ContextFlow++：基于混合变量上下文编码的通才-专才流生成模型
ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding
AI总结：
针对双射流模型中上下文条件生成被忽视及难以结合预训练通才模型训练专才模型的问题，提出ContextFlow++方法，通过显式解耦通才与专才知识的加法条件机制及混合变量上下文编码器，实现了更快的稳定训练与更优性能。
摘要：
归一化流生成模型已广泛应用于以精确密度估计为关键的应用中。近期研究提出了许多方法来提升其表达能力。然而，在双射流研究中，基于上下文的条件生成很大程度上被忽视了。使用向量拼接的传统条件方法仅限于少数几种流类型。更重要的是，这种方法无法支持一种实际设置，即一组上下文条件化的（专才）模型与固定的预训练通用知识（通才）模型一起训练。我们提出了ContextFlow++方法，通过使用具有显式通才-专才知识解耦的加法条件来克服这些限制。此外，我们通过提出的带有上下文编码器的混合变量架构来支持离散上下文。特别是，我们针对离散变量的上下文编码器是一个满射流，从中采样上下文条件化的连续变量。我们在旋转的MNIST-R、损坏的CIFAR-10C、真实世界的ATM预测性维护和SMAP无监督异常检测基准上的实验表明，所提出的ContextFlow++提供了更快的稳定训练，并实现了更高的性能指标。我们的代码已在 https://github.com/gudovskiy/contextflow 上公开。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
