Improving the Efficiency of Inductive Logic Programming Through the
Use of Query Packs

Blockeel, Hendrik; Dehaspe, Luc; Demoen, Bart; Janssens, Gerda; Ramon, Jan; Vandecasteele, Henk

doi:10.1613/jair.924

Cited by 73 publications

(78 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the current approach to ILP has limitations in its scalability and computational efficiency. Recent efforts extend ideas from relational database query optimization to this setting [2][3][4][5][6]. Along the same line, we present a new formulation of ILP that systematically exploits caching to achieve greater efficiency and flexibility, and present theoretical results that characterize it.…”

Section: Introductionmentioning

confidence: 95%

“…Input: Hypothesis pair hi, ti and extension p, pred(p) Output: Extended hypothesis pair hi+1, ti+1 X-Join( hi, ti , p, pred(p) ) (1) compute projection of ti (2) build join constraints and result projection list (3) execute join and result projection (4) if result is not empty make new table ti+1 (5) let hi = (h ← r1, . .…”

Section: Algorithm 1: the Extension-join Operationmentioning

confidence: 99%

“…For instance, earlier we described an optimization where extension-join on a particular hypothesis and a set of its extensions (for example, modes that share a base table) is executed in a set-oriented fashion. This optimization is in the spirit of the query packs presented by Blockeel et al [5] Alternative Search Methods The cached table for a hypothesis pair can be used to maintain statistics that help in defining the hypothesis search-space, and in exploring that space. In this paper we present an application in which statistics from extensional tables are used to restrict the space of allowable hypotheses.…”

Section: Benefits Of the Wild Representationmentioning

confidence: 99%

See 2 more Smart Citations

A Framework for Set-Oriented Computation in Inductive Logic Programming and Its Application in Generalizing Inverse Entailment

Bravo¹,

Page²,

Ramakrishnan³

et al. 2005

Inductive Logic Programming

View full text Add to dashboard Cite

Abstract. We propose a new approach to Inductive Logic Programming that systematically exploits caching and offers a number of advantages over current systems. It avoids redundant computation, is more amenable to the use of set-oriented generation and evaluation of hypotheses, and allows relational DBMS technology to be more easily applied to ILP systems. Further, our approach opens up new avenues such as probabilistically scoring rules during search and the generation of probabilistic rules. As a first example of the benefits of our ILP framework, we propose a scheme for defining the hypothesis search space through Inverse Entailment using multiple example seeds.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Algorithm 1: the Extension-join Operationmentioning

confidence: 99%

Section: Benefits Of the Wild Representationmentioning

confidence: 99%

See 1 more Smart Citation

A Framework for Set-Oriented Computation in Inductive Logic Programming and Its Application in Generalizing Inverse Entailment

Bravo¹,

Page²,

Ramakrishnan³

et al. 2005

Inductive Logic Programming

View full text Add to dashboard Cite

show abstract

“…An implementation is publicly available in the first-order learner Tilde that is included in the ACE tool [5]; however for this paper we have used Clus, a downgrade of Tilde that works only on propositional data.…”

Section: Predictive Clustering Treesmentioning

confidence: 99%

Ranking with Predictive Clustering Trees

Todorovski

Blockeel

Džeroski

2002

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.A novel class of applications of predictive clustering trees is addressed, namely ranking. Predictive clustering trees, as implemented in Clus, allow for predicting multiple target variables. This approach makes sense especially if the target variables are not independent of each other. This is typically the case in ranking, where the (relative) performance of several approaches on the same task has to be predicted from a given description of the task. We propose to use predictive clustering trees for ranking. As compared to existing ranking approaches which are instance-based, our approach also allows for an explanation of the predicted rankings. We illustrate our approach on the task of ranking machine learning algorithms, where the (relative) performance of the learning algorithms on a dataset has to be predicted from a given dataset description.

show abstract

“…Research in improving the efficiency of ILP systems has thus focused in reducing their sequential execution time, either by reducing the number of generated hypotheses [2,3]; by efficiently testing candidate hypotheses [4,5,6]; or through parallelism [7,8]. Arguably, best results can be achieved through a reduction of the search space.…”

Section: Introductionmentioning

confidence: 99%

On Avoiding Redundancy in Inductive Logic Programming

Fonseca

Costa

Silva

et al. 2004

Inductive Logic Programming

View full text Add to dashboard Cite

Abstract. ILP systems induce first-order clausal theories performing a search through very large hypotheses spaces containing redundant hypotheses. The generation of redundant hypotheses may prevent the systems from finding good models and increases the time to induce them. In this paper we propose a classification of hypotheses redundancy and show how expert knowledge can be provided to an ILP system to avoid it. Experimental results show that the number of hypotheses generated and execution time are reduced when expert knowledge is used to avoid redundancy.

show abstract

Improving the Efficiency of Inductive Logic Programming Through the Use of Query Packs

Cited by 73 publications

References 20 publications

A Framework for Set-Oriented Computation in Inductive Logic Programming and Its Application in Generalizing Inverse Entailment

A Framework for Set-Oriented Computation in Inductive Logic Programming and Its Application in Generalizing Inverse Entailment

Ranking with Predictive Clustering Trees

On Avoiding Redundancy in Inductive Logic Programming

Contact Info

Product

Resources

About