Large graph visualizations using a distributed computing platform

Big Data analytics is recognized as one of the major issues in our current information society, and raises several challenges and opportunities in many fields, including economy and finance, e-commerce, public health and administration, national security, and scientific research. The use of visualization techniques to make sense of large volumes of information is an essential ingredient, especially for the analysis of complex interrelated data, which are represented as graphs. The growing availability of powerful and inexpensive cloud computing services naturally motivates the study of distributed graph visualization algorithms, able to scale to the size of large graphs. We study the problem of designing a distributed visualization algorithm that must be simple to implement and whose computing infrastructure does not require major hardware or software investments. We design, implement, and experiment a force-directed algorithm in Giraph, a popular open source framework for distributed computing, based on a vertex-centric design paradigm. The algorithm is tested both on real and artificial graphs with up to one million edges. The experiments show the scalability and effectiveness of our technique when compared to a centralized implementation of the same force-directed model. Graphs with about one million edges can be drawn in a few minutes, by spending about 1 USD per drawing with a cloud computing infrastructure of Amazon.