ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gudovskiy, Denis, Okuno, Tomoyuki, Nakata, Yohei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910467892445184
author Gudovskiy, Denis
Okuno, Tomoyuki
Nakata, Yohei
author_facet Gudovskiy, Denis
Okuno, Tomoyuki
Nakata, Yohei
contents 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 https://github.com/gudovskiy/contextflow.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00578
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding
Gudovskiy, Denis
Okuno, Tomoyuki
Nakata, Yohei
Machine Learning
Artificial Intelligence
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 https://github.com/gudovskiy/contextflow.
title ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.00578