Frequent Sub-Graph Mining Using Missing Items

Document Type : Primary Research paper


Assistant Professor & Head PG & Research Department of computer science Jairams Arts and Science College (affiliated to Bharathidasan University) karur.3


One of the most sought after research area is graph mining and extracting the hidden patterns from the graphs is a tedious task and that too unearthing meaningful patterns is a challenging process and this paper focus on discovering useful patterns from the graph data using a new algorithm named “Frequent Subgraph miningusing missing items – FSMM algorithm” is employing some simple mechanisms to evade the consumption of excess runtime and memory allocation. The graphs are initially converted into textual transaction data where only the missing items are considered and this is transformed into binary representations to discover the frequent sub-graphs. The results are experimentally evaluated with state of the art existing algorithms to prove the performance of the proposed algorithm.