Building NeuroSearch

1
Building NeuroSearch Intelligent Evolutionary
Search Algorithm For Peer-to-Peer
EnvironmentMasters Thesis by Joni Töyrylä
3.9.2004

• Mikko Vapa, researcher studentInBCT 3.2 Cheese
  Factory / P2P Communication
• Agora Center
• http//tisu.it.jyu.fi/cheesefactory

2
Contents

• Resource Discovery Problem
• Related Work
• Peer-to-Peer Network
• Neural Networks
• Evolutionary Computing
• NeuroSearch
• Research Environment
• Research Cases
• Fitness
• Population
• Inputs
• Resources
• Queriers
• Brain Size
• Summary and Future

3
Resource Discovery Problem

• In peer-to-peer (P2P) resource discovery problem
  a P2P node decides based on local knowledge
  which neighbors would be the best targets (if
  any) for the query to find the needed resource
• A good solution locates the predetermined number
  of resources using minimal number of packets

4
NeuroSearch

• NeuroSearch resource discovery algorithm uses
  neural networks and evolution to adapt its
  behavior to given environment
• neural network for deciding whether to pass the
  query further down the link or not
• evolution for breeding and finding out the best
  neural network in a large class of local search
  algorithms

Neighbor Node
Forward the query
Query
Neighbor Node
Forward the query
5
NeuroSearchs Inputs

• The internal structure of NeuroSearch algorithm
• Multiple layers enable the algorithm to express
  non-linear behavior
• With enough neurons the algorithm can universally
  approximate any decision function

6
NeuroSearchs Inputs

• Bias is always 1 and provides means for neuron to
  produce non-zero output with zero inputs
• Hops is the number of links the message has gone
  this far
• Neighbors (also known as currentNeighbors or
  MyNeighbors) is the amount of neighbor nodes this
  node has
• Targets neighbors (also known as toNeighbors) is
  the amount of neighbor nodes the messages target
  has
• Neighbor rank (also known as NeighborsOrder)
  tells targets neighbor amoun related to current
  nodes other neighbors
• Sent is a flag telling if this message has
  already been forwarded to the target node by this
  node
• Received (also known as currentVisited) is a flag
  describing whether the current node has got this
  message earlier

7
NeuroSearchs Training Program

• The neural network weights define how neural
  network behaves so they must be adjusted to right
  values
• This is done using iterative optimization process
  based on evolution and Gaussian mutation

Define thenetwork conditions
Iteratethousandsofgenerations
Create candidate algorithmsrandomly
Select the bestones for nextgeneration
Breed a newpopulation
Define the quality requirementsfor the algorithm
Finally select thebest algorithm forthese
conditions
8
Research Environment

• The peer-to-peer network being tested contained
• 100 power-law distributed P2P nodes with 394
  links and 788 resources
• Resources were distributed based on the number of
  connections the node has meaning that
  high-connectivity nodes were more likely to
  answer to the queries
• Topology was static so nodes were not
  disappearing or moving
• Querier and the queried resource were selected
  randomly and 10 different queries were used in
  each generation (this was found to be enough to
  determine the overall performance of the neural
  network)
• Requirements for the fitness function were
• The algorithm should locate half of the available
  resources for every query (each obtained resource
  increased fitness 50 points)
• The algorithm should use as minimal number of
  packets as possible (each used packet decreased
  fitness by 1 point)
• The algorithm should always stop (stop limit for
  number of packets was set to 300)

9
Research Environment
10
Research Cases - Fitness

• Fitness value determines how good the neural
  network is compared to others
• Even smallest and simplest neural networks manage
  to have fitness value over 10000
• Fitness value is calculated for poor NeuroSearch
  as following
• Fitness 50 replies packets 50239
  1290 10660

Note Because of bug Steiner tree does not locate
half of replies and thus gets a lower fitness
than HDS
11
Research Cases Random Weights

• 10 million new neural networks were randomly
  generated
• It seems that over 16000 fitness values cannot be
  obtained purely by guessing and therefore we need
  optimization method

12
Research Cases - Inputs

• Different inputs were tested individually and
  together to get a feeling what inputs are
  important

Using Hops we can forexample design rules I
have travelled 4 hops,I will not send further
13
Target node contains 10 neighbors,I will send
further
Target node contains the most number
ofneighbors compared to all my neighbors,I will
not send further
14
I have 7 neighbors,I will send further
I have received this query earlier,I will not
send further
15
The results indicate that using only one
topological information is more efficient than
combining it with other topological information
(the explanation for this behavior is still
unclear)
16
Also the results indicate that using only one
query related information is more efficient than
combining it with other query related information
(the explanation for this behavior is also
unclear)
17
Research Cases - Resources

• The needed percentage of resources was varied and
  the results compared to other local search
  algorithms (Highest Degree Search and
  Breadth-First Search) and to near-optimal search
  trees (Steiner)

Note Breadth-FirstSearch curve needsto be
halved becausethe percentage wascalculated to
half ofresources and not allavailable resources
18
Research Cases - Queriers

• The effect of lowering the amount of queriers per
  generation to calculate fitness value of neural
  network was examined
• It was found that the number ofqueriers can be
  dropped from 50 to 10 and still we get reliable
  fitness values? Speeds up the
  optimizationprocess significantly

19
Research Cases Brain Size

• The amount of neurons on first and second layer
  were varied
• It was found that there exists many different
  kind of NeuroSearch algorithms

20
Research Cases Brain Size

• Also optimization of larger neural networks takes
  more time

21
Research Cases Brain Size

• And there exists an interesting breadth-first
  search vs. depth-first search dilemma where
• smaller networks obtain best fitness values with
  breadth-first search strategy,
• medium-sized networks obtain best fitness values
  with depth-first search strategy and
• large-sized networks obtain best fitness values
  with breadth-first search strategy
• In overall it seems that best fitness 18091.0 can
  be obtained with breadth-first strategy using 5
  hops with neuron size of 2510 (25 on the first
  hidden layer and 10 on the second hidden layer)

22
2010 had the greatest average hops value What
happens if the number of neuronson 2nd hidden
layer is increased? Willthe average number of
hops decrease?
2510 had the greatest fitness value Would more
generations than 100.000 increase the fitness
when 1st hiddenlayer contains more than 25
neurons?
23
Summary and Future

• The main findings of the thesis were that
• Population size of 24 and query amount of 10 are
  sufficient
• Optimization algorithm needs to be used, because
  randomly guessing neural network weights does not
  give good results
• Individual inputs give better results than
  combination of two inputs (however the best
  fitnesses can be obtained by using all 7 inputs)
• By choosing specific set of inputs NeuroSearch
  may imitate any existing search algorithm or it
  may behavior as combination of any of those
• Optimal algorithm (Steiner) has efficiency of
  99, whereas the best known local search
  algorithm (HDS) achieves 33 and NeuroSearch 25
• Breadth-first search vs. Depth-first search
  dilemma exists, but no good explanation can be
  given yet

24
Summary and Future

• In addition to the problems shown this far, for
  the future work of NeuroSearch it is suggested
  that
• More inputs would be designed such that they
  provide useful information e.g., the number of
  received replies, inputs used by Highest-Degree
  Search algorithm, inputs that define how many
  forwarding decisions have already been done in
  the current decision round and how many are still
  left
• Probability based output instead of threshold
  function could also be tested
• The correct neural network architecture and the
  size of population could be dynamically adjusted
  during evolution to find an optimal structure
  more easily