Abstract
Sum-Product Networks have received increasing attention from academia and industry alike, but the software ecosystem is comparably sparse. In this work, we enhance the ecosystem with an open-source, domain-specific compiler that allows to easily and efficiently target CPUs and GPUs for Sum-Product Network inference. The implementation of the compiler is based on the open-source MLIR framework. Using a real-world application of Sum-Product Networks, a robust speaker identification model, we showcase the performance improvements our compiler can achieve for SPN inference on CPUs and GPUs.
Calculations for this research were conducted on the Lichtenberg high performance computer of TU Darmstadt. This research was funded by the German Federal Ministry for Education and Research (BMBF) with the funding ID ZN 01\(\vert \)S17050.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kschischang, F.R., Frey, B.J., Loeliger, H.A.: Factor graphs and the sum-product algorithm. IEEE Trans. Inf. Theory 47(2), 498–519 (2001)
Lattner, C., et al.: Mlir: scaling compiler infrastructure for domain specific computation. In: CGO 2021 (2021)
Molina, A., et al.: Spflow: an easy and extensible library for deep probabilistic learning using sum-product networks (2019)
Nicolson, A., Paliwal, K.K.: Sum-product networks for robust automatic speaker identification (2020)
Paris, I., Sanchez-Cauce, R., Diez, F.J.: Sum-product networks: A survey (2020)
Peharz, R., et al.: Random sum-product networks: a simple but effective approach to probabilistic deep learning. In: Proceedings of UAI (2019)
Poon, H., Domingos, P.: Sum-product networks: a new deep architecture. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) (2011)
Pronobis, A., Ranganath, A., Rao, R.P.: Libspn: a library for learning and inference with sum-product networks and tensorflow. In: Principled Approaches to Deep Learning Workshop (2017)
Sommer, L., Oppermann, J., Molina, A., Binnig, C., Kersting, K., Koch, A.: Automatic mapping of the sum-product network inference problem to fpga-based accelerators. In: IEEE International Conference on Computer Design (ICCD), IEEE (2018)
Sommer, L., Weber, L., Kumm, M., Koch, A.: Comparison of arithmetic number formats for inference in sum-product networks on fpgas. In: 2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM) (2020)
Sugiarto, I., Axenie, C., Conradt, J.: Fpga-based hardware accelerator for an embedded factor graph with configurable optimization. J. Circuits Syst. Comput. 28(02), 1950031 (2019)
van de Wolfshaar, J., Pronobis, A.: Deep Generalized Convolutional Sum-Product Networks for Probabilistic Image Representations. arXiv:1902.06155 (September 2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Sommer, L., Axenie, C., Koch, A. (2021). SPNC: Fast Sum-Product Network Inference. In: Kamp, M., et al. Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2021. Communications in Computer and Information Science, vol 1524. Springer, Cham. https://doi.org/10.1007/978-3-030-93736-2_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-93736-2_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93735-5
Online ISBN: 978-3-030-93736-2
eBook Packages: Computer ScienceComputer Science (R0)