MICROSOFT SEMANTIC ENGINE Unified Search, Discovery and Insight.
Semantic Meta-Mining of Knowledge Discovery Processes
-
Upload
agnieszka-lawrynowicz -
Category
Data & Analytics
-
view
333 -
download
0
Transcript of Semantic Meta-Mining of Knowledge Discovery Processes
Semantic Meta-Mining of Knowledge DiscoveryProcesses
Agnieszka Lawrynowiczcollaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario,Claudia d’Amato, Raul Palma and others - see acknowledgements
Poznan University of Technology
June 11, 2015ADAA Seminar
Silesian University of Technology
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 1
/ 50
Outline
Semantic data mining
Pattern discovery with Fr-ONT-Qu
Meta-mining of KD processes▸ e-LICO Intelligent Discovery Assistant▸ Data Mining OPtimization Ontology▸ Semantic meta-mining
Summary and future work
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 2
/ 50
Introduction: data mining
Input: a data table, text documents, ...Output: a model, a pattern set
DATA$MINING$
Model,$pa0erns$data$
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 3
/ 50
Introduction: using background knowledge in data mining
Using background knowledge in data mining has been extensivelyresearched
hierarchy/taxonomy of attributes (Michalski et al., 1986, Srikant,Agrawal, 1995)
Inductive Logic Programming (Muggleton, 1991, Lavrac andDzeroski, 1994)
relational learning (Quinlan, 1993, de Raedt, 2008)
semantic data mining tutorial @ ECML/PKDD’2011 (Lavrac,Vavpetic, Lawrynowicz, Potoniec, Hilario, Kalousis)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 4
/ 50
Introduction: relational data mining
Input: a relational database, a graph, a set of logical facts, ...Output: a model, a pattern set
RELATIONAL)DATA)MINING)
Model,)pa4erns)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 5
/ 50
Semantic data mining
Input:
a data table, text documents, Web pages, a relational database, agraph, a set of logical facts, ...
one or more ontologies
Output: a model, a pattern set
SEMANTIC)DATA)MINING)
Model,)pa3erns)
Data)
Ontologies)
annota;ons)mappings)vocabulary)reBuse)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 6
/ 50
Fr-ONT-Qu
algorithm for mining patterns in RDF(s) data
patterns expressed as SPARQL queries
consists of: a refinement operator and a strategy to select bestpatterns for further refinement
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 7
/ 50
Overview
Input of the algorithm:
a declarative bias (B) to limit a search space (i.e. classes andproperties to use) and maximal number of iterations
2 thresholds: for keeping good enough patterns and for refining bestpatterns
several quality measures to select for thresholds (e.g. support on KB)
beam search size
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 8
/ 50
Example
B: classes: PassengerTrain, CargoTrain, property: hasEngine
1 Refine every pattern from the previous iteration by adding a singlerestriction for a variable already existing in the pattern. E.g. forpatern {?x a :Train.}, its refinements are:
▸ {?x a :Train . ?x a :CargoTrain.}▸ {?x a :Train . ?x a :PassengerTrain}▸ {?x a :Train . ?x :hasEngine ?y}
2 Evaluate patterns (with some quality measure as support on a dataset) and select only the best ones
3 Repeat steps 1-2 as long as there are patterns for refinement andmaximal number of iterations is not exceeded
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 9
/ 50
Trie data structure
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 10
/ 50
Pattern based classification 1/2
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 11
/ 50
Pattern based classification 2/2
We learn features that are optimized with regard to the (classification) task
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 12
/ 50
Propositionalisation 1/2
Pa#erns 1) ?x a :Train . ?x :hasCar ?y 2) ?x a :Train . ?x :hasCar ?y . ?y :hasShape :rectangle 3) ?x a :Train . ?x :hasCar ?y . ?y :wheels :three 4) …
Dataset (Michalski’s train problem, 1977)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 13
/ 50
Propositionalisation 2/2
In this way, learned features may be consumed by any out-of-the-shelf’attribute-value’ classification algorithm
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 14
/ 50
What is RapidMiner? 1/2
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 15
/ 50
What is RapidMiner? 2/2
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 16
/ 50
What is RapidMiner? 2/2
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 17
/ 50
RMonto - plugin to RapidMiner
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 18
/ 50
Comparative experiments on classification of semantic data1/2
we considered published work with available results and datasets(including ESWC 2008 best paper, ESWC 2012 best paper)
various types of methods: kernel methods, statistical relationalclassifier, concept learning algorithms
we strictly followed the tasks, protocols and experimental setups ofthe methods
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 19
/ 50
Comparative experiments on classification of semantic data2/2
For classification task Fr-ONT-Qu outperformed state-of-art approaches toclassification of Semantic Web data(see: ”Pattern based feature construction in semantic data mining” by A.Lawrynowicz, J. Potoniec, IJSWIS 10(1), 2014):
kernel methods Bloehdorn et al. (2007), Loesch et al. (ESWC 2012best paper) on SWRC AIFB dataset,
statistical relational classifier SPARQL-ML by Kiefer et al (ESWC2008 best paper) on SWRC AIFB dataset and OWLS-TC v2.1dataset,
concept learning algorithms DL-FOIL by Fanizzi et al (2008),DL-Learner cutting-edge CELOE variant by Lehmann (2009) on allmeasures on datasets BioPax, NTN, Financial
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 20
/ 50
Overview of meta-learning
Meta-learning: learning to learn
application of machine learning techniques to meta-data about pastmachine learning experiments;
the goal: to modify some aspect of the learning process to improvethe performance of the resulting model;
meta-mining: meta-learning applied to full data mining process
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 21
/ 50
Overview of the e-LICO system
!"#$%&'()*+,'-!./01' ' ' '(23"$%4'567879'
"':'"'
'
! "#$%&'()&*+,-./,012*+3*2-%4,&
!56 78+*8$+9&21&/:+&+;<=>7&?"&<#@&4;!' <=!*+0)/' />1,)*!?' )*' @!=1)/*' 5' A)!,?<' +' <!1' /B' 0!C>)0!D!*1<' /*' 1;!' >*?!0,A*E' ?+1+' D)*)*E'.,+1B/0DF'4;)<'<!=1)/*'.0!<!*1<'1;!'?)BB!0!*1'=/D./*!*1<'/B'1;!'!"#$%&'+0=;)1!=1>0!'G()E>0!'7H'+*?'<;/I<';/I'1;!A')*1!0+=1'1/'+=;)!J!'1;!'><!0K<'L*/I,!?E!'?)<=/J!0A'E/+,F''
4;!'!"#$%&')*B0+<10>=1>0!'G?!.)=1!?')*'1;!'B)E>0!'>*?!0'1;!'?+<;!?',)*!H')<'1;!'D!+*<'MA'I;)=;'1;!'?+1+"D)*)*E' .,+1B/0D' )<' ?!,)J!0!?' 1/' <=)!*1)<1<F' 4;!' )**/J+1)J!' =/0!' ' /B' 1;!' !"#$%&'.,+1B/0D' )<' 1;!'!"#$%%&'$"#( )&*+,-$./( 0**&*#1"#' G$NOP' +M/J!' 1;!' ?+<;!?' ,)*!H' I)1;' )1<' .,+**!0' +*?' D!1+",!+0*!0F'Q/I!J!0P'1/'?!,)J!0'1;!'?+1+"D)*)*E'.,+1B/0D'1/')1<'<=)!*1)<1'><!0<P'1;!0!'+0!'<!J!0+,'/1;!0'<!0J)=!<'+*?'=/D./*!*1<F'()E>0!'7'<;/I<'+*'/J!0J)!I'/B'!"#$%&R<'=/D./*!*1<'+*?';/I'1;!A' )*1!0+=1'I)1;'!+=;'/1;!0F'
'()E>0!'7F'&J!0J)!I'/B'1;!'!"#$%&'<A<1!DF''
4;!0!'+0!'1I/'><!0"B+=)*E'=/D./*!*1<'B/0'1;!'!"#$%&'.,+1B/0DS'1;!<!'+,,/I'<=)!*1)<1<'1/'+==!<<'?+1+"D)*)*E' /.!0+1/0<' +*?T/0' /1;!0' ?+1+' .0/=!<<)*E' <!0J)=!<P' 1/' =/D./<!' 1;!D' )*1/' I/0LB,/I<' +*?'!U!=>1!' 1;!DP' =/,,!=1)*E' 1;!' 0!<>,1<' B/0' )*1!0.0!1+1)/*' /0' B>01;!0' +*+,A<)<F' 4;!<!' 1I/' =!*10+,')*B0+<10>=1>0!'=/D./*!*1<'+0!V'
7F 213&45&"$.V' O*' +..,)=+1)/*' 1;+1' E)J!<' +==!<<' 1/' +' I)?!' J+0)!1A' /B' ?+1+"D)*)*E' /.!0+1/0<P'1/E!1;!0'I)1;'1;!'D!+*<'1/'=/D./<!'1;!D')*1/'I/0LB,/I<F'
5F 61-$."1V' O' I/0LB,/I' =0!+1)/*' +*?' !*+=1D!*1' I/0LM!*=;' 1;+1' E)J!<' +==!<<' 1/' +0M)10+0A'W!M'<!0J)=!<'+*?'D+*A'/1;!0'L)*?<'/B'<!0J)=!<F' $1' )<'I)?!,A'><!?' )*'M)/)*B/0D+1)=<P'M>1'+,</' )*'D+*A'/1;!0'?)<=).,)*!<F'
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 22
/ 50
IDA architecture
!"##$%&''()#
goal data
*
DM Workflow Ontology (DMWF)
$)+,&,-%-./0##1&'2()#
planned workflows
ranked workflows
3 4
5(6&'/0#7(8&97-'()#meta-mined model
:
DM Optimization Ontology (DMOP)
;7<=#;>#
training meta-data ?
top ranked workflows
@
INTELLIGENT DISCOVERY ASSISTANT
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 23
/ 50
Ontology in computer science
“engineering artefact [...]“ (Guarino 98)
“An ontology is aformal specification ê machine interpretationof a shared ê group of people, consensusconceptualization ê abstract model of phenomena, conceptsof a domain of interest“ ê domain knowledge(Gruber 93)
Ontologia = formal specification of a terminology (from a particulardomain)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 24
/ 50
Ontology in computer science
“engineering artefact [...]“ (Guarino 98)
“An ontology is aformal specification ê machine interpretationof a shared ê group of people, consensusconceptualization ê abstract model of phenomena, conceptsof a domain of interest“ ê domain knowledge(Gruber 93)
Ontologia = formal specification of a terminology (from a particulardomain)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 24
/ 50
Data Mining OPtimization Ontology (DMOP)
the primary goal of DMOP is to support all decision-making stepsthat determine the outcome of the data mining process;
development started in EU FP7 project e-LICO (2009-2012);
DMOP v5.5: 723 classes, 111 properties, 4291 axioms;
highly axiomatized;
represented in Web Ontology Language (OWL 2);
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 25
/ 50
Competency questions
”Given a data mining task/data set, which of the valid or applicableworkflows/algorithms will yield optimal results (or at least better resultsthan the others)?”
”Given a set of candidate workflows/algorithms for a given task/dataset, which data set/workflow/algorithm characteristics should betaken into account in order to select the most appropriate one?”
and others more fine-grained, e.g.:
”Which induction algorithms should I use (or avoid) when my datasethas many more variables than instances?”
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 26
/ 50
Architecture of DMOP knowledge base and its satellitetriple stores
TBox%
DMOP%
ABox%
Operator%DB%
DMEX(DB1%%%%DMEX(DB2%%…%%%DMEX(DBk%
OWL2%
RDF%
Triple%
Store%
Formal%Conceptual%Framework%%of%Data%Mining%Domain%
Accepted%Knowledge%of%DM%Tasks,%Algorithms,%Operators%%
Specific%DM%ApplicaFons%Datasets,%Workflows,%Results%
MetaHminer’s%training%data%
MetaHminer’s%prior%%
DM%knowledge%
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 27
/ 50
The core concepts of DMOP
Fig. 1. The core concepts of DMOP.
more than specify their input/output types; only processes called DM-Operations haveactual inputs and outputs. A process that executes a DM-Operator also realizes the DM-Algorithm implemented by the operator and achieves the DM-Task addressed by thealgorithm. Finally, a DM-Workflow is a complex structure composed of DM operators, aDM-Experiment is a complex process composed of operations (or operator executions).An experiment is described by all the objects that participate in the process: a workflow,data sets used and produced by the different data processing phases, the resulting mod-els, and meta-data quantifying their performance. In the following, the basic elementsof DMOP are detailed.
DM Tasks: The top-level DM tasks are defined by their inputs and outputs. ADataProcessingTask receives and outputs data. Its three subclasses produce new databy cleansing (DataCleaningTask), reducing (DataReductionTask), or otherwise trans-forming the input data (DataTransformationTask). These classes are further articulatedin subclasses representing more fine-grained tasks for each category. An Induction-Task consumes data and produces hypotheses. It can be either a ModelingTask or aPatternDiscoveryTask, based on whether it generates hypotheses in the form of globalmodels or local pattern sets. Modeling tasks can be predictive (e.g. classification) ordescriptive (e.g., clustering), while pattern discovery tasks are further subdivided intoclasses based on the nature of the extracted patterns: associations, dissociations, devia-tions, or subgroups. A HypothesisProcessingTask consumes hypotheses and transforms(e.g., rewrites or prunes) them to produce enhanced—less complex or more readable—versions of the input hypotheses.
Data: As the primary resource that feeds the knowledge discovery process, datahave been a natural research focus for data miners. Over the past decades meta-learningresearchers have actively investigated data characteristics that might explain generaliza-tion success or failure. Fig. 2 shows the characteristics associated with the different Datasubclasses (shaded boxes). Most of these are statistical measures, such as the number of
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 28
/ 50
DMOP: algorithm representation
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 29
/ 50
Alignment of DMOP with DOLCE 1/3
Two main reasons to align DMOP with a foundational ontology:
considerations about attributes and data properties; extantnon-foundational ontology solutions were partial re-inventions of howthey are treated in a foundational ontology;
reuse of the ontology’s object properties;
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 30
/ 50
Alignment of DMOP with DOLCE 2/3
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 31
/ 50
Alignment of DMOP with DOLCE 3/3
Perdurant: DM-Experiment and DM-Operation are subclasses ofdolce:process;
Endurant: most DM classes, such as algorithm, software, strategy,task, and optimization problem, are subclasses ofdolce:non-physical-endurant;
Quality: characteristics and parameters of DM entities madesubclasses of dolce:abstract-quality;
Abstract: for identifying discrete values, classes added as subclassesof dolce:abstract-region;
object properties: DMOP reuses mainly DOLCE’s parthood, quality,and quale relations;
each of the four DOLCE main branches have been used.
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 32
/ 50
Qualities and attributes 1/4
How to handle ’attributes’ in OWL ontologies, and, in a broader context,measurements?
easy way: attribute is a binary functional relation between a class anda datatype
Elephant ⊑ =1 hasWeight.integerElephant ⊑ =1 hasWeightPrecise.realElephant ⊑ =1 hasWeightImperial.integer (in lbs)
building into one’s ontology application decisions about how to storethe data (and in which unit it is) /
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 33
/ 50
Qualities and attributes 2/4
How to handle ’attributes’ in OWL ontologies, and, in a broader context,measurements?
more elaborate way: unfold the notion of an object’s property (e.g.weight) from one attribute/OWL data property into at least twoproperties: one OWL object property from the object to the ’reifiedattribute’ (“quality property” represented as an OWL class) andanother property to the value(s)
▸ favoured in foundational ontologies;▸ solves the problem of non-reusability of the ’attribute’ and prevents
duplication of data properties;▸ neither ontology has any solution to represent actual values and units
of measurements;
measurements for DMOP more alike values for parameters;
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 34
/ 50
Qualities and attributes 3/4
DM-Data
dolce:non-physical-endurant dolce:abstract
DataType DataFormat
dolce:quality
dolce:region
dolce:abstract-regiondolce:quale
dolce:abstract-quality
anyType
hasDataValue
Characteristic Parameter
hasDataType
hasDataType
dolce:has-quale
dolce:particular
dolce:has-quality
dolce:q-location
TableFormat
DataTable hasTableFormat
DataCharacteristic
has-quality
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 35
/ 50
Qualities and attributes 4/4
ModelingAlgorithm ⊑ =1 has-quality.LearningPolicy
LearningPolicy is a dolce:quality
LearningPolicy ⊑ =1 has-quale.Eager-Lazy
Eager-Lazy is a subclass of dolce:abstract-region
Eager-Lazy ⊑ ≤ 1 hasDataValue.anyType
In this way, the ontology can be linked to many different applications, whoeven may use different data types, yet still agree on the meaning of thecharacteristics and parameters (’attributes’) of the algorithms, tasks, andother DM endurants.
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 36
/ 50
Meta-modeling in DMOP 1/4
only processes (executions of workflows) and operations (executionsof operators) consume inputs and produce outputs
DM algorithms (as well as operators and workflows) can only specifythe type of input or output
inputs and outputs (DM-Dataset and DM-Hypothesis class hierarchy,respectively) are modeled as subclasses of IO-Object class
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 37
/ 50
Meta-modeling in DMOP 2/4
DM algorithms: classes or individuals? Individuals.
Problem: expressing types of inputs/outputs associated withalgorithm
”C4.5 specifiesInputClass CategoricalLabeledDataSet” 8
↗ ↖
Individual Class(instance of DM-Algorithm) (subclass of DM-Hypothesis)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 38
/ 50
Meta-modeling in DMOP 3/4
Initial solution: one artificial class per each single algorithm with asingle instance corresponding to this particular algorithm
Problem: hasInput, hasOutput, specifiesInputClass,specifiesOutputClass—assigned a common range—IO-Object
”C4.5 specifiesInputClass Iris” ?
↗ ↖
Individual Individual(instance of DM-Algorithm) (instance of DM-Hypothesis)
Iris is a concrete dataset. Clearly, any DM algorithm is not designedto handle only a particular dataset.
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 39
/ 50
Meta-modeling in DMOP 4/4
Final solution: weak form of punning available in OWL 2
IO-Class: meta-class—the class of all classes of input and outputobjects
”C4.5 specifiesInputClass CategoricalLabeledDataSet” 4
↗ ↖
Individual Individual(instance of DM-Algorithm) (instance of IO-Class)
”DM-Process hasInput some CategoricalLabeledDataSet” 4↗ ↖
Class Class(subclass of dolce:process) (subclass of IO-Object)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 40
/ 50
DMOP: further details
Data Mining Optimization Ontology. C. Maria Keet, AgnieszkaLawrynowicz, Claudia d’Amato, Alexandros Kalousis, Phong Nguyen, RaulPalma, Robert Stevens, and Melanie Hilario, Journal of Web Semantics,DOI: 10.1016/j.websem.2015.01.001
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 41
/ 50
Recap: Propositionalisation
Pa#erns 1) ?x a :Train . ?x :hasCar ?y 2) ?x a :Train . ?x :hasCar ?y . ?y :hasShape :rectangle 3) ?x a :Train . ?x :hasCar ?y . ?y :wheels :three 4) …
Dataset (Michalski’s train problem, 1977)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 42
/ 50
RapidMiner XML based workflow representation
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 43
/ 50
Importing RapidMiner worfklows to DMOP based RDFformat
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 44
/ 50
Propositionalisation
Workflow pa*erns
Dataset
DMOP-‐based RDF repository of DM
processes
Results of experiments. Below we present the results of experimental evaluation of Fr-ONT-Qu in the meta-mining scenario. In the experiments, we used OWLIM SE (v5.3.5849) as an underlying reasoning engine and a semantic store with the owl2-rl-reduced-optimized ruleset. The choice of such a ruleset was motivated by the expressivity of our background knowledge base, e.g. existence of object property chains. During each cycle of cross-validation, Fr-ONT-Qu discovered around 2000 patterns, and redundant patterns were subsequently pruned. We discuss some of the discovered patterns below (for compactness denoting by Bd the body of the base pattern used in the experiments). The first example pattern: Q1 = select distinct ?x where { Bd ∪ ?opex2!dmop:executes ?front0 .! ?opex2!dmop:executes rm:RM-Decision_Tree .! ?opex2!dmop:hasParameterSetting ?front1.! ?front0!dmop:executes rm:DM-Operator .! ?front0!dmop:implements ?front2 .!!! ?front2 a dmop:DM-Algorithm . ?front2 a dmop:InductionAlgorithm .!!! ?front2 a dmop:ModelingAlgorithm .!!! ?front2 a dmop:ClassificationModelingAlgorithm .!!! ?front2 a dmop:ClassificationTreeInductionAlgorithm .!}!
was mined when Fr-ONT-Qu traversed down the algorithm classes hierarchy specializing variable ?front2. In this way, it is possible to abstract from the level of operators (algorithm implementations) to the level of algorithms and their taxonomy. For instance, both rm:RM-Decision_Tree and weka:Weka-J48 operators implement a classification tree induction algorithm and one may generalize over it. The patterns containing class hierarchies provide similar expressivity to this of patterns mined in so-called generalized association rule mining.
The following pattern covers only those workflows that contain ‘Decision Tree’ operator, for which the parameter minimal size for split has value between 2 and 5.5: Q2 = select distinct ?x where { Bd ∪ ?opex2!dmop:executes ?front0 .! ?opex2!dmop:executes rm:RM-Decision_Tree .! ?opex2!dmop:hasParameterSetting ?front1.! ?front0!dmop:executes rm:DM-Operator .! ?front1!dmop:setsValueOf ?front2.! ?front1!dmop:hasValue ?front3.! filter(2.000000 <= xsd:double(?front3) && xsd:double(?front3) <= 16.000000) . ?front2!dmop:hasParameterKey 'minimal_size_for_split'.! ?front1!dmop:hasValue ?front3.! filter(2.000000 <= xsd:double(?front3) && xsd:double(?front3) <= 9.000000) . ?front1!dmop:hasValue ?front3.! filter(2.000000 <= xsd:double(?front3) && xsd:double(?front3) <= 5.500000) . }
Dataset characteris3cs …
Features
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 45
/ 50
Semantic meta-mining experimental setup
baseline DM experiment set: 1581 RapidMiner workflows solving apredictive modeling task on 11 UCI datasets
dataset characteristics meta-data stored in DMEX-DB containingover 85 million of RDF triples
workflow patterns represented as SPARQL queries using DMOPentities
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 46
/ 50
The inside of X-Validation operator with the workflow fortraining and evaluating the pattern-based model
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 47
/ 50
Semantic meta-mining results
McNemar’s test for pairs of classifiers performed with the nullhypothesis that a classifier built using dataset characteristics and amined pattern set has the same error rate as the baseline that useddataset characteristics and only the names of the machine learningDM operators
Test confirmed that classifiers trained using workflow patternsperformed significantly better (accuracy 0.927) than the baseline(accuracy 0.890)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 48
/ 50
Summary and future work
RMonto RapidMiner plugin, all experimental data and (meta-mining)workflows are publicly available:http://www.myexperiment.org/packs/421.html,http://semantic.cs.put.poznan.pl/fr-ont/
LeoLOD project - Learning and Evolving Ontologies from LinkedOpen Data (2013-2015)
▸ project funded by Foundation for Polish Science under the POMOSTprogram,
▸ Fr-ONT-Qu re-adapted for ontology learning,▸ DMOP used to model provenance metadata (in industry: treaceability)
of ontology learning workflows
DMOP is being aligned to OPMW (Open Provenance Model forWorkflows)
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 49
/ 50
Acknowledgements
Foundation for Polish Science under the POMOST programme,cofinanced from European Union, Regional Development Fund (NoPOMOST/2013-7/8) (2013-2015)
EU FP7 ICT-2007.4.4 (No 231519) ”e-LICO: An e-Laboratory forInterdisciplinary Collaborative Research in Data Mining andData-Intensive Science” (2009-2012)
RMonto, Meta-mining experiments, LeoLOD plugin done jointly withJedrzej Potoniec
Contributors to the development of DMOP and/or other e-LICOinfrastructure used in the research described in this presentation:Melanie Hilario, C. Maria Keet, Claudia d’Amato, Huyen Do, SimonFischer, Dragan Gamberger, Lina Al-Jadir, Simon Jupp, AlexandrosKalousis, Joerg Uwe-Kietz, Petra Kralj Novak, Babak Mougouie,Phong Nguyen, Raul Palma, Floarea Serban, Robert Stevens, AnzeVavpetic, Jun Wang, Derry Wijaya, Adam Woznica
Thanks to Veli Bicer for sharing the AIFB dataset
Agnieszka Lawrynowicz collaboration with Jedrzej Potoniec, Maria C. Keet, Melanie Hilario, Claudia d’Amato, Raul Palma and others - see acknowledgements ( Poznan University of Technology )Semantic Meta-Mining of Knowledge Discovery ProcessesJune 11, 2015 ADAA Seminar Silesian University of Technology 50
/ 50