GraMi

Abstract

Mining frequent subgraphs is an important operation on graphs; it is defined as finding all subgraphs that appear frequently in a database according to a given frequency threshold. Most existing work assumes a database of many small graphs, but modern applications, such as social networks, citation graphs, or proteinprotein interactions in bioinformatics, are modeled as a single large graph. In this paper we present GRAMI, a novel framework for frequent subgraph mining in a single large graph. GRAMI undertakes a novel approach that only finds the minimal set of instances to satisfy the frequency threshold and avoids the costly enumeration of all instances required by previous approaches. We accompany our approach with a heuristic and optimizations that significantly improve performance. Additionally, we present an extension of GRAMI that mines frequent patterns. Compared to subgraphs, patterns offer a more powerful version of matching that captures transitive interactions between graph nodes (like friend of a friend) which are very common in modern applications. Finally, we present CGRAMI, a version supporting structural and semantic constraints, and AGRAMI, an approximate version producing results with no false positives. Our experiments on real data demonstrate that our framework is up to 2 orders of magnitude faster and discovers more interesting patterns than existing approaches.

Grasping frequent subgraph mining for bioinformatics applications

“…As the input graph gets larger, so does the number of potential subgraphs of interests and for a lower frequency threshold, the number of patterns potentially explodes. Recently, there have been solutions that mine for frequent subgraphs in large graphs at low frequency thresholds [70]. There is also a question of the right interestingness measure, i.e.…”

An Improved Pattern Mining Technique for Graph Pattern Analysis Using a Novel Behavior of Artificial Bee Colony Algorithm

“…The graph having such anti monotonic nature is of prime importance as it provides various methods without avoiding a situation. There are several anti-monotone metrics developed in literature (Talukder and Zaki, 2016;Elseidy et al, 2014). Definition 2: There are two directed graphs such as G: Y= (SY, TY) and Z = (SZ, TZ) where ⌈ ≤ ⌉, the problem of SI represented by SI (Y, Z) is to determine an injective function : → that reduces the value of fitness function (f).…”

“…The problem of FSM is categorized into two phases, such as determining frequent patterns in either (a) graphical database having multiple inputs (Protein interaction or chemical compounds) or (b) large graph having single input (e.g., social media,) (Elseidy et al, 2014). The main task of FSM is to calculate all the subgraphs having support or frequency exceeds the minimum frequency threshold.…”

Frequent Subgraph Mining Based Collaboration Pattern Analysis for Wikipedia

“…Currently, frequent subgraph mining technologies are rather mature and there are many algorithms for frequent subgraph mining such as CloseGraph, FSG, gSpan, GRAMI [10,22]. Different frequent subgraph mining algorithms are applicable for different types of graphs and also different in performance.…”