We present a novel extension of the traditional neural network approach to classification tasks, referred to as variational classification (VC). By incorporating latent variable modeling, akin to the relationship between variational autoencoders and traditional autoencoders, we derive a training objective based on the evidence lower bound (ELBO), optimized using an adversarial approach. Our VC model allows for more flexibility in design choices, in particular class-conditional latent priors, in place of the implicit assumptions made in off-the-shelf softmax classifiers. Empirical evaluation on image and text classification datasets demonstrates the effectiveness of our approach in terms of maintaining prediction accuracy while improving other desirable properties such as calibration and adversarial robustness, even when applied to out-of-domain data.

翻译：我们提出了一种传统神经网络分类方法的创新扩展，称为变分分类（VC）。通过引入潜变量建模（类似于变分自编码器与传统自编码器之间的关系），我们基于证据下界（ELBO）推导出训练目标，并采用对抗性方法进行优化。我们的VC模型在设计选择上具备更高的灵活性，特别是能够采用类别条件潜先验，替代现成softmax分类器中隐含的假设。在图像和文本分类数据集上的实证评估表明，该方法在保持预测精度的同时，能够提升其他理想特性（如校准性和对抗鲁棒性），即使应用于域外数据时依然有效。