Abstract
Vertex-centric computation introduced in Part I has two weaknesses. (1) The model may suffer from poor performance in some real graphs, such as those with a large diameter. This chapter describes a novel block-centric computation model that overcomes the weaknesses of vertex-centric computation, and that significantly speeds up iterative graph computation. We also include a hands-on tutorial on how to get started with Blogel, a state-of-the-art block-centric system, which may be skipped if you are only interested in surveying existing big graph analytics systems. (2) Vertex-centric (and even block-centric) API is not suitable for some important graph mining problems such as mining subgraphs. The next chapter will describe a novel subgraph-centric computation model that makes it easy to write programs for efficient large-scale subgraph mining.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
You may also search “Blogel” in Google.
- 3.
- 4.
- 5.
- 6.
- 7.
That is why a user needs to know the structure of BPartVertex and BPartValue.
- 8.
- 9.
We copy the line first, since strtok(.) replaces the token splitters with ‘∖0’ and thus changes the line. We use strtok(.) since C++’s stringstream needs to copy the line into its internal buffer for parsing, which incurs additional overhead.
- 10.
- 11.
- 12.
- 13.
References
G. Karypis and V. Kumar. Multilevel k-way partitioning scheme for irregular graphs. J. Parallel Distrib. Comput., 48(1):96–129, 1998.
S. Salihoglu and J. Widom. Optimizing graph algorithms on pregel-like systems. PVLDB, 7(7):577–588, 2014.
Y. Tian, A. Balmin, S. A. Corsten, S. Tatikonda, and J. McPherson. From “think like a vertex” to “think like a graph”. PVLDB, 7(3):193–204, 2013.
W. Xie, G. Wang, D. Bindel, A. J. Demers, and J. Gehrke. Fast iterative graph computation with block updates. PVLDB, 6(14):2014–2025, 2013.
D. Yan, J. Cheng, Y. Lu, and W. Ng. Blogel: A block-centric framework for distributed computation on real-world graphs. PVLDB, 7(14):1981–1992, 2014.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2017 The Author(s)
About this chapter
Cite this chapter
Yan, D., Tian, Y., Cheng, J. (2017). Block-Centric Computation. In: Systems for Big Graph Analytics. SpringerBriefs in Computer Science. Springer, Cham. https://doi.org/10.1007/978-3-319-58217-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-58217-7_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-58216-0
Online ISBN: 978-3-319-58217-7
eBook Packages: Computer ScienceComputer Science (R0)