Efficient Large-Scale Multi-graph Similarity Search Using MapReduce
Lists
Only you see this
Abstract
A multi-graph is a set consisting of multiple graphs. Multi-graph similarity search aims to find the multi-graphs similar to the query multi-graphs from the multi-graph datasets. It plays important role in a wide range of application fields, such as finding similar drugs, searching similar molecule groups and so on. However, existing algorithms of multi-graph similarity search are memory-based algorithms, which are not suitable for the large amount of multi-graph scenarios. In this paper, we propose a parallel algorithm based on the MapReduce programming model to solve the problem of the large-scale multi-graph similarity search. Our proposed algorithm consists of two MapReduce jobs, one for indexing and the other for filtering and validation. Specially, we adapt the localization strategy to further improve the performance of our algorithm, which not only reduces the communication cost, but also mitigates the load imbalance. Extensive experimental results show that our algorithm is effective and efficient.
BibTeX
@inproceedings{pang2019efficient,
author = {Jun Pang and Minghe Yu and Yu Gu},
title = {{Efficient Large-Scale Multi-graph Similarity Search Using MapReduce}},
booktitle = {WISA},
year = {2019},
doi = {10.1007/978-3-030-30952-7\_23},
}Loading related content...