联合训练方差网络与贝叶斯神经网络，分离数据噪声与模型不确定性。
Cooperative Variance Estimation and Bayesian Neural Networks for Disentangling Aleatoric and Epistemic Uncertainties
- 用方差估计网络与贝叶斯神经网络协同训练，实现不确定性解耦。
- 在自建时变异方差数据集上，准确识别已知的随机不确定性。
- 方法简单易实现，适用于多种模型结构，适合需要可信预测的场景。
真实世界数据包含不可消除的随机不确定性（由测量不精确或生成过程不完全知识导致）。均值-方差估计网络可学习此类不确定性，但需人工正则化防止过拟合，且无法预测认知不确定性（模型不确定性）。相反，贝叶斯神经网络能预测认知不确定性，但因贝叶斯推断近似性，训练困难。本文提出联合训练方差估计网络与贝叶斯神经网络，实证表明该方法可有效解耦随机与认知不确定性，同时提升均值预测性能。我们在多个数据集上验证了该方法的有效性与可扩展性，包括一个自建的时间依赖异方差回归数据集，其中随机不确定性已知。所提方法实现简单、鲁棒性强，可适配多种模型架构。代码已开源：https://github.com/bessagroup/VeBNN。
原文摘要 · Abstract (English)
Real-world data contains aleatoric uncertainty - irreducible noise arising from imperfect measurements or from incomplete knowledge about the data generation process. Mean-variance estimation networks can learn this type of uncertainty but require ad-hoc regularization strategies to avoid overfitting and are unable to predict epistemic uncertainty (model uncertainty). Conversely, Bayesian neural networks predict epistemic uncertainty but are notoriously difficult to train due to the approximate nature of Bayesian inference. We propose to cooperatively train a variance estimation network with a Bayesian neural network and empirically demonstrate that the resulting model disentangles aleatoric and epistemic uncertainties while improving the mean estimation. We demonstrate the effectiveness and scalability of this method across a diverse range of datasets, including a time-dependent heteroscedastic regression dataset we created where the aleatoric uncertainty is known. The proposed method is straightforward to implement, robust, and adaptable to various model architectures. Code is available at https://github.com/bessagroup/VeBNN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。