Efficient Mining of Top-k Breaker Emerging Subgraph Patterns from Graph Datasets

This paper introduces a new type of discriminative subgraph pattern called breaker emerging subgraph pattern by introducing three constraints and two new concepts: base and breaker. A breaker emerging subgraph pattern consists of three subpatterns: a constrained emerging subgraph pattern, a set of bases and a set of breakers. An efficient approach is proposed for the discovery of top-k breaker emerging subgraph patterns from graph datasets. Experimental results show that the approach is capable of efficiently discovering top-k breaker emerging subgraph patterns from given datasets, is more efficient than two previous methods for mining discriminative subgraph patterns. The discovered top-k breaker emerging subgraph patterns are more informative, more discriminative, more accurate and more compact than the minimal distinguishing subgraph patterns. The top-k breaker emerging patterns are more useful for substructure analysis, such as molecular fragment analysis.