Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads

1 code implementation • 24 May 2021 • John Thorpe, Yifan Qiao, Jonathan Eyolfson, Shen Teng, Guanzhou Hu, Zhihao Jia, Jinliang Wei, Keval Vora, Ravi Netravali, Miryung Kim, Guoqing Harry Xu

Computation separation makes it possible to construct a deep, bounded-asynchronous pipeline where graph and tensor parallel tasks can fully overlap, effectively hiding the network latency incurred by Lambdas.

Pattern Morphing for Efficient Graph Mining

no code implementations • 8 Dec 2020 • Kasra Jamshidi, Keval Vora

Existing graph mining techniques including both custom graph mining applications and general-purpose graph mining systems, develop efficient execution plans to speed up the exploration of the given query patterns that represent subgraph structures of interest.

Graph Mining Distributed, Parallel, and Cluster Computing Databases

Peregrine: A Pattern-Aware Graph Mining System

1 code implementation • 6 Apr 2020 • Kasra Jamshidi, Rakesh Mahadasa, Keval Vora

General purpose graph mining systems provide a generic runtime to explore subgraph structures of interest with the help of user-defined functions that guide the overall exploration process.

Graph Mining Distributed, Parallel, and Cluster Computing Databases D.4; H.3.4; H.2.8

GraphBolt: Dependency-Driven Synchronous Processing of Streaming Graphs

1 code implementation • 1 Apr 2020 • Mugilan Mariappan, Keval Vora

Efficient streaming graph processing systems leverage incremental processing by updating computed results to reflect the change in graph structure for the latest graph snapshot.