Evaluating Complex Queries on Streaming Graphs

Abstract

In this paper, we study the problem of evaluating persistent queries over streaming graphs in a principled fashion. These queries need to be evaluated over unbounded and very high speed graph streams. We define a streaming graph model and a streaming graph query model incorporating navigational queries, subgraph queries and paths as first-class citizens. To support this full-fledged query model we develop a streaming graph algebra that describes the precise semantics of persistent graph queries with their complex constructs. We present transformation rules and describe query formulation and plan generation for persistent graph queries over streaming graphs. Our implementation of a streaming graph query processor based on the dataflow computational model shows the feasibility of our approach and allows us to gauge the high performance gains obtained for query processing over streaming graphs.

A Reachability Index for Recursive Label-Concatenated Graph Queries

“…Optimal solutions can be used for subclasses of regular expressions, e.g., a matrix-based method [20] for the case without recursive concatenation, and a B+tree index for the case with a bounded path length (non-recursive path constraints) [22] and a fixed path pattern [32]. There also exist in the literature partial evaluation for distributed graphs [21], and incremental approaches for streaming graphs [39,40]. Compared to all these works, we focus on designing an index-based solution to handle reachability queries with path constraints of recursive concatenation over a static and centralized graph under the arbitrary path semantics, which is an open challenge in the design of reachability indexes.…”