Mar 2, 2023 · Current frameworks designed for graph sampling and random walk tasks are generally not efficient in terms of memory requirement and throughput.

In this paper we aim to achieve high-quality sam- pling/walking in an efficient and scalable way. We thor- oughly investigate existing algorithms, frameworks, ...

Abstract—Graph sampling and random walk algorithms are playing increasingly important roles today because they can significantly.

This paper presents. Skywalker, a high-throughput, quality-preserving random walk and sampling framework based on GPUs. Skywalker makes three key contributions: ...

Apr 16, 2024 · In this paper, we propose FlowWalker, a GPU-based dynamic graph random walk framework. FlowWalker implements an efficient parallel sampling ...

Graph sampling and random walk algorithms are playing increasingly important roles today because they can significantly reduce graph size while preserving ...

2023. Optimizing GPU-Based Graph Sampling and Random Walk for Efficiency and Scalability. P Wang, C Xu, C Li, J Wang, T Wang, L Zhang, X Hou, M Guo. IEEE ...

To support sophisticated graph learning tasks, various graph sampling algorithms have been proposed, which are far more complex than conventional random walks.

In this paper, we propose, to the best of our knowledge, the first GPU-based framework for graph sampling/random walk. First, our framework provides a ...

Oct 23, 2023 · gSampler models graph sampling using a general 4-step Extract-Compute-Select-Finalize (ECSF) programming model, proposes a set of matrix-centric ...