An interval-centric model for distributed computing over temporal graphs

Gandhi, S and Simmhan, Y (2020) An interval-centric model for distributed computing over temporal graphs. In: 36th IEEE International Conference on Data Engineering, ICDE 2020, 20 April 2020through 24 April 2020, Dallas, pp. 1129-1140.

PDF An_Int_cen_Mod_for_Dis_Com_ove_Tem_Gra_pdf_2024 - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Algorithms for temporal property graphs may be time-dependent (TD), navigating the structure and time concurrently, or time-independent (TI), operating separately on different snapshots. Currently, there is no unified and scalable programming abstraction to design TI and TD algorithms over large temporal graphs. We propose an interval-centric computing model (ICM) for distributed and iterative processing of temporal graphs, where a vertex's time-interval is a unit of data-parallel computation. It introduces a unique time-warp operator for temporal partitioning and grouping of messages that hides the complexity of designing temporal algorithms, while avoiding redundancy in user logic calls and messages sent. GRAPHITE is our implementation of ICM over Apache Giraph, and we use it to design 12 TI and TD algorithms from literature. We rigorously evaluate its performance for diverse real-world temporal graphs - as large as 131M vertices and 5.5B edges, and as long as 219 snapshots. Our comparison with 4 baseline platforms on a 10-node commodity cluster shows that ICM shares compute and messaging across intervals to out-perform them by up to 25 �, and matches them even in worst-case scenarios. GRAPHITE also exhibits weak-scaling with near-perfect efficiency. © 2020 IEEE.

Item Type:	Conference Paper
Publication:	Proceedings - International Conference on Data Engineering
Publisher:	IEEE Computer Society
Additional Information:	Conference of 36th IEEE International Conference on Data Engineering, ICDE 2020 ; Conference Date: 20 April 2020 Through 24 April 2020; Conference Code:160235
Keywords:	Computer programming; Financial markets; Graph structures; Graph theory; Graphic methods; Graphite; Iterative methods, Commodity clusters; Computing model; Iterative processing; Programming abstractions; Temporal partitioning; Temporal property; Time independents; Worst case scenario, Graph algorithms
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	21 Dec 2024 09:38
Last Modified:	21 Dec 2024 09:38
URI:	http://eprints.iisc.ac.in/id/eprint/65864

Actions (login required)

View Item