MC-TopLog: Complete Multi-clause Learning Guided by a Top Theory

Muggleton, Stephen; Lin, Dianhuan; Tamaddoni‐Nezhad, Alireza

doi:10.1007/978-3-642-31951-8_22

Cited by 10 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Progol5 [11] and MC-TopLog [13] were used to represent SCL and MCL, respectively. In the tomato application, leave-one-out cross validation was used to compute the predictive accuracies due to the availability of a limited set of abundance data (22 metabolites).…”

Section: Methodsmentioning

confidence: 99%

“…Multi-clause learning (MCL) systems like CF-Induction [6], XHAIL [15], TAL [4] and MC-TopLog [13] were designed to overcome Progol's entailment-incompleteness. However, as discussed above, it is not clear whether completeness is important in real-world applications.…”

Section: Complete and Incomplete Ilp Systemsmentioning

confidence: 99%

“…This entailment-incompleteness restricts its derivable hypothesis to be a single clause, and that clause is used only once in the refutation proof of the example e. Thus we define SCL and MCL as follows. More details about MCL and SCL can be found in [13]. Definition 1.…”

Section: Multi-clause Learning Vs Single-clause Learningmentioning

confidence: 99%

See 2 more Smart Citations

Does Multi-Clause Learning Help in Real-World Applications?

Lin

Chen

Watanabe

et al. 2012

Inductive Logic Programming

Self Cite

View full text Add to dashboard Cite

Abstract. The ILP system Progol is incomplete in not being able to generalise a single example to multiple clauses. However, according to the Blumer bound, incomplete learners such as Progol, can have higher predictive accuracy using less search than more complete learners. This issue is particularly relevant in real-world problems, in which it is unclear whether the unknown target theory is within the hypothesis space of the incomplete learner. This paper uses two real-world applications in systems biology to study whether there exist datasets where a complete multi-clause learning (MCL) method can significantly outperform a single-clause learning (SCL) method. The experimental results show that in both applications there do exist datasets, in which hypotheses derived by MCL have significantly higher predictive accuracies. On the other hand, for most of the datasets in the two applications, there are good approximations of the target within the hypothesis space of SCL, so that MCL does not outperform SCL.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Complete and Incomplete Ilp Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Does Multi-Clause Learning Help in Real-World Applications?

Lin

Chen

Watanabe

et al. 2012

Inductive Logic Programming

Self Cite

View full text Add to dashboard Cite

show abstract

“…A Top theory is used by some ILP systems as e.g. in TopLog (Muggleton et al 2008) and MC-TopLog (Muggleton et al 2012) and in the non-monotonic setting in the ASPlearning systems TAL (Corapi et al 2010), ASPAL (Corapi et al 2011) and RASPAL (Athakravi et al 2014). A Top theory is an instance of strong inductive bias used to direct the search of H which remains expensive and which Top program construction avoids altogether.…”

Section: Related Workmentioning

confidence: 99%

Top program construction and reduction for polynomial time Meta-Interpretive learning

Patsantzis

Muggleton

2021

Mach Learn

View full text Add to dashboard Cite

Meta-Interpretive Learners, like most ILP systems, learn by searching for a correct hypothesis in the hypothesis space, the powerset of all constructible clauses. We show how this exponentially-growing search can be replaced by the construction of a Top program: the set of clauses in all correct hypotheses that is itself a correct hypothesis. We give an algorithm for Top program construction and show that it constructs a correct Top program in polynomial time and from a finite number of examples. We implement our algorithm in Prolog as the basis of a new MIL system, Louise, that constructs a Top program and then reduces it by removing redundant clauses. We compare Louise to the state-of-the-art search-based MIL system Metagol in experiments on grid world navigation, graph connectedness and grammar learning datasets and find that Louise improves on Metagol’s predictive accuracy when the hypothesis space and the target theory are both large, or when the hypothesis space does not include a correct hypothesis because of “classification noise” in the form of mislabelled examples. When the hypothesis space or the target theory are small, Louise and Metagol perform equally well.

show abstract

“…Alternatively one could explore the use of machine learning techniques such as [73] to construct performance trees automatically using Inductive Logic Programming to synthesise logical formulas representing a practitioners assessment of a training set of buildings. Recent research into learning multi-clause logical formulas will map simply to a performance tree concept.…”

Section: Performance Treesmentioning

confidence: 99%