With graphs being subject to dynamism, with updates arriving periodically or continuously (i.e., the latter called graph streaming), the challenge faced by these platforms is increased as the continuously arriving updates to the graph may require, without better knowledge, the entire graph to be (re-)processed by some algorithm in order to provide updated results to users’ and applications’ queries to the graph. Processing larger and larger graphs in a time and cost-effective way, even when static/immutable, requires distributed computing infrastructures, and distributed data processing platforms such as Hadoop, Spark and Flink have been adapted or extended to carry out graph processing (e.g., GraphX/ Spark and Gelly/ Flink). The domains of application are vast and varied with graphs being used to represent and process the structure and contents of the World Wide Web, structures in chemistry, knowledge graphs, social networks, machine learning, analytics, epidemiology, transportation and network security, to name a few. Graph-based data is increasingly relevant in big-data storage and processing, as it allows richer semantics in data and knowledge representation, as well as enabling the application of powerful algorithms with graph processing. We have found V eilG raph implementation on Flink to be scalable, as it is able to improve performance up to 10X speedups, when more resources are employed (16 workers), achieving better speedups with scale for larger graphs, which are the most relevant. yielding a reduction of up to 66% in latency). In some cases, depending on the workload, speedups against Apache Flink reach up to 3.0x (i.e. without any summarization or approximation techniques). Our experiments show that V eilG raph can often reduce latency closely to half (speedup of 2.0×), while achieving result quality above 95% when compared to results of the traditional version of PageRank executing in Apache Flink with Gelly (i.e. We analyse the feasibility of our model and evaluate it with the case study of the PageRank algorithm, the most famous measure of vertex centrality used to rank websites in search engine results. We showcase an innovative model for approximate graph processing implemented in Apache Flink. Herein we present V eilG raph, through which we conducted our research.
#1 hop vertex cover update
The relationships between the frequency of graph algorithm execution, the update rate and the type of update play an important role in applying these techniques. In the scope of stream processing over graphs, we research the trade-offs between result accuracy and the speedup of approximate computation techniques.
With the advent of greater volumes of information and the need for continuously updated results under temporal constraints, it is necessary to explore alternative approaches that further enable performance improvements. Graphs are found in a plethora of domains, including online social networks, the World Wide Web and the study of epidemics, to name a few.
0 kommentar(er)
