logic programming (68N17) Database theory (68P15)
Cites Work
- The YAP prolog system
- Probabilistic graphical models.
- Learning to construct knowledge bases from the World Wide Web
- Graph kernels
- Weisfeiler-Lehman graph kernels
- Solving the multiple instance problem with axis-parallel rectangles.
- Probabilistic inductive logic programming. Theory and applications
- Markov logic networks
- Title not available (Why is that?)
- Large margin methods for structured and interdependent output variables
- Convex multi-task feature learning
- Hash kernels for structured data
- Title not available (Why is that?)
- Isomorphism of graphs of bounded valence can be tested in polynomial time
- On the implementation of the probabilistic logic programming language ProbLog
- Title not available (Why is that?)
- Logical and Relational Learning
- Large-scale machine learning with stochastic gradient descent
- Structured machine learning: the next ten years
- A parametric filtering algorithm for the graph isomorphism problem
- Top-down induction of first-order logical decision trees
- Learning multiple tasks with kernel methods
- Kernels for Structured Data
- Feature Discovery with Type Extension Trees
- Fast learning of relational kernels
- Relational retrieval using a combination of path-constrained random walks
- Transforming graph data for statistical relational learning
- Improving Prolog programs: Refactoring for Prolog
Cited In (19)
- DKL: an efficient algorithm for learning deterministic Kripke structures
- Probabilistic learning on graphs via contextual architectures
- An integrated development environment for probabilistic relational reasoning
- Structure learning for relational logistic regression: an ensemble approach
- Inclusion of domain-knowledge into GNNs using mode-directed inverse entailment
- Title not available (Why is that?)
- Kernels on Prolog proof trees: statistical learning in the ILP setting
- kLog
- Learning with Kernels and Logical Representations
- Modalities, relations, and learning. A relational interpretation of learning approaches
- A gentle introduction to deep learning for graphs
- Fast learning of relational kernels
- From statistical relational to neurosymbolic artificial intelligence: a survey
- Learning with Kernels in Description Logics
- An expressive dissimilarity measure for relational clustering using neighbourhood trees
- kProbLog: an algebraic Prolog for machine learning
- Soft quantification in statistical relational learning
- Statistical relational learning with soft quantifiers
- kProbLog: an algebraic Prolog for kernel programming
Uses Software
This page was built for publication: kLog: a language for logical and relational learning with kernels
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q464624)
