GPflux: A Library for Deep Gaussian Processes
This library addresses a gap for researchers and practitioners in Bayesian deep learning by enabling easier implementation and extension of DGPs, though it is incremental as it builds on existing tools like GPflow and Keras.
The authors tackled the lack of actively maintained, open-source libraries for deep Gaussian processes (DGPs) by introducing GPflux, a Python library that provides state-of-the-art DGP algorithms and building blocks for novel Bayesian models, built on top of Keras and GPflow for efficiency and compatibility.
We introduce GPflux, a Python library for Bayesian deep learning with a strong emphasis on deep Gaussian processes (DGPs). Implementing DGPs is a challenging endeavour due to the various mathematical subtleties that arise when dealing with multivariate Gaussian distributions and the complex bookkeeping of indices. To date, there are no actively maintained, open-sourced and extendable libraries available that support research activities in this area. GPflux aims to fill this gap by providing a library with state-of-the-art DGP algorithms, as well as building blocks for implementing novel Bayesian and GP-based hierarchical models and inference schemes. GPflux is compatible with and built on top of the Keras deep learning eco-system. This enables practitioners to leverage tools from the deep learning community for building and training customised Bayesian models, and create hierarchical models that consist of Bayesian and standard neural network layers in a single coherent framework. GPflux relies on GPflow for most of its GP objects and operations, which makes it an efficient, modular and extensible library, while having a lean codebase.