Upload
anika-browning
View
36
Download
1
Embed Size (px)
DESCRIPTION
SCAN: A Structural Clustering Algorithm for Networks. Xiaowei Xu, Nurcan Yuruk, Zhidan Feng, and Thomas Schweiger KDD’07. An Introduction to DBSCAN. DBSCAN is a density-based algorithm. Density = number of points within a specified radius (Eps) - PowerPoint PPT Presentation
Citation preview
SCAN: A Structural Clustering Algorithm for Networks
Xiaowei Xu, Nurcan Yuruk, Zhidan Feng, and Thomas Schweiger
KDD’07
An Introduction to DBSCAN
DBSCAN is a density-based algorithm.– Density = number of points within a specified radius (Eps)
– A point is a core point if it has more than a specified number of points (MinPts) within Eps
These are points that are at the interior of a cluster
– A border point has fewer than MinPts within Eps, but is in the neighborhood of a core point
– A noise point is any point that is not a core point or a border point.
DBSCAN: Core, Border, and Noise Points
DBSCAN Algorithm
Eliminate noise points Perform clustering on the remaining points
DBSCAN: Core, Border and Noise Points
Original Points Point types: core, border and noise
Eps = 10, MinPts = 4
When DBSCAN Works Well
Original Points Clusters
• Resistant to Noise
• Can handle clusters of different shapes and sizes
DBSCAN: Determining EPS and MinPts
Idea is that for points in a cluster, their kth nearest neighbors are at roughly the same distance
Noise points have the kth nearest neighbor at farther distance
So, plot sorted distance of every point to its kth nearest neighbor
Network Clustering Problem
Networks made up of the mutual relationships of data elements usually have an underlying structure. Because relationships are complex, it is difficult to discover these structures. How can the structure be made clear?
Stated another way, given simply information of who associates with whom, could one identify clusters of individuals with common interests or special relationships (families, cliques, terrorist cells).
An Example of Networks
How many clusters? What size should they
be? What is the best
partitioning? Should some points
be differentiated?
A Social Network Model
Individuals in a tight social group, or clique, know many of the same people, regardless of the size of the group.
Individuals who are hubs know many people in different groups but belong to no single group. Politicians, for example bridge multiple groups.
Individuals who are outliers reside at the margins of society. Hermits, for example, know few people and belong to no group.
The Neighborhood of a Vertex
v
Define () as the immediate neighborhood of a vertex (i.e. the set of people that an individual knows ).
Structure Similarity
The desired features tend to be captured by a measure we call Structural Similarity
Structural similarity is large for members of a clique and small for hubs and outliers.
|)(||)(|
|)()(|),(
wv
wvwv
Structural Connectivity [1]
-Neighborhood: Core: Direct structure reachable:
Structure reachable: transitive closure of direct structure reachability
Structure connected:
}),(|)({)( wvvwvN
|)(|)(, vNvCORE
)()(),( ,, vNwvCOREwvDirRECH
),(),(:),( ,,, wuRECHvuRECHVuwvCONNECT
[1] M. Ester, H. P. Kriegel, J. Sander, & X. Xu (KDD'97)
Structure-Connected Clusters
Structure-connected cluster C– Connectivity:
– Maximality:
Hubs:– Not belong to any cluster– Bridge to many clusters
Outliers:– Not belong to any cluster– Connect to less clusters
),(:, , wvCONNECTCwv
CwwvREACHCvVwv ),(:, ,
hub
outlier
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
0.63
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
0.75
0.67
0.82
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
0.67
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
0.73
0.730.73
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
0.51
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
0.68
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
0.51
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7 0.51
0.51
0.68
13
9
10
11
7
812
6
4
0
15
2
3
Algorithm
= 2 = 0.7
Running Time
Running time = O(|E|) For sparse networks = O(|V|)
[2] A. Clauset, M. E. J. Newman, & C. Moore, Phys. Rev. E 70, 066111 (2004).
Conclusion
We propose a novel network clustering algorithm:
– It is fast O(|E|), for scale free networks: O(|V|)
– It can find clusters, as well as hubs and outliers