TY - GEN
T1 - Generating evolving property graphs with attribute-aware preferential attachment
AU - Aghasadeghi, A. Amir
AU - Stoyanovich, J. Julia
N1 - Publisher Copyright:
© 2018 ACM.
PY - 2018/6/15
Y1 - 2018/6/15
N2 - In recent years there has been significant interest in evolutionary analysis of large-scale networks. Researchers study network evolution rate and mechanisms, the impact of specific events on evolution, and spatial and spatio-temporal patterns. To support data scientists who are studying network evolution, there is a need to develop scalable and generalizable systems. Tangible systems progress in turn depends on the availability of standardized datasets on which performance can be tested. In this work, we make progress towards a data generator for evolving property graphs, which represent evolution of graph topology, and of vertex and edge attributes. We propose an attribute-based model of preferential attachment, and instantiate this model on a co-authorship network derived from DBLP, with attributes representing publication venues of the authors. We show that this attribute-based model predicts which edges are created more accurately than a structure-only model. Finally, we demonstrate that synthetic graphs are indeed useful for evaluating performance of evolving graph query primitives.
AB - In recent years there has been significant interest in evolutionary analysis of large-scale networks. Researchers study network evolution rate and mechanisms, the impact of specific events on evolution, and spatial and spatio-temporal patterns. To support data scientists who are studying network evolution, there is a need to develop scalable and generalizable systems. Tangible systems progress in turn depends on the availability of standardized datasets on which performance can be tested. In this work, we make progress towards a data generator for evolving property graphs, which represent evolution of graph topology, and of vertex and edge attributes. We propose an attribute-based model of preferential attachment, and instantiate this model on a co-authorship network derived from DBLP, with attributes representing publication venues of the authors. We show that this attribute-based model predicts which edges are created more accurately than a structure-only model. Finally, we demonstrate that synthetic graphs are indeed useful for evaluating performance of evolving graph query primitives.
UR - http://www.scopus.com/inward/record.url?scp=85063582985&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063582985&partnerID=8YFLogxK
U2 - 10.1145/3209950.3209954
DO - 10.1145/3209950.3209954
M3 - Conference contribution
AN - SCOPUS:85063582985
T3 - Proceedings of the Workshop on Testing Database Systems, DBTest 2018
BT - Proceedings of the Workshop on Testing Database Systems, DBTest 2018
PB - Association for Computing Machinery, Inc
T2 - 2018 Workshop on Testing Database Systems, DBTest 2018
Y2 - 15 June 2018
ER -