On Avoiding Redundancy in Inductive Logic Programming

Fonseca, Nuno A.; Costa, Vítor Santos; Silva, Fernando M. A.; Camacho, Rui

doi:10.1007/978-3-540-30109-7_13

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the trivial identical duplicates, prior work [10,15] has used another type of syntactic duplicates, which we call renaming duplicates. Formally, a literal Li is a renaming duplicate if there is another literal Lj in the clause such that (i) there is a renaming of the free variables in Li such that Li and Lj are identical after renaming, and (ii) all renamed variables only occur in Li or Lj.…”

Section: Pruning Candidate Literalsmentioning

confidence: 99%

See 1 more Smart Citation

QuickFOIL

2014

View full text Add to dashboard Cite

Inductive Logic Programming (ILP) is a classic machine learning technique that learns first-order rules from relationalstructured data. However, to-date most ILP systems can only be applied to small datasets (tens of thousands of examples). A long-standing challenge in the field is to scale ILP methods to larger data sets. This paper presents a method called QuickFOIL that addresses this limitation. QuickFOIL employs a new scoring function and a novel pruning strategy that enables the algorithm to find highquality rules. QuickFOIL can also be implemented as an in-RDBMS algorithm. Such an implementation presents a host of query processing and optimization challenges that we address in this paper. Our empirical evaluation shows that QuickFOIL can scale to large datasets consisting of hundreds of millions tuples, and is often more than order of magnitude more efficient than other existing approaches.

show abstract

Section: Pruning Candidate Literalsmentioning

confidence: 99%

“…We assume partitioned hash join algorithms in developing the performance optimization techniques. The radix-hash join algorithm [15] is used in QuickFOIL. In this paper we only look at a single-threaded implementation of QuickFOIL.…”

Section: In-database Implementationmentioning

confidence: 99%

QuickFOIL

2014

View full text Add to dashboard Cite

show abstract

“…Research on reducing the execution time of ILP systems has deserved plenty attention in the last years. The proposed approaches are very diverse, ranging from new algorithms (see e.g., [5,6,7]), reducing the number of hypotheses generated (see e.g., [8,9,10]), to efficiently testing candidate hypotheses (see e.g., [11,12]), just to mention a few. A quite different line of research to reduce the execution time of ILP systems is through parallelization.…”

Section: Introductionmentioning

confidence: 99%

Strategies to Parallelize ILP Systems

Fonseca

Silva

Camacho

2005

Inductive Logic Programming

Self Cite

View full text Add to dashboard Cite

It is well known by Inductive Logic Programming (ILP) practioners that ILP systems usually take a long time to find valuable models (theories). The problem is specially critical for large datasets, preventing ILP systems to scale up to larger applications. One approach to reduce the execution time has been the parallelization of ILP systems. In this paper we overview the state-of-the-art on parallel ILP implementations and present work on the evaluation of some major parallelization strategies for ILP. Conclusions about the applicability of each strategy are presented.

show abstract

“…Fonseca et al (2004) propose a classification of redundancy in the hypothesis language and show how expert knowledge can be provided to an ILP system to in order reduce it. The technique is correct (if complete search is performed) and yields good results.…”

Section: Hypothesis Checking and Pruningmentioning

confidence: 99%

Induction as a Search Procedure

Konstantopoulos¹,

Camacho²,

Fonseca³

et al.

Artificial Intelligence for Advanced Problem Solving Techniques

Self Cite

View full text Add to dashboard Cite

This chapter introduces Inductive Logic Programming from the perspective of search algorithms in Computer Science. It first briefly considers the Version Spaces approach to induction, and then focuses on Inductive Logic Programming: from its formal definition and main techniques and strategies, to priors used to restrict the search space and optimized sequential, parallel, and stochastic algorithms. The authors hope that this presentation of the theory and applications of Inductive Logic Programming will help the reader understand the theoretical underpinnings of inductive reasoning, and also provide a helpful overview of the State-of-theArt in the domain.

show abstract

On Avoiding Redundancy in Inductive Logic Programming

Cited by 7 publications

References 9 publications

QuickFOIL

QuickFOIL

Strategies to Parallelize ILP Systems

Induction as a Search Procedure

Contact Info

Product

Resources

About