SlideShare ist ein Scribd-Unternehmen logo
1 von 40
A Review of Relational Machine Learning
for Knowledge Graphs
Present By: Yalda Akbarzadeh
May 2018
A Review of
Relational Machine Learning
for Knowledge Graphs
1. INTRODUCTION
2. KNOWLEDGE
GRAPHS
A. Knowledge
representation
B. Open vs.
closed world
assumption
C. Knowledge
base
construction
3. STATISTICAL
RELATIONAL LEARNING
FOR KNOWLEDGE
GRAPHS
D. Uses of
knowledge
graphs
E. Main tasks in
knowledge graph
construction and
curation
A. Probabilistic
knowledge
graphs
B. Statistical
properties of
knowledge
graphs
C. Types of
SRL models
4. LATENT
FEATURE MODELS
D. Multi-layer
perceptrons
B. Other tensor
factorization
models
C. Matrix
factorization
methods
A. RESCAL: A
bilinear model
E. Neural tensor
networks
F. Latent
distance models
G. Comparison
of models
8. MARKOV
RANDOM
FIELDS
C. Path Ranking
Algorithm
B. Rule Mining and
Inductive Logic
Programming
A. Similarity
measures for uni-
relational data
6. COMBINING
LATENT AND GRAPH
FEATURE MODELS
7. TRAINING SRL
MODELS ON
KNOWLEDGE
GRAPHS 5. GRAPH FEATURE
MODELS
A. Additive
relational
effects model
B. Other
combined
models
A. Penalized
maximum
likelihood
training
B. Where do
the negative
examples come
from?
C. Pairwise loss
training
D. Model
selection
B. Inference
A. Representation
C. Learning
D. Discussion
9. KNOWLEDGE
VAULT
10. EXTENSIONS
AND FUTURE
WORK
D. Discussion
B. Hard
constraints
A. Non-binary
relations
C. Generalizing
to new entities
and relations
D. Querying
probabilistic
knowledge graphs
12. APPENDIX
11. CONCLUDING
REMARKS
D. Querying
probabilistic
knowledge graphs
A Review of Relational Machine Learning for Knowledge Graphs
1. INTRODUCTION
2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS
3. LATENT FEATURE MODELS
4. GRAPH FEATURE MODELS
5. COMBINING LATENT AND GRAPH FEATURE MODELS
6. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS
7. MARKOV RANDOM FIELDS
EXTENSIONS AND FUTURE WORK, COCLUSION
REFERENCES
Traditional machine
Learning Algorithms
feature vector,
numeric or categorical attribute
Input
Mapping
Output Observation
tower
Class labels,
Regression score,
Unsupervised cluster id
Latent vector (embedding)
1. INTRODUCTION  A. Relational Machine Learning 4
feature vector,
numeric or categorical attribute
Representation of an Object
Traditional machine
Learning Algorithms
Graph,
Node and Labeled edges
Berlin
Munich
Düsseldorf
478 Km.
486 Km.
505Km.
1. INTRODUCTION A. Relational Machine Learning 5
Some Canonical Tasks
>> Collective classification
>> Linkprediction
>> Link-based clustering
prediction of
missing edge
clustering nodes
based on their
connectivity pattern
prediction of
properties of
nodes
1. INTRODUCTION A. Relational Machine Learning 6
>> PREDICT(new facts (edges) |existing fact) = LEARN SRL Methods(KGs )
Two main SRL Models
1. INTRODUCTION A. Relational Machine Learning 7
1. INTRODUCTION B. KNOWLEDGE GRAPHS 8
>> Knowledge graphs model information in the form of entities and relationships between them.
Linked Data
(subject, predicate, object) :: (SPO)
(Leonard Nimoy, played, Spock)
 Leonard Nimoy was an actor who played the character
Spock in the science-fiction movie Star Trek
Semantic Web
Linked Data
Resource Description Framework
subject object
predicate
1. INTRODUCTION B. KNOWLEDGE GRAPHS i. Knowledge representation 9
>> closed world assumption (CWA),
non-existing triples indicate false relationships.
Linked Data>> KGs are known to be very incomplete
>> RDF and the Semantic Web make the open-world assumption.
>> open world assumption (OWA),
a non-existing triple is interpreted as unknown.
1. INTRODUCTION B. KNOWLEDGE GRAPHS ii. Open vs. closed world assumption 10
Existing triples are facts
What about non-existing
triples?
Linked Data
1. INTRODUCTION B. KNOWLEDGE GRAPHS iii. Knowledge base construction 11
Linked Data
1. INTRODUCTION B. KNOWLEDGE GRAPHS iv. Uses of knowledge
graphs
12
Linked Data
1. INTRODUCTION  B. KNOWLEDGE GRAPHS  v. Main tasks in KGs construction and curation
Link prediction Entity resolution Link-based clustering
Kate
Ted
Jack
is sister of
isfatherof
isfatherof
Jack
Bonn
uni.
Worksin
uni.
Of
Bonn
Ted
Studiesin
TjLu
Rj
Ed
Lj
Rt
Kj
Jd
Pj
13
2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS 14
2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS A. Probabilistic KGs 15
2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS B. Statistical properties of KGs 16
• Denotes that query answer
should follow a type.
• Tendency of entities to be related
to other entities with similar characteristic.
• All the same blocks members have
the same relation with other block.
2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS C. Types of SRL models 17
M1) latent features and additional parameters
M2) observed graph features and additional parameters
 M3) existence of local interactions (Markov Random Fields)
2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS C. Types of SRL models 18
of M1 and M2:
3. LATENT FEATURE MODELS 19
prestigious awardlatent features -->
Ex) Guinness received the Academy Award
good actor
<- good actor ->
<- prestigious award ->
Relationships between entities can be derived from interactions of their latent features.
3. LATENT FEATURE MODELS A. RESCAL 20
>> RESCAL is a bilinear relational latent feature model which explains triples via pairwise interactions of latent
features.
This importance is used here:
Relationships between entities can be derived
from interactions of their latent features.
3. LATENT FEATURE MODELS B. Matrix factorization methods 21
>> Approach for learning from knowledge graphs is based on matrix factorization
memory
complexity
Lose
information
Reshape
3. LATENT FEATURE MODELS C. Multi-layer-perceptrons 22
L:
3. LATENT FEATURE MODELS C. Multi-layer-perceptrons 23
>> E-MLP model :
02
03
04
Σ
3. LATENT FEATURE MODELS C. Multi-layer-perceptrons 24
It can reduce the number of required parametersIt can reduce the number of required parameters
Advantage of E-MLP
Disadvantage of E-MLP
02
03
04
Σ
3. LATENT FEATURE MODELS D. Neural tensor networks 25
02
03
04
>> Neural Tensor Network (NTN):
Combines traditional MLPs with bilinear models
3. LATENT FEATURE MODELS E. Latent distance models 26
02
03
04
>> Latent distance models or latent space models in social network analysis:
 Derive the probability of relationships from the distance between latent representations of entities
#--------------------------------------------------------------------------------------------------------------------------------------
4. GRAPH FEATURE MODELS A. Similarity measures for uni-relational data 27
>> Existence of an edge can be predicted by extracting features from the observed edges in the graph.
>> GFMs Widely used for link prediction in uni-relational graphs.
>> intuition:
 similar entities are likely to be related (homophily)
 the similarity of entities can be derived from:
• neighborhood of nodes
• existence of paths between nodes
>> Approaches to measure the similarity of entities:
John Mary
Parent of
Anne
Parent of
(John, marriedTo, Mary)
Predict
Local similarity
Global similarity
Quasi-local similarity
4. GRAPH FEATURE MODELS  B. Path Ranking Algorithm 28
>> Using random walks of bounded lengths for predicting links
in multi-relational knowledge graphs.
4. GRAPH FEATURE MODELS  B. Path Ranking Algorithm 29
EXAMPLES OF PATHS LEARNED BY PRA ON FREEBASE
TO PREDICT WHICH COLLEGE A PERSON ATTENDED
Relation Path Weight
(draftedBy, school) 2.62
(sibling(s), sibling, education, institution) 1.88
(parents, education, institution) 1.37
(children, education, institution) 1.85
>> key idea in PRA:
Use path probabilities as features for predicting the probability of missing edges.
5. COMBINING LATENT AND GRAPH FEATURE MODEL 30
>>Latent feature models:
 well-suited for modeling global relational patterns via newly
introduced latent variables.
 They are computationally efficient if triples can be explained
with a small number of latent variables.
>>Graph feature models:
 are well-suited for modeling local and quasi-local graphs
patterns.
 They are computationally efficient if triples can be explained
from the neighborhood of entities or from short paths in
the graph
5. COMBINING LATENT AND GRAPH FEATURE MODEL  Additive Relational Effects models 31
6. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS  A. Penalized maximum likelihood training 32
02
03
04
posterior priorlikelihood
6. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS  B. Where do the negative examples come from? 33
>> Most knowledge graphs only contain positive training examples.
6. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS 34
02
03
04
7. MARKOV RANDOM FIELDS 35
 3-vertex cliques
7. MARKOV RANDOM FIELDS 36
02
03
04
>> Form of Markov Random Fields (MRFs):
EXTENSIONS AND FUTURE WORK 37
A. Non-binary relations
B. Hard constraints: types, functional constraints, and others
C. Generalizing to new entities and relations
D. Querying probabilistic knowledge graphs
E. Trustworthiness of knowledge graphs
 Conclusion 38
review of state-of-the-art statistical relational learning (SRL) methods applied to very large knowledge graphs
KGs have found important applications in question answering, structured search, exploratory search
showed how to create a truly massive, machine-interpretable “semantic memory” of facts
REFERENCES
39
[1] M. Nickel, K. Murphy, V. Tresp, and E. Gabrilovich, “A review of relational machine learning for knowledge
graphs,” Proceedings of the IEEE, vol. 104, pp. 11-33, 2016.
[2] N. Lao, T. Mitchell, and W. W. Cohen, “Random walk inference and learning in a large scale knowledge base,”
in Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2011, pp. 529-539.
[3] “An Introduction to Statistical Relational Learning” at: www.cs.kuleuven.be/~lucdr/salvador.pdf.
[4] “sampling procedure” at: https://www.slideshare.net/anasomoray/chapter-4-sampling-procedure
[5] “Non-Hierarchical Clustering” at: https://courses.cs.washington.edu/courses/cse527/01au/oct25/oct25.html
[6] https://en.wikipedia.org/
[7] N. Feldman, Learning and overgeneralization patterns in a connectionist model of the German plural: Cite seer,
2005.
[8] “Introduction to: Open World Assumption vs Closed World Assumption”, at:
http://www.dataversity.net/introduction-to-open-world-assumption-vs-closed-world-assumption/
[9] “Introducing the Knowledge Graph ”, at: https://www.youtube.com/watch?v=mmQl6VGvX-c
[10] “What is Linked Data?”, at: https://www.w3.org/standards/semanticweb/data
[11] “Resource Description Framework (RDF)”, at: https://www.w3.org/TR/rdf-concepts/
THE END
Thank you
40
?

Weitere ähnliche Inhalte

Was ist angesagt?

Ijarcet vol-2-issue-2-337-341
Ijarcet vol-2-issue-2-337-341Ijarcet vol-2-issue-2-337-341
Ijarcet vol-2-issue-2-337-341Editor IJARCET
 
M.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsM.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsVijay Karan
 
M.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsM.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsVijay Karan
 
A Hybrid Technique for Shape Matching Based on chain code and DFS Tree
A Hybrid Technique for Shape Matching Based on chain code and DFS TreeA Hybrid Technique for Shape Matching Based on chain code and DFS Tree
A Hybrid Technique for Shape Matching Based on chain code and DFS TreeIOSR Journals
 
M.E Computer Science Image Processing Projects
M.E Computer Science Image Processing ProjectsM.E Computer Science Image Processing Projects
M.E Computer Science Image Processing ProjectsVijay Karan
 
Role Model of Graph Coloring Application in Labeled 2D Line Drawing Object
Role Model of Graph Coloring Application in Labeled 2D Line Drawing ObjectRole Model of Graph Coloring Application in Labeled 2D Line Drawing Object
Role Model of Graph Coloring Application in Labeled 2D Line Drawing ObjectWaqas Tariq
 
The state of the art in handwriting synthesis
The state of the art in handwriting synthesisThe state of the art in handwriting synthesis
The state of the art in handwriting synthesisRanda Elanwar
 
Std 12 Computer Chapter 6 object oriented concept important mcqs
Std 12 Computer Chapter 6 object oriented concept important mcqsStd 12 Computer Chapter 6 object oriented concept important mcqs
Std 12 Computer Chapter 6 object oriented concept important mcqsNuzhat Memon
 
A study and implementation of the transit route network design problem for a ...
A study and implementation of the transit route network design problem for a ...A study and implementation of the transit route network design problem for a ...
A study and implementation of the transit route network design problem for a ...csandit
 
AUTOMATIC TRAINING DATA SYNTHESIS FOR HANDWRITING RECOGNITION USING THE STRUC...
AUTOMATIC TRAINING DATA SYNTHESIS FOR HANDWRITING RECOGNITION USING THE STRUC...AUTOMATIC TRAINING DATA SYNTHESIS FOR HANDWRITING RECOGNITION USING THE STRUC...
AUTOMATIC TRAINING DATA SYNTHESIS FOR HANDWRITING RECOGNITION USING THE STRUC...ijaia
 

Was ist angesagt? (10)

Ijarcet vol-2-issue-2-337-341
Ijarcet vol-2-issue-2-337-341Ijarcet vol-2-issue-2-337-341
Ijarcet vol-2-issue-2-337-341
 
M.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsM.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing Projects
 
M.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing ProjectsM.Phil Computer Science Image Processing Projects
M.Phil Computer Science Image Processing Projects
 
A Hybrid Technique for Shape Matching Based on chain code and DFS Tree
A Hybrid Technique for Shape Matching Based on chain code and DFS TreeA Hybrid Technique for Shape Matching Based on chain code and DFS Tree
A Hybrid Technique for Shape Matching Based on chain code and DFS Tree
 
M.E Computer Science Image Processing Projects
M.E Computer Science Image Processing ProjectsM.E Computer Science Image Processing Projects
M.E Computer Science Image Processing Projects
 
Role Model of Graph Coloring Application in Labeled 2D Line Drawing Object
Role Model of Graph Coloring Application in Labeled 2D Line Drawing ObjectRole Model of Graph Coloring Application in Labeled 2D Line Drawing Object
Role Model of Graph Coloring Application in Labeled 2D Line Drawing Object
 
The state of the art in handwriting synthesis
The state of the art in handwriting synthesisThe state of the art in handwriting synthesis
The state of the art in handwriting synthesis
 
Std 12 Computer Chapter 6 object oriented concept important mcqs
Std 12 Computer Chapter 6 object oriented concept important mcqsStd 12 Computer Chapter 6 object oriented concept important mcqs
Std 12 Computer Chapter 6 object oriented concept important mcqs
 
A study and implementation of the transit route network design problem for a ...
A study and implementation of the transit route network design problem for a ...A study and implementation of the transit route network design problem for a ...
A study and implementation of the transit route network design problem for a ...
 
AUTOMATIC TRAINING DATA SYNTHESIS FOR HANDWRITING RECOGNITION USING THE STRUC...
AUTOMATIC TRAINING DATA SYNTHESIS FOR HANDWRITING RECOGNITION USING THE STRUC...AUTOMATIC TRAINING DATA SYNTHESIS FOR HANDWRITING RECOGNITION USING THE STRUC...
AUTOMATIC TRAINING DATA SYNTHESIS FOR HANDWRITING RECOGNITION USING THE STRUC...
 

Ähnlich wie A Review of Relational Machine Learning(SRL) for Knowledge Graphs

Graph Signal Processing for Machine Learning A Review and New Perspectives - ...
Graph Signal Processing for Machine Learning A Review and New Perspectives - ...Graph Signal Processing for Machine Learning A Review and New Perspectives - ...
Graph Signal Processing for Machine Learning A Review and New Perspectives - ...lauratoni4
 
Learning Graph Representation for Data-Efficiency RL
Learning Graph Representation for Data-Efficiency RLLearning Graph Representation for Data-Efficiency RL
Learning Graph Representation for Data-Efficiency RLlauratoni4
 
Lecture 07 leonidas guibas - networks of shapes and images
Lecture 07   leonidas guibas - networks of shapes and imagesLecture 07   leonidas guibas - networks of shapes and images
Lecture 07 leonidas guibas - networks of shapes and imagesmustafa sarac
 
(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot LearningMasahiro Suzuki
 
Laplacian-regularized Graph Bandits
Laplacian-regularized Graph BanditsLaplacian-regularized Graph Bandits
Laplacian-regularized Graph Banditslauratoni4
 
Deep Graph Contrastive Representation Learning.pptx
Deep Graph Contrastive Representation Learning.pptxDeep Graph Contrastive Representation Learning.pptx
Deep Graph Contrastive Representation Learning.pptxssuser2624f71
 
Linearity of Feature Extraction Techniques for Medical Images by using Scale ...
Linearity of Feature Extraction Techniques for Medical Images by using Scale ...Linearity of Feature Extraction Techniques for Medical Images by using Scale ...
Linearity of Feature Extraction Techniques for Medical Images by using Scale ...ijtsrd
 
From Signal to Symbols
From Signal to SymbolsFrom Signal to Symbols
From Signal to Symbolsgpano
 
Responsible AI in Industry: Practical Challenges and Lessons Learned
Responsible AI in Industry: Practical Challenges and Lessons LearnedResponsible AI in Industry: Practical Challenges and Lessons Learned
Responsible AI in Industry: Practical Challenges and Lessons LearnedKrishnaram Kenthapadi
 
A Novel Feature Selection with Annealing For Computer Vision And Big Data Lea...
A Novel Feature Selection with Annealing For Computer Vision And Big Data Lea...A Novel Feature Selection with Annealing For Computer Vision And Big Data Lea...
A Novel Feature Selection with Annealing For Computer Vision And Big Data Lea...theijes
 
Exploring the potential of deep learning for map generalization
Exploring the potential of deep learning for map generalizationExploring the potential of deep learning for map generalization
Exploring the potential of deep learning for map generalizationazellecourtial
 
An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...IJDKP
 
What Makes Graph Queries Difficult?
What Makes Graph Queries Difficult?What Makes Graph Queries Difficult?
What Makes Graph Queries Difficult?Gábor Szárnyas
 
A Graph-based Model for multimodal Information Retrieval (partially presented)
A Graph-based Model for multimodal Information Retrieval (partially presented)A Graph-based Model for multimodal Information Retrieval (partially presented)
A Graph-based Model for multimodal Information Retrieval (partially presented)serwah_S_gh
 
Attentive Relational Networks for Mapping Images to Scene Graphs
Attentive Relational Networks for Mapping Images to Scene GraphsAttentive Relational Networks for Mapping Images to Scene Graphs
Attentive Relational Networks for Mapping Images to Scene GraphsSangmin Woo
 
IRJET- Link Prediction in Social Networks
IRJET- Link Prediction in Social NetworksIRJET- Link Prediction in Social Networks
IRJET- Link Prediction in Social NetworksIRJET Journal
 
Executive SummaryIntroductionProtein engineering
Executive SummaryIntroductionProtein engineeringExecutive SummaryIntroductionProtein engineering
Executive SummaryIntroductionProtein engineeringBetseyCalderon89
 

Ähnlich wie A Review of Relational Machine Learning(SRL) for Knowledge Graphs (20)

Graph Signal Processing for Machine Learning A Review and New Perspectives - ...
Graph Signal Processing for Machine Learning A Review and New Perspectives - ...Graph Signal Processing for Machine Learning A Review and New Perspectives - ...
Graph Signal Processing for Machine Learning A Review and New Perspectives - ...
 
Learning Graph Representation for Data-Efficiency RL
Learning Graph Representation for Data-Efficiency RLLearning Graph Representation for Data-Efficiency RL
Learning Graph Representation for Data-Efficiency RL
 
Lecture 07 leonidas guibas - networks of shapes and images
Lecture 07   leonidas guibas - networks of shapes and imagesLecture 07   leonidas guibas - networks of shapes and images
Lecture 07 leonidas guibas - networks of shapes and images
 
(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning
 
Laplacian-regularized Graph Bandits
Laplacian-regularized Graph BanditsLaplacian-regularized Graph Bandits
Laplacian-regularized Graph Bandits
 
Deep Graph Contrastive Representation Learning.pptx
Deep Graph Contrastive Representation Learning.pptxDeep Graph Contrastive Representation Learning.pptx
Deep Graph Contrastive Representation Learning.pptx
 
Linearity of Feature Extraction Techniques for Medical Images by using Scale ...
Linearity of Feature Extraction Techniques for Medical Images by using Scale ...Linearity of Feature Extraction Techniques for Medical Images by using Scale ...
Linearity of Feature Extraction Techniques for Medical Images by using Scale ...
 
From Signal to Symbols
From Signal to SymbolsFrom Signal to Symbols
From Signal to Symbols
 
Responsible AI in Industry: Practical Challenges and Lessons Learned
Responsible AI in Industry: Practical Challenges and Lessons LearnedResponsible AI in Industry: Practical Challenges and Lessons Learned
Responsible AI in Industry: Practical Challenges and Lessons Learned
 
Objects Clustering of Movie Using Graph Mining Technique
Objects Clustering of Movie Using Graph Mining TechniqueObjects Clustering of Movie Using Graph Mining Technique
Objects Clustering of Movie Using Graph Mining Technique
 
algorithms
algorithmsalgorithms
algorithms
 
A Novel Feature Selection with Annealing For Computer Vision And Big Data Lea...
A Novel Feature Selection with Annealing For Computer Vision And Big Data Lea...A Novel Feature Selection with Annealing For Computer Vision And Big Data Lea...
A Novel Feature Selection with Annealing For Computer Vision And Big Data Lea...
 
Exploring the potential of deep learning for map generalization
Exploring the potential of deep learning for map generalizationExploring the potential of deep learning for map generalization
Exploring the potential of deep learning for map generalization
 
An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...
 
What Makes Graph Queries Difficult?
What Makes Graph Queries Difficult?What Makes Graph Queries Difficult?
What Makes Graph Queries Difficult?
 
A Graph-based Model for multimodal Information Retrieval (partially presented)
A Graph-based Model for multimodal Information Retrieval (partially presented)A Graph-based Model for multimodal Information Retrieval (partially presented)
A Graph-based Model for multimodal Information Retrieval (partially presented)
 
Attentive Relational Networks for Mapping Images to Scene Graphs
Attentive Relational Networks for Mapping Images to Scene GraphsAttentive Relational Networks for Mapping Images to Scene Graphs
Attentive Relational Networks for Mapping Images to Scene Graphs
 
IRJET- Link Prediction in Social Networks
IRJET- Link Prediction in Social NetworksIRJET- Link Prediction in Social Networks
IRJET- Link Prediction in Social Networks
 
Executive SummaryIntroductionProtein engineering
Executive SummaryIntroductionProtein engineeringExecutive SummaryIntroductionProtein engineering
Executive SummaryIntroductionProtein engineering
 
Sunbelt 2013 Presentation
Sunbelt 2013 PresentationSunbelt 2013 Presentation
Sunbelt 2013 Presentation
 

Kürzlich hochgeladen

Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bSérgio Sacani
 
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...chandars293
 
GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)Areesha Ahmad
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticssakshisoni2385
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfrohankumarsinghrore1
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Servicenishacall1
 
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICESAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICEayushi9330
 
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)Joonhun Lee
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learninglevieagacer
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPirithiRaju
 
STS-UNIT 4 CLIMATE CHANGE POWERPOINT PRESENTATION
STS-UNIT 4 CLIMATE CHANGE POWERPOINT PRESENTATIONSTS-UNIT 4 CLIMATE CHANGE POWERPOINT PRESENTATION
STS-UNIT 4 CLIMATE CHANGE POWERPOINT PRESENTATIONrouseeyyy
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPirithiRaju
 
Dopamine neurotransmitter determination using graphite sheet- graphene nano-s...
Dopamine neurotransmitter determination using graphite sheet- graphene nano-s...Dopamine neurotransmitter determination using graphite sheet- graphene nano-s...
Dopamine neurotransmitter determination using graphite sheet- graphene nano-s...Mohammad Khajehpour
 
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flypumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flyPRADYUMMAURYA1
 
Unit5-Cloud.pptx for lpu course cse121 o
Unit5-Cloud.pptx for lpu course cse121 oUnit5-Cloud.pptx for lpu course cse121 o
Unit5-Cloud.pptx for lpu course cse121 oManavSingh202607
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)Areesha Ahmad
 
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxSCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxRizalinePalanog2
 
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts ServiceJustdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Servicemonikaservice1
 
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑Damini Dixit
 

Kürzlich hochgeladen (20)

Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
 
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
 
GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdf
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
 
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICESAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
 
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
 
STS-UNIT 4 CLIMATE CHANGE POWERPOINT PRESENTATION
STS-UNIT 4 CLIMATE CHANGE POWERPOINT PRESENTATIONSTS-UNIT 4 CLIMATE CHANGE POWERPOINT PRESENTATION
STS-UNIT 4 CLIMATE CHANGE POWERPOINT PRESENTATION
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
 
Dopamine neurotransmitter determination using graphite sheet- graphene nano-s...
Dopamine neurotransmitter determination using graphite sheet- graphene nano-s...Dopamine neurotransmitter determination using graphite sheet- graphene nano-s...
Dopamine neurotransmitter determination using graphite sheet- graphene nano-s...
 
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flypumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
 
Unit5-Cloud.pptx for lpu course cse121 o
Unit5-Cloud.pptx for lpu course cse121 oUnit5-Cloud.pptx for lpu course cse121 o
Unit5-Cloud.pptx for lpu course cse121 o
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxSCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
 
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts ServiceJustdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
 
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
 

A Review of Relational Machine Learning(SRL) for Knowledge Graphs

  • 1. A Review of Relational Machine Learning for Knowledge Graphs Present By: Yalda Akbarzadeh May 2018
  • 2. A Review of Relational Machine Learning for Knowledge Graphs 1. INTRODUCTION 2. KNOWLEDGE GRAPHS A. Knowledge representation B. Open vs. closed world assumption C. Knowledge base construction 3. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS D. Uses of knowledge graphs E. Main tasks in knowledge graph construction and curation A. Probabilistic knowledge graphs B. Statistical properties of knowledge graphs C. Types of SRL models 4. LATENT FEATURE MODELS D. Multi-layer perceptrons B. Other tensor factorization models C. Matrix factorization methods A. RESCAL: A bilinear model E. Neural tensor networks F. Latent distance models G. Comparison of models 8. MARKOV RANDOM FIELDS C. Path Ranking Algorithm B. Rule Mining and Inductive Logic Programming A. Similarity measures for uni- relational data 6. COMBINING LATENT AND GRAPH FEATURE MODELS 7. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS 5. GRAPH FEATURE MODELS A. Additive relational effects model B. Other combined models A. Penalized maximum likelihood training B. Where do the negative examples come from? C. Pairwise loss training D. Model selection B. Inference A. Representation C. Learning D. Discussion 9. KNOWLEDGE VAULT 10. EXTENSIONS AND FUTURE WORK D. Discussion B. Hard constraints A. Non-binary relations C. Generalizing to new entities and relations D. Querying probabilistic knowledge graphs 12. APPENDIX 11. CONCLUDING REMARKS D. Querying probabilistic knowledge graphs
  • 3. A Review of Relational Machine Learning for Knowledge Graphs 1. INTRODUCTION 2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS 3. LATENT FEATURE MODELS 4. GRAPH FEATURE MODELS 5. COMBINING LATENT AND GRAPH FEATURE MODELS 6. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS 7. MARKOV RANDOM FIELDS EXTENSIONS AND FUTURE WORK, COCLUSION REFERENCES
  • 4. Traditional machine Learning Algorithms feature vector, numeric or categorical attribute Input Mapping Output Observation tower Class labels, Regression score, Unsupervised cluster id Latent vector (embedding) 1. INTRODUCTION  A. Relational Machine Learning 4
  • 5. feature vector, numeric or categorical attribute Representation of an Object Traditional machine Learning Algorithms Graph, Node and Labeled edges Berlin Munich Düsseldorf 478 Km. 486 Km. 505Km. 1. INTRODUCTION A. Relational Machine Learning 5
  • 6. Some Canonical Tasks >> Collective classification >> Linkprediction >> Link-based clustering prediction of missing edge clustering nodes based on their connectivity pattern prediction of properties of nodes 1. INTRODUCTION A. Relational Machine Learning 6
  • 7. >> PREDICT(new facts (edges) |existing fact) = LEARN SRL Methods(KGs ) Two main SRL Models 1. INTRODUCTION A. Relational Machine Learning 7
  • 8. 1. INTRODUCTION B. KNOWLEDGE GRAPHS 8
  • 9. >> Knowledge graphs model information in the form of entities and relationships between them. Linked Data (subject, predicate, object) :: (SPO) (Leonard Nimoy, played, Spock)  Leonard Nimoy was an actor who played the character Spock in the science-fiction movie Star Trek Semantic Web Linked Data Resource Description Framework subject object predicate 1. INTRODUCTION B. KNOWLEDGE GRAPHS i. Knowledge representation 9
  • 10. >> closed world assumption (CWA), non-existing triples indicate false relationships. Linked Data>> KGs are known to be very incomplete >> RDF and the Semantic Web make the open-world assumption. >> open world assumption (OWA), a non-existing triple is interpreted as unknown. 1. INTRODUCTION B. KNOWLEDGE GRAPHS ii. Open vs. closed world assumption 10 Existing triples are facts What about non-existing triples?
  • 11. Linked Data 1. INTRODUCTION B. KNOWLEDGE GRAPHS iii. Knowledge base construction 11
  • 12. Linked Data 1. INTRODUCTION B. KNOWLEDGE GRAPHS iv. Uses of knowledge graphs 12
  • 13. Linked Data 1. INTRODUCTION  B. KNOWLEDGE GRAPHS  v. Main tasks in KGs construction and curation Link prediction Entity resolution Link-based clustering Kate Ted Jack is sister of isfatherof isfatherof Jack Bonn uni. Worksin uni. Of Bonn Ted Studiesin TjLu Rj Ed Lj Rt Kj Jd Pj 13
  • 14. 2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS 14
  • 15. 2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS A. Probabilistic KGs 15
  • 16. 2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS B. Statistical properties of KGs 16 • Denotes that query answer should follow a type. • Tendency of entities to be related to other entities with similar characteristic. • All the same blocks members have the same relation with other block.
  • 17. 2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS C. Types of SRL models 17 M1) latent features and additional parameters M2) observed graph features and additional parameters  M3) existence of local interactions (Markov Random Fields)
  • 18. 2. STATISTICAL RELATIONAL LEARNING FOR KNOWLEDGE GRAPHS C. Types of SRL models 18 of M1 and M2:
  • 19. 3. LATENT FEATURE MODELS 19 prestigious awardlatent features --> Ex) Guinness received the Academy Award good actor <- good actor -> <- prestigious award -> Relationships between entities can be derived from interactions of their latent features.
  • 20. 3. LATENT FEATURE MODELS A. RESCAL 20 >> RESCAL is a bilinear relational latent feature model which explains triples via pairwise interactions of latent features. This importance is used here: Relationships between entities can be derived from interactions of their latent features.
  • 21. 3. LATENT FEATURE MODELS B. Matrix factorization methods 21 >> Approach for learning from knowledge graphs is based on matrix factorization memory complexity Lose information Reshape
  • 22. 3. LATENT FEATURE MODELS C. Multi-layer-perceptrons 22 L:
  • 23. 3. LATENT FEATURE MODELS C. Multi-layer-perceptrons 23 >> E-MLP model : 02 03 04 Σ
  • 24. 3. LATENT FEATURE MODELS C. Multi-layer-perceptrons 24 It can reduce the number of required parametersIt can reduce the number of required parameters Advantage of E-MLP Disadvantage of E-MLP 02 03 04 Σ
  • 25. 3. LATENT FEATURE MODELS D. Neural tensor networks 25 02 03 04 >> Neural Tensor Network (NTN): Combines traditional MLPs with bilinear models
  • 26. 3. LATENT FEATURE MODELS E. Latent distance models 26 02 03 04 >> Latent distance models or latent space models in social network analysis:  Derive the probability of relationships from the distance between latent representations of entities #--------------------------------------------------------------------------------------------------------------------------------------
  • 27. 4. GRAPH FEATURE MODELS A. Similarity measures for uni-relational data 27 >> Existence of an edge can be predicted by extracting features from the observed edges in the graph. >> GFMs Widely used for link prediction in uni-relational graphs. >> intuition:  similar entities are likely to be related (homophily)  the similarity of entities can be derived from: • neighborhood of nodes • existence of paths between nodes >> Approaches to measure the similarity of entities: John Mary Parent of Anne Parent of (John, marriedTo, Mary) Predict Local similarity Global similarity Quasi-local similarity
  • 28. 4. GRAPH FEATURE MODELS  B. Path Ranking Algorithm 28 >> Using random walks of bounded lengths for predicting links in multi-relational knowledge graphs.
  • 29. 4. GRAPH FEATURE MODELS  B. Path Ranking Algorithm 29 EXAMPLES OF PATHS LEARNED BY PRA ON FREEBASE TO PREDICT WHICH COLLEGE A PERSON ATTENDED Relation Path Weight (draftedBy, school) 2.62 (sibling(s), sibling, education, institution) 1.88 (parents, education, institution) 1.37 (children, education, institution) 1.85 >> key idea in PRA: Use path probabilities as features for predicting the probability of missing edges.
  • 30. 5. COMBINING LATENT AND GRAPH FEATURE MODEL 30 >>Latent feature models:  well-suited for modeling global relational patterns via newly introduced latent variables.  They are computationally efficient if triples can be explained with a small number of latent variables. >>Graph feature models:  are well-suited for modeling local and quasi-local graphs patterns.  They are computationally efficient if triples can be explained from the neighborhood of entities or from short paths in the graph
  • 31. 5. COMBINING LATENT AND GRAPH FEATURE MODEL  Additive Relational Effects models 31
  • 32. 6. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS  A. Penalized maximum likelihood training 32 02 03 04 posterior priorlikelihood
  • 33. 6. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS  B. Where do the negative examples come from? 33 >> Most knowledge graphs only contain positive training examples.
  • 34. 6. TRAINING SRL MODELS ON KNOWLEDGE GRAPHS 34 02 03 04
  • 35. 7. MARKOV RANDOM FIELDS 35  3-vertex cliques
  • 36. 7. MARKOV RANDOM FIELDS 36 02 03 04 >> Form of Markov Random Fields (MRFs):
  • 37. EXTENSIONS AND FUTURE WORK 37 A. Non-binary relations B. Hard constraints: types, functional constraints, and others C. Generalizing to new entities and relations D. Querying probabilistic knowledge graphs E. Trustworthiness of knowledge graphs
  • 38.  Conclusion 38 review of state-of-the-art statistical relational learning (SRL) methods applied to very large knowledge graphs KGs have found important applications in question answering, structured search, exploratory search showed how to create a truly massive, machine-interpretable “semantic memory” of facts
  • 39. REFERENCES 39 [1] M. Nickel, K. Murphy, V. Tresp, and E. Gabrilovich, “A review of relational machine learning for knowledge graphs,” Proceedings of the IEEE, vol. 104, pp. 11-33, 2016. [2] N. Lao, T. Mitchell, and W. W. Cohen, “Random walk inference and learning in a large scale knowledge base,” in Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2011, pp. 529-539. [3] “An Introduction to Statistical Relational Learning” at: www.cs.kuleuven.be/~lucdr/salvador.pdf. [4] “sampling procedure” at: https://www.slideshare.net/anasomoray/chapter-4-sampling-procedure [5] “Non-Hierarchical Clustering” at: https://courses.cs.washington.edu/courses/cse527/01au/oct25/oct25.html [6] https://en.wikipedia.org/ [7] N. Feldman, Learning and overgeneralization patterns in a connectionist model of the German plural: Cite seer, 2005. [8] “Introduction to: Open World Assumption vs Closed World Assumption”, at: http://www.dataversity.net/introduction-to-open-world-assumption-vs-closed-world-assumption/ [9] “Introducing the Knowledge Graph ”, at: https://www.youtube.com/watch?v=mmQl6VGvX-c [10] “What is Linked Data?”, at: https://www.w3.org/standards/semanticweb/data [11] “Resource Description Framework (RDF)”, at: https://www.w3.org/TR/rdf-concepts/