This document discusses predicting SPARQL query execution time using machine learning techniques. It first provides context on assisting users and agents in querying and consuming semantic web data. It then outlines predicting query times and suggesting similar queries from history. The document discusses applying the scientific method used for analyzing algorithms to understand query performance. It describes using machine learning to represent SPARQL queries as feature vectors to predict execution times, with the key challenge being effective feature engineering. An experiment uses support vector machine regression to predict times for test queries from DBpedia with mixed results.

1. Predic'ng
SPARQL
Query
Execu'on
Time
and
Sugges'ng
SPARQL
Queries
Based
on
Query
History
Rakebul
Hasan

2. Context
• Assis'ng
human
users
and
soAware
agents
in:
– Querying
Seman'c
Web
data
• Understanding
query
behavior:
predic'ng
query
performance
– Workload
management,
query
scheduling,
query
op'miza'on
• Construc'ng
and
refining
queries:
sugges'ng
alterna'ves
– Consuming
Seman'c
Web
data
• Understanding
reasoning
of
Seman'c
Web
soAware
agents:
explaining
reasoning
– Transparency,
trust,
scrutability,
decision
effec'veness,
decision
efficiency,
user
sa'sfac'on
1

3. Outline
• Predic'ng
SPARQL
query
execu'on
'me
• Sugges'ng
similar
SPARQL
queries
from
query
history
2

4. PREDICTING
SPARQL
QUERY
EXECUTION
TIME
3

5. • Accurately
predic'ng
query
performance
enables
effec've
– workload
management
– query
scheduling
– query
op'miza'on
4

6. Understanding
performance
of
computer
programs
Insight.
[Knuth]
Use
scien'fic
method
to
understand
performance
5

7. Scien'fic
method
applied
to
analysis
of
algorithms
• A
framework
for
predic'ng
performance
and
comparing
algorithms.
• Scien'fic
method
–
–
–
–
–
Observe
some
feature
of
the
natural
world.
Hypothesize
a
model
that
is
consistent
with
the
observa'ons.
Predict
events
using
the
hypothesis.
Verify
the
predic'ons
by
making
further
observa'ons.
Validate
by
repea'ng
un'l
the
hypothesis
and
observa'ons
agree.
• Principles
– Experiments
must
be
reproducible.
– Hypotheses
must
be
falsifiable.
• Feature
of
the
natural
world.
Computer
itself.
Slide
credit:
Robert
Sedgewick
6

8. Example:
3-­‐Sum
• 3-­‐SUM.
Given
N dis'nct
integers,
how
many
triples
sum
to
exactly
zero?
• 3-­‐SUM
brute-­‐force
algorithm.
Check
all
the
possible
triples.
• How
much
'me
does
it
take?
Slide
credit:
Robert
Sedgewick
7

9. Data
analysis
• Standard
plot.
Plot
running
'me
T (N)
vs.
input
size
N.
Slide
credit:
Robert
Sedgewick
8

10. Data
analysis
• Log-­‐log
plot.
Plot
running
'me
lg(T (N))
vs.
input
size lg N.
• Regression.
Fit
straight
line
through
data
points:
a N b.
• Hypothesis.
The
running
'me
is
about
1.006 × 10 –10 × N 2.999
Slide
credit:
Robert
Sedgewick
9

11. Predic'on
and
valida'on
• Hypothesis.
The
running
'me
is
about
1.006 × 10 –10 × N 2.999
• Predic'ons.
– 51.0
seconds
for
N =
8000.
– 408.1
seconds
for
N =
16000.
• Observa'ons.
Validates
the
hypothesis
Slide
credit:
Robert
Sedgewick
10

12. Understanding
performance
of
database
queries
• Ganapathi
et
al.
predic'ng
performance
metrics
of
database
queries
prior
to
query
execu'on
using
machine
learning.
• Gupta
et
al.
use
machine
learning
for
predic'ng
query
execu'on
'me
ranges.
Ganapathi
et
al.:
Predic'ng
mul'ple
metrics
for
queries:
Befer
decisions
enabled
by
machine
learning.
In
Proc.
of
the
2009
IEEE
ICDE
Gupta
et
al.:
PQR:
Predic'ng
query
execu'on
'mes
for
autonomous
workload
management.
In
Proc.
of
the
2008
ICAC
11

13. Predic'ng
SPARQL
query
execu'on
'me
• Key
challenge.
Feature
engineering
– Represen'ng
SPARQL
queries
as
feature
vectors
• Each
dimension
of
the
vector
is
a
feature
12

14. Configura'on
• Apache
Jena
TDB
– With
DBpedia
3.8
dataset
• Training,
valida'on,
and
test
queries:
randomly
selected
from
DBpedia
SPARQL
Benchmark
(DBPSB)
query
dataset
– 3600
training,
1200
valida'on,
1200
test
13

15. Jena
ARQ
query
processing
• A
SPARQL
query
in
ARQ
goes
through
several
stages
of
processing:
– String
to
Query
(parsing)
– Transla'on
from
Query
to
a
SPARQL
algebra
expression
– Op'miza'on
of
the
algebra
expression
– Query
plan
determina'on
and
low-­‐level
op'miza'on
– Evalua'on
of
the
query
plan
14

16. SPARQL
algebra
features
• SPARQL
Algebra1
1
hfp://www.w3.org/TR/sparql11-­‐query/#sparqlQuery
15

17. SPARQL
algebra
features
DEFGHI,4)/48,9>$$'8JJ703%#<&)0J4)/4JA<BJ=,
KFLFMN,OHKNHPMN,.%/0+,.%"&1,QRFEF,S,
,,,.7,4)/4805)7,90/"3$)8'+(#)%:#+(;+(<&)0=,<,
,,,.7,4)/48%/0+,.%/0+,,
,,,TDNHTPUL,S,.7,4)/48%"&1,.%"&1,V
V
!"#$"%&$
'()*+&$,-.%/0+,.%"&12
3+4$*)"%
56'
$("'3+,
.7,
4)/4805)7,
90/"3$)8'+(#)%:#+(;+(<&)0=
56'
$("'3+,
.7,
4)/48%/0+,
.%/0+
$("'3+,
.7,
4)/48%"&1
.%"&1
$("'3+,56',*)"%,3+4$*)"%,<,<,<,<,'()*+&$,!"#$"%&$,<,<,<,<,!+'$>
,,?,,,,,@,,,A,,,,,,B,,,,,<,<,<,<,,,,B,,,,,,,B,,,,,<,<,<,<,,,C
16

18. Experiment
1
• Model:
Support
Vector
Machine
regression
• Evalua'on
measure:
R2
•
Measures
how
well
future
samples
are
likely
to
be
predicted
by
the
model.
17

19. Experiment
1
• Test
dataset
R2
=
0.004492
Log
scale
plomng
of
predicted
vs
actual
execu'on
'mes
for
the
test
queries.
18

20. Experiment
1
Some
of
the
long
running
queries
share
structurally
similar
basic
graph
paferns.
{
dbpedia
:1549
_Mikko
?p
?
uri
.
?
uri
rdf
:
type
?x
}
Challenge.
How
do
we
represent
basic
graph
paferns
as
vectors?
19

21. Basic
Graph
Pafern
Features
• Infinite
number
of
possibili'es
to
write
a
basic
graph
pafern
(BGP)
• Only
the
set
of
literal
values
and
the
set
of
resources
appearing
in
the
RDF
graph
– Exponen'al
number
of
possibili'es
– A
graph
with
n
triples
has
2n subsets
of
triples
• Feature
vector
with
exponen'al
number
of
dimensions
– Not
feasible
20

22. Basic
Graph
Pafern
Features
• Pafern
graph
=
RDF
graph
constructed
from
all
the
BGPs
in
a
query
– Replace
variables
with
a
fixed
symbol
‘?’
• Cluster
the
training
queries
based
on
pafern
graph
similari'es
• Create
a
vector
with
similarity
scores
between
the
pafern
graph
of
the
query
and
the
queries
in
the
cluster
centers.
21

23. • Graph
Edit
Distance
– Minimum
amount
of
distor'on
needed
to
transform
one
graph
to
another
– Compute
similarity
by
inversing
distance
22

24. • Graph
Edit
Distance
– Usually
computed
using
A*
search
• Exponen'al
running
'me
– Bipar'te
matching
based
approximated
graph
edit
distance
with
• Previous
research
shows
very
accurate
results
with
classifica'on
problems
23

25. • Clustering
Training
Queries
– K-­‐mediods
clustering
algorithm
with
approximated
edit
distance
as
distance
func'on
• Selects
data
points
as
cluster
centers
• Arbitrary
distance
func'on
24

26. Experiment
2
• Model:
Support
Vector
Machine
regression
• Test
dataset
R2
=
0.124204
• K
=
10
Algebra
features
Algebra
+
BGP
features
25

27. Mul'ple
Regressions
• We
train
different
SMV
regressions
for
different
'me
ranges.
• The
variance
in
y-­‐axis
is
less
for
each
regression,
easier
to
fit
a
curve.
26

28. • Different
'me
ranges
– Clustering
the
execu'on
'me
ranges
• We
use
x-­‐means
clustering
algorithm
which
automa'cally
es'mates
the
number
of
clusters
– 5
clusters
found
in
the
training
dataset
– Each
cluster
contains
queries
with
similar
execu'on
'mes
27

29. • Predic'ng
execu'on
'me
range
– Predict
the
corresponding
clusters
for
unseen
queries.
– How
• Train
a
SMV
classifier
with
the
found
clusters
as
labels
• Classify
unseen
queries:
accuracy
of
96%
for
the
test
dataset
• This
means
we
can
accurately
predict
'me
ranges
28

30. • Predic'ng
execu'on
'me
– Different
SMV
regressions
for
different
'me
ranges.
– Use
the
corresponding
regression
to
the
'me
range
cluster
for
an
unseen
query
29

31. Experiment
3
• Test
dataset
R2
=
0.83862
Algebra
+
BGP
features
Mul'ple
regressions
30

32. Predic'ng
with
nearest
neighbors
regression
• The
k-­‐nearest
neighbors
algorithm
(k-­‐NN)
is
oAen
successful
in
the
cases
where
decision
boundary
is
irregular.
• We
train
a
k-­‐NN
with
– Euclidean
distance
as
the
distance
func'on
– Distance
weigh'ng:
weighted
by
the
inverse
of
the
distance
31

33. • k-­‐dimensional
tree
(k-­‐d
tree)
data
structure
to
search
the
nearest
neighbors
– a
space-­‐par''oning
data
structure
for
organizing
points
in
a
k-­‐dimensional
space
• Complexity
of
a
search:
O(log N)
opera'ons
32

34. Experiment
4
• Test
dataset
R2
=
0.837
• k=2
for
k-­‐NN
(selected
by
cross
valida'on)
Mul'ple
regressions
k-­‐NN
33

35. • Future
work
– Training
data
with
broad
coverage
• DBpedia
SPARQL
benchmark
query
templates
– Berlin:
5
templates
– DBPSB:
20
templates
– Fine
tuning
with
more
cross
valida'on
34

36. SUGGESTING
SPARQL
QUERIES
35

37. Sugges'ng
SPARQL
queries
based
on
query
history
• Use
the
same
features
• Construct
a
k-­‐d
tree
for
nearest
neighbor
search
• Top
M neighbors
for
a
query
are
the
top
M
sugges'ons
for
that
query
36

38. Example
SELECT
DISTINCT
?uri
WHERE
{
dbpedia
:1549
_Mikko
?p
?
uri
.
?
uri
rdf
:
type
?x
}
Sugges'on
1
SELECT
DISTINCT
?uri
WHERE
{
dbpedia
:
Radu_Sabo
?p
?
uri
.
?
uri
rdf
:
type
?x
}
Sugges'on
2
SELECT
DISTINCT
?uri
WHERE
{
dbpedia
:
Hafar_Al
-­‐
Ba'n
?p
?
uri
.
?
uri
rdf
:
type
?x
}
Sugges'on
3
SELECT
DISTINCT
?uri
WHERE
{
dbpedia
:
Maurice_D
._G.
_Scof
?p
?
uri
.
?
uri
rdf
:
type
?x
}
37

39. • Future
work
– Query
construc'on
and
refinement
workflow
• How
to
use
the
query
sugges'ons?
– Evalua'ng
the
sugges'ons
• User
study
38

40. Thank
you
39