As computer clusters become more common and the size of the problems encountered in the field of AI grows, there is an increasing demand for efficient parallel inference algorithms. We consider the problem of parallel inference on large factor graphs in the distributed memory setting of computer clusters. We develop a new efficient parallel inference algorithm, DBRSplash, which incorporates over-segmented graph partitioning, belief residual scheduling, and uniform work Splash operations. We empirically evaluate the DBRSplash algorithm on a 120 processor cluster and demonstrate linear to super-linear performance gains on large factor graph models.
Fast Parallel Exact Inference on Bayesian Networks: Poster
The University of Western Australia（西澳大利亚大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Hong Kong University of Science and Technology（香港科技大学）
Failure-Resilient Distributed Inference with Model Compression over Heterogeneous Edge Devices
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications (BUPT)（北京邮电大学计算机学院（国家示范性软件学院））；Frontier Research Center, Peng Cheng Laboratory（鹏城实验室前沿研究中心）；School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT)（北京邮电大学电子工程学院）
DistrEE: Distributed Early Exit of Deep Neural Network Inference on Edge Devices
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications（北京邮电大学计算机学院（国家示范性软件学院））；School of Electronic Engineering, Beijing University of Posts and Telecommunications（北京邮电大学电子工程学院）
