Title: A%20Binary%20Linear%20Programming%20Formulation%20of%20the%20Graph%20Edit%20Distance
1A Binary Linear Programming Formulation of the
Graph Edit Distance
Authors Derek Justice Alfred Hero (PAMI 2006)
Presented by Shihao Ji Duke University Machine
Learning Group July 17, 2006
2Outline
- Introduction to Graph Matching
- Proposed Method (binary linear program)
- Experimental Results (chemical graph matching)
3Graph Matching
- Objective matching a sample input graph to a
database of known prototype graphs.
4Graph Matching (contd)
- A real example face identification
5Graph Matching (contd)
Key issues (1) representative graph generation
(a) facial graph representations
(b) chemical graphs
6Graph Matching (contd)
Key issues (2) graph distance metrics
- Maximum Common Subgraph (MCS)
- Graph Edit Distance (GED)
- Enumeration procedures (for small
graphs) - Probabilistic models (MAP
estimates) - Binary Linear Programming (BLP)
7Graph Edit Distance
- Basic idea define graph edit operations (such as
insertion or deletion or relabeling of a vertex)
along with costs associated with each operation. - The GED between two graphs is the cost associated
with the least costly series of edit operations
needed to make the two graph isomorphic. - Key issues
- how to find the least costly series
of edit operations? - how to define edit costs?
8Graph Edit Distance (contd)
- How to compute the distance between G0 and G1?
- Edit Grid
-
9Graph Edit Distance (contd)
- Isomorphisms of G0 on the edit grid
- State Vectors
-
standard placement
10Graph Edit Distance (Contd)
- Definition (if the cost function c is a metric)
- Objective function binary linear program
(NP-hard!!!)
11Graph Edit Distance (contd)
- Lower bound linear program (polynomial time)
- Upper bound assignment problem (polynomial time)
12Edit Cost Selection
- Goal suppose there is a set of prototype graphs
Gi i1,,N and we classify a sample graph G0 by
a nearest neighbor classifier in the metric space
defined by the graph edit distance. - Prior informaiton the prototypes should be
roughly uniformly distributed in the metric space
of graphs. - Why it minimizes the worst case classification
error since it equalizes the probability of error
under a nearest neighbor classifier.
13Edit Cost Selection (contd)
- Objective minimize the variance of pairwise NN
distances - Define unit cost function, i.e., c(0,1)1,
c(a,b)1, c(a,a)0 - Solve the BLP (with unit cost) and find the NN
pair - Construct Hk,i the number of ith edit operation
for the kth NN pair -
- Objective function (convex optimization)
14Experimental Results
- Chemical Graph Recognition
15Experiments Results (contd)
(a) original graph
1. edge edit 2. vertex deletion 3. vertex
insertion 4. vertex relabeling 5. random
(b) example perturbed graphs
16Experiments Results (contd)
17Experiments Results (contd)
18Conclusion
- Present a binary linear programming formulation
of the graph edit distance - Offer a minimum variance method for choosing a
cost metric - Demonstrate the utility of the new method in the
context of a chemical graph recognition.