Inductive constraint logic

Raedt, Luc De; Laer, Wim Van

doi:10.1007/3-540-60454-5_30

Cited by 86 publications

(57 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As Perlich and Provost (2003) show, the choice of aggregation operator can have a much stronger impact on the resulting model's generalisation performance than the choice of the model induction method. Therefore, we believe it is worth investigating the use of complex aggregates in, e.g., systems as ICL (De Raedt & Van Laer, 1995) or ALEPH (Srinivasan, 2003). In the context of such rule learners however, attention should be paid to the refinement of aggregates which will not be automatically valid anymore, indeed, a local bottom-up search could interleave the top-down search strategy.…”

Section: Discussionmentioning

confidence: 99%

“…RIBL (Emde & Wettschereck, 1995) is a relational instance based learning algorithm. The ICL system (De Raedt & Van Laer, 1995) uses exactly the same representation as TILDE, but induces rule sets instead of trees. We only used the red-relation for FORF, since it should be able to construct the prop relation by itself, but we compared it to the other systems both using only red and using red and prop.…”

Section: Diterpenesmentioning

confidence: 99%

See 1 more Smart Citation

First order random forests: Learning relational classifiers with complex aggregates

et al. 2006

View full text Add to dashboard Cite

In relational learning, predictions for an individual are based not only on its own properties but also on the properties of a set of related individuals. Relational classifiers differ with respect to how they handle these sets: some use properties of the set as a whole (using aggregation), some refer to properties of specific individuals of the set, however, most classifiers do not combine both. This imposes an undesirable bias on these learners. This article describes a learning approach that avoids this bias, using first order random forests. Essentially, an ensemble of decision trees is constructed in which tests are first order logic queries. These queries may contain aggregate functions, the argument of which may again be a first order logic query. The introduction of aggregate functions in first order logic, as well as upgrading the forest's uniform feature sampling procedure to the space of first order logic, generates a number of complications. We address these and propose a solution for them. The resulting first order random forest induction algorithm has been implemented and integrated in the ACE-ilProlog system, and experimentally evaluated on a variety of datasets. The results indicate that first order random forests with complex aggregates are an efficient and effective approach towards learning relational classifiers that involve aggregates over complex selections.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Diterpenesmentioning

confidence: 99%

First order random forests: Learning relational classifiers with complex aggregates

et al. 2006

View full text Add to dashboard Cite

show abstract

“…Doubling the g parameter more or less doubles the timings. For larger queries, namely for (10,10,4) and (5,5,6), control flow compilation becomes a factor 15 faster than compile & run. If the query is executed a number of times, meta-call is outperformed by control flow compilation (e.g.…”

Section: Discussionmentioning

confidence: 99%

Fast Query Evaluation with (Lazy) Control Flow Compilation

2004

View full text Add to dashboard Cite

Abstract. Learning algorithms such as decision tree learners dynamically generate a huge amount of large queries. Because these queries are executed often, the trade-off between meta-calling and compiling & running them has been in favor of the latter, as compiled code is faster. This paper presents a technique named control flow compilation, which improves the compilation time of the queries by an order of magnitude without reducing the performance of executing the queries. We exploit the technique further by using it in a just-in-time manner. This improves performance in two ways: it opens the way to incremental compilation of the generated queries, and also gives potentially large gains by never compiling dynamically unreachable code. Both the implementation of (lazy) control flow compilation and its experimental evaluation in a real world application are reported on.

show abstract

“…Secondly, how it can perform discriminating induction. A step in this direction was already taken by (De Raedt & Van Laer, 1995). Thirdly, it would be interesting to see how the engine can be coupled to a relational database system and evaluate its performance on huge data bases.…”

Section: Discussionmentioning

confidence: 99%

“…interpretations that are a model for a theory true versus interpretations that are not. This alternative setting has been adopted in the ICL system of (De Raedt & Van Laer, 1995). The ICL setting, discriminant induction from interpretations, provides a clue as how problems and solutions along the different dimensions relate to each other.…”

Section: Normal Inductive Logic Programmingmentioning

confidence: 99%

Untitled

1997

View full text Add to dashboard Cite

Abstract. The clausal discovery engine Claudien is presented. Claudien is an inductive logic programming engine that fits in the descriptive data mining paradigm. Claudien addresses characteristic induction from interpretations, a task which is related to existing formalisations of induction in logic. In characteristic induction from interpretations, the regularities are represented by clausal theories, and the data using Herbrand interpretations. Because Claudien uses clausal logic to represent hypotheses, the regularities induced typically involve multiple relations or predicates. Claudien also employs a novel declarative bias mechanism to define the set of clauses that may appear in a hypothesis.

show abstract

Inductive constraint logic

Cited by 86 publications

References 11 publications

First order random forests: Learning relational classifiers with complex aggregates

First order random forests: Learning relational classifiers with complex aggregates

Fast Query Evaluation with (Lazy) Control Flow Compilation

Untitled

Contact Info

Product

Resources

About