CommonGraph: Graph Analytics on Evolving Data

Afarin, Mahbod; Gao, Chao; Rahman, Shafiur; Abu-Ghazaleh, Nael; Gupta, Rajiv

doi:10.1145/3575693.3575713

Cited by 9 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graphs are often dynamic, with edges and vertices being added or removed over time. There are two broad classes of analyses on dynamic graphs: (1) Streaming graph analytics: where results of a query are continuously updated as the graph continues to change because updates to it stream in over time. Typically incremental algorithms are employed to update query results in response to graph changes [2][3][4][5]; and (2) Evolving graph analytics: where multiple snapshots of the graph are available and an evolving graph query seeks to track a graph property over a time window by computing its value for different snapshots within the time window.…”

mentioning

confidence: 99%

See 1 more Smart Citation

CommonGraph: Graph Analytics on Evolving Data (Abstract)

Afarin

Gao

Rahman

et al. 2023

Proceedings of the 2023 ACM Workshop on Highlights of Parallel Computing

Self Cite

View full text Add to dashboard Cite

We consider the problem of graph analytics on evolving graphs. In this scenario, a query typically needs to be applied to different snapshots of the graph over an extended time window. We propose CommonGraph, an approach for efficient processing of queries on evolving graphs. We first observe that edge deletions are significantly more expensive than addition operations. CommonGraph converts all deletions to additions by finding a common graph that exists across all snapshots. After computing the query on this graph, to reach any snapshot, we simply need to add the missing edges and incrementally update the query results. CommonGraph also allows sharing of common additions among snapshots that require them, and breaks the sequential dependency inherent in the traditional streaming approach where snapshots are processed in sequence, enabling additional opportunities for parallelism. We incorporate the CommonGraph approach by extending the KickStarter streaming framework. CommonGraph achieves 1.38×-8.17× improvement in performance over Kickstarter across multiple benchmarks.

show abstract

mentioning

confidence: 99%

“…Finally, Kickstarter's cost of graph mutation is greater for deletions than additions. This work is an abstracted version of the CommonGraph paper [1].…”

mentioning

confidence: 99%