ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-variable Context Encoding
Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata
Abstract
Normalizing flow-based generative models have been widely used in applications where the exact density estimation is of major importance. Recent research proposes numerous methods to improve their expressivity. However, conditioning on a context is largely overlooked area in the bijective flow research. Conventional conditioning with the vector concatenation is limited to only a few flow types. More importantly, this approach cannot support a practical setup where a set of context-conditioned (*specialist*) models are trained with the fixed pretrained general-knowledge (*generalist*) model. We propose ContextFlow++ approach to overcome these limitations using an additive conditioning with explicit generalist-specialist knowledge decoupling. Furthermore, we support discrete contexts by the proposed mixed-variable architecture with context encoders. Particularly, our context encoder for discrete variables is a surjective flow from which the context-conditioned continuous variables are sampled. Our experiments on rotated MNIST-R, corrupted CIFAR-10C, real-world ATM predictive maintenance and SMAP unsupervised anomaly detection benchmarks show that the proposed ContextFlow++ offers faster stable training and achieves higher performance metrics. Our code is publicly available at [github.com/gudovskiy/contextflow](https://github.com/gudovskiy/contextflow).
BibTeX
@InProceedings{pmlr-v244-gudovskiy24a,
title = {ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-variable Context Encoding},
author = {Gudovskiy, Denis and Okuno, Tomoyuki and Nakata, Yohei},
booktitle = {Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence},
pages = {1479--1490},
year = {2024},
editor = {Kiyavash, Negar and Mooij, Joris M.},
volume = {244},
series = {Proceedings of Machine Learning Research},
month = {15--19 Jul},
publisher = {PMLR},
pdf = {https://raw.githubusercontent.com/mlresearch/v244/main/assets/gudovskiy24a/gudovskiy24a.pdf},
url = {https://proceedings.mlr.press/v244/gudovskiy24a.html},
abstract = {Normalizing flow-based generative models have been widely used in applications where the exact density estimation is of major importance. Recent research proposes numerous methods to improve their expressivity. However, conditioning on a context is largely overlooked area in the bijective flow research. Conventional conditioning with the vector concatenation is limited to only a few flow types. More importantly, this approach cannot support a practical setup where a set of context-conditioned (*specialist*) models are trained with the fixed pretrained general-knowledge (*generalist*) model. We propose ContextFlow++ approach to overcome these limitations using an additive conditioning with explicit generalist-specialist knowledge decoupling. Furthermore, we support discrete contexts by the proposed mixed-variable architecture with context encoders. Particularly, our context encoder for discrete variables is a surjective flow from which the context-conditioned continuous variables are sampled. Our experiments on rotated MNIST-R, corrupted CIFAR-10C, real-world ATM predictive maintenance and SMAP unsupervised anomaly detection benchmarks show that the proposed ContextFlow++ offers faster stable training and achieves higher performance metrics. Our code is publicly available at [github.com/gudovskiy/contextflow](https://github.com/gudovskiy/contextflow).}
}