2017 · 12 citations · 17 references
ComputingComputer ScienceData VisualizationDatabasesGraph VisualizationGraph AlgorithmsGraph AnalyticsGraph MiningGraph ExplorationGraph GenerationGraph ProcessingVisual Analytics For GraphsVisual Graph Analytics
Graph querying and analytics are becoming an increasingly important component of the arsenal of tools for extracting different kinds of insights from data. Despite an immense amount of work on those topics, graphs are largely still handled in an ad hoc manner, in part because most data continues to reside in relational-like data management systems, and because graph analytics/querying typically forms a small portion of the overall analysis pipelines. In this paper we describe an end-to-end graph analysis framework, called GraphGen, that sits atop an RDBMS, and supports graph querying/analytics through: (a) defining graphs as transformations over underlying relational datasets (as Graph-Views) and (b) specifying queries or analytics on those graphs using either a high-level language or Java programs against a simple graph API. Although conceptually simple, GraphGen acts as an abstraction/independence layer that opens up many opportunities for adaptively optimizing graph analysis workflows, since the system can decide where to execute tasks on a per-task basis (in database or outside), how much of the graph to materialize in memory, and what types of in-memory representations to use (especially critical when the graphs are larger than the input datasets, as is often the case). At the same time, by providing the ability to write arbitrary programs against the graphs, GraphGen removes a major expressivity limitation of many existing graph analysis systems, which only support limited programming frameworks. We describe the GraphGen DSL, loosely based on Datalog, that includes both graph specification and in-line analysis capabilities. We then discuss many optimization challenges in building GraphGen, that we are currently working on addressing.
17
Julian Shun, Guy E. Blelloch · 2013 · 808 citations
Scalability! but at what cost?
Frank McSherry, Michael Isard, Derek G. Murray · 2015 · 218 citations
Julian Shun, Guy E. Blelloch · ACM SIGPLAN Notices · 2013 · 218 citations
Jiwon Seo, Jongsoo Park, Jaeho Shin et al. · Proceedings of the VLDB Endowment · 2013 · 106 citations