Subgraph Querying with Parallel Use of Query Rewritings and Alternative Algorithms

Subgraph queries are central to graph analytics and graph. We analyze this problem and present key novel discoveries and observations on the nature of the problem which across query sizes, datasets, and top-performing algorithms. Firstly, we show that algorithms (for both the decision and matching versions of the problem) suffer from queries, which dominate query workload times. As research caps query times not reporting results for exceeding the cap, this can lead to erroneous conclusions of the methods' relative performance. Secondly, we and show the dramatic effect that isomorphic graph can have on query times. Thirdly, we show that each query, isomorphic queries based on proposed query can introduce large performance benefits. Fourthly, straggler queries are largely algorithm-specific: many queries to one algorithm can be executed efficiently by another. Finally, the above discoveries naturally to the derivation of a novel framework for subgraph processing. The central idea is to employ parallelism a novel way, whereby parallel matching/decision attempts initiated, each using a query rewriting and/or an alternate algorithm. The framework is shown to be highly beneficial across algorithms and datasets.