Abstract
In this paper we show how graph structure can be used to significantly reduce the computational bottleneck of the Breadth First Search algorithm (the foundation of many graph traversal techniques) for social networks. In particular, we address parallel implementations where the bottleneck is the number of messages between processors emitted at the peak iteration. First, we derive an expression for the expected degree distribution of vertices in the frontier of the algorithm which is shown to be highly skewed. Subsequently, we derive an expression for the expected message along an edge in a particular iteration. This skew suggests a weighted, iteration based, partition would be advantageous. Empirical simulations show that such partitions can reduce the message overhead in the order of 20 % for graphs with common social network structural properties. These results have implications for graph processing in multiprocessor and distributed computing environments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A good estimate of the number of vertices expected in each iteration of BFS can be obtained from a single graph traversals.
- 2.
Here we use the YouTube friendship graph as an example: the power law exponent = \(-2\) and \(t_\tau \) = \(\{0.0006,0.02,0.19,0.53,0.81,0.93,0.97,0.99,1\}\), the results are similar for the other graphs we examined.
- 3.
- 4.
- 5.
Alternatively one could insert a concentrated degree distribution for \(p_k\) in (4) and see that \(\pi _{k}^{tau} = p_k\).
References
Merrill, D., Garland, M., Grimshaw, A.: Scalable GPU graph traversal. In: 17th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, vol. 47, no. 8, pp. 117–128, Feb 2012
Buluç, A., Madduri, K.: Graph partitioning for scalable distributed graph computations. Contemp. Math. 588, 83 (2013)
Krzywdzinski, K., Kowalski, D.: On the complexity of distributed BFS in ad hoc networks with spontaneous wake-up. Discrete Math. Theor. Comput. Sci. 15(3), 101–118 (2013)
Shang, H., Kitsuregawa, M.: Efficient breadth-first search on large graphs with skewed degree distributions. In: Joint 2013 EDBT/ICDT Conferences, EDBT’13 Proceedings, Genoa, Italy, March 18–22, 2013, pp. 311–322 (2013)
Chen, R., Shi, J., Chen, Y., Chen, H.: PowerLyra: differentiated graph computation and partitioning on skewed graphs. In: Proceedings of the Tenth European Conference on Computer Systems, EuroSys’15, pp. 1:1–1:15. ACM, New York, NY, USA (2015)
Fu, Z., Dasari, H., Berzins, M., Thompson, B.: Parallel breadth first search on GPU clusters. SCI Institute, University of Utah, SCI Technical report UUSCI-2014-002 (2014)
Wang, Y., Owens, J.D.: Large-scale graph processing algorithms on the GPU. UC Davis, Technical report (2013)
Buluç, A., Beamer, S., Madduri, K., Asanović, K., Patterson, D.: Distributed-memory breadth-first search on massive graphs. In: Bader, D. (ed.) Parallel Graph Algorithms. CRC Press, Taylor-Francis (2016). https://www.crcpress.com/Parallel-Graph-Algorithms/Bader/9781466573260
Luo, L., Wong, M., Hwu, W.-M.: An effective GPU implementation of breadth-first search. Proceedings of the 47th Design Automation Conference. DAC’10, pp. 52–55. ACM, New York, NY, USA (2010)
Bisson, M., Bernaschi, M., Mastrostefano, E.: Parallel distributed breadth first search on the Kepler architecture (2014). arXiv:1408.1605
Buluç, A., Madduri, K.: Parallel breadth-first search on distributed memory systems. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, SC’11, pp. 65:1–65:12. ACM, New York, NY, USA (2011)
Yuan, L., Ding, C., Tefankovic, D., Zhang, Y.: Modeling the locality in graph traversals. In: ICPP. IEEE Computer Society, pp. 138–147 (2012)
Buluç, A., Meyerhenke, H., Safro, I., Sanders, P., Schulz, C.: Recent advances in graph partitioning (2013). arXiv:1311.3144
Akiba, T., Iwata, Y., Yoshida, Y.: Fast exact shortest-path distance queries on large networks by pruned landmark labeling. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, SIGMOD’13, pp. 349–360. ACM, New York, NY, USA (2013). http://doi.acm.org/10.1145/2463676.2465315
Idwan, S., Etaiwi, W.: Computing breadth first search in large graph using hmetis partitioning. Eur. J. Sci. Res. 29(2), 215–221 (2009)
Abou-Rjeili, A., Karypis, G.: Multilevel algorithms for partitioning power-law graphs. Proceedings of the 20th International Conference on Parallel and Distributed Processing. IPDPS’06, pp. 124–124. IEEE Computer Society, Washington, DC, USA (2006)
Hong, S., Kim, S.K., Oguntebi, T., Olukotun, K.: Accelerating CUDA graph algorithms at maximum warp. SIGPLAN Not. 46(8), 267–276 (2011)
Then, M., Kaufmann, M., Chirigati, F., Hoang-Vu, T.-A., Pham, K., Kemper, A., Neumann, T., Vo, H.T.: The more the merrier: Efficient multi-source graph traversal. In: Proceedings of VLDB Endow., vol. 8, no. 4, pp. 449–460 (2014). http://dx.doi.org/10.14778/2735496.2735507
Karypis, G., Kumar, V.: Multilevel k-way partitioning scheme for irregular graphs. J. Parallel Distrib. Comput. 48, 96–129 (1998)
Kurant, M., Markopoulou, A., Thiran, P.: On the bias of BFS (breadth first search). In: 22nd International Teletraffic Congress (ITC), pp. 1–8 (2010)
Mahadevan, P., Hubble, C., Krioukov, D., Huffaker, B., Vahdat, A.: Orbis: rescaling degree correlations to generate annotated Internet topologies. SIGCOMM Comput. Commun. Rev. 37(4), 325–336 (2007)
Achlioptas, D., Clauset, A., Kempe, D., Moore, C.: On the bias of traceroute sampling: or, power-law degree distributions in regular graphs. In: STOC’05: Proceedings of the 37th Annual ACM Symposium on Theory of Computing, Baltimore, MD, May 2005, pp. 694–703
Fay, D., Haddadi, H., Uhlig, S., Kilmartin, L., Moore, A.W., Kunegis, J., Iliofotou, M.: Discriminating graphs through spectral projections. Comput. Netw. 55(15), 3458–3468 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Fay, D. (2016). Predictive Partitioning for Efficient BFS Traversal in Social Networks. In: Cherifi, H., Gonçalves, B., Menezes, R., Sinatra, R. (eds) Complex Networks VII. Studies in Computational Intelligence, vol 644. Springer, Cham. https://doi.org/10.1007/978-3-319-30569-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-30569-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-30568-4
Online ISBN: 978-3-319-30569-1
eBook Packages: EngineeringEngineering (R0)