project final presentation · google france matchs afril matchs afrique matchs africain en direct...

Post on 19-Jun-2020

1 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

TRANSCRIPT

Community-BasedLabelling

SocialNetworks

• Relatedusersandcontents• Analyzeinfluentialpeopleandcommunities

WebGraphs

• Giveranktowebpages

Real World Networks

BFS or Dijkstra’s algorithm

E.g. Naïve Pair-wise Labelling (Index)

a b c d e …

a 1 1 1 1 1

b 1 2 3 4 5

c 1 3 6 10 15

d 1 4 10 20 35

e 1 5 15 35 70

… …

Fact - real world networks have inborn communities

Why not index for each community?

ReasonableIndexSizeComparativeQueryTime

2-Layer Framework

1st Layer– Communities

2nd Layer– MetaGraph

How it works

Dist(a, b) =Dist(a, bond(a)) + Dist(b, bond(b)) + Dist(bond(a), bond(b))

(fromCommunity labels)

(fromMeta-graph label)

Communities

Meta-graph

TOOLS & DATASETS

Stanford Network Analysis PlatformS.N.A.P

• Amazon• DBLP• Emails

Datasets• Labelling for each community

C++

• Snap.py connects with SNAP• Community detection

Python

Q&A

Contact:

Hao Zhang

u5319850@anu.edu.au

www.zengineerhao.com

top related