2016
DOI: 10.1007/978-3-319-40566-7_4
|View full text |Cite
|
Sign up to set email alerts
|

Meta-Interpretive Learning of Data Transformation Programs

Abstract: Abstract. Data transformation involves the manual construction of large numbers of special-purpose programs. Although typically small, such programs can be complex, involving problem decomposition, recursion, and recognition of context. Building such programs is common in commercial and academic data analytic projects and can be labour intensive and expensive, making it a suitable candidate for machine learning. In this paper, we use the meta-interpretive learning framework (MIL) to learn recursive data transf… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
22
0

Year Published

2017
2017
2020
2020

Publication Types

Select...
5
3

Relationship

2
6

Authors

Journals

citations
Cited by 28 publications
(22 citation statements)
references
References 12 publications
0
22
0
Order By: Relevance
“…This value gives us a sufficiently large set of metarules to reduce but not too large that the reduction problem is intractable. When running the E-and D-reduction algorithms (both k-bounded), we use a resolution-depth bound of 7, which is the largest value for which the algorithms terminate in reasonable time 15 . After applying the reduction algorithms to the finite fragments, we then try to solve G2 by extrapolating the results to the infinite case (i.e.…”
Section: Reduction Of Metarulesmentioning
confidence: 99%
“…This value gives us a sufficiently large set of metarules to reduce but not too large that the reduction problem is intractable. When running the E-and D-reduction algorithms (both k-bounded), we use a resolution-depth bound of 7, which is the largest value for which the algorithms terminate in reasonable time 15 . After applying the reduction algorithms to the finite fragments, we then try to solve G2 by extrapolating the results to the infinite case (i.e.…”
Section: Reduction Of Metarulesmentioning
confidence: 99%
“…This is in contrast to most recent publications on inductive synthesis, which seem to focus on only one level of recursion [13,4,7]. Moreover, CombInduce generates mentioned fold-2 programs in under a second with mostly less than a handful examples, compared to some other methods that require tens of examples and are distinctly slower.…”
Section: Introductionmentioning
confidence: 66%
“…It employs a reversible meta-interpreter, which is a technique developed through the 1990s [14,9], and recently revisited by multiple works [13,4]. The CombInduce approach is distinguished by its capability to synthesize two nested recursions at once, classified as a fold-2 program.…”
Section: Introductionmentioning
confidence: 99%
“…11. For example, TopLog (Muggleton, Santos, & Tamaddoni-Nezhad, 2008), TAL (Corapi, Russo, & Lupu, 2010), Metagol (Muggleton, Lin, Pahlavi, & Tamaddoni-Nezhad, 2014;Muggleton, Lin, & Tamaddoni-Nezhad, 2015;Cropper, Tamaddoni-Nezhad, & Muggleton, 2015). 12.…”
Section: Ilp As a Satisfiability Problemmentioning
confidence: 99%