As Deep Neural Networks (DNN) make their way into safety-critical decision processes, it becomes imperative to have robust and reliable uncertainty estimates for their predictions for both in-distribution and out-of-distribution (OOD) examples. This is particularly important in real-life high-risk settings such as healthcare, where OOD examples (e.g., patients with previously unseen or rare labels, i.e., diagnoses) are frequent, and an incorrect clinical decision might put human life in danger, in addition to having severe ethical and financial costs. While evidential uncertainty estimates for deep learning have been studied for multi-class problems, research in multi-label settings remains untapped. In this paper, we propose a DEep Evidential Doctor (DEED), which is a novel deterministic approach to estimate multi-label targets along with uncertainty. We achieve this by placing evidential priors over the original likelihood functions and directly estimating the parameters of the evidential distribution using a novel loss function. Additionally, we build a redundancy layer (particularly for high uncertainty and OOD examples) to minimize the risk associated with erroneous decisions based on dubious predictions. We achieve this by learning the mapping between the evidential space and a continuous semantic label embedding space via a recurrent decoder. Thereby inferring, even in the case of OOD examples, reasonably close predictions to avoid catastrophic consequences. We demonstrate the effectiveness of DEED on a digit classification task based on a modified multi-label MNIST dataset, and further evaluate it on a diagnosis prediction task from a real-life electronic health record dataset. We highlight that in terms of prediction scores, our approach is on par with the existing state-of-the-art having a clear advantage of generating reliable, memory and time-efficient uncertainty estimates with minimal changes to any multi-label DNN classifier.

随着深度神经网络 (DNN) 进入安全关键型决策过程，必须对其分布内和分布外 (OOD) 示例的预测进行稳健且可靠的不确定性估计。这在现实生活中的高风险环境中尤其重要，例如医疗保健，其中 OOD 示例（例如，具有以前未见过或罕见标签的患者，即诊断）很常见，并且不正确的临床决策可能会将人类生命置于危险之中。除了严重的道德和财务成本之外。虽然深度学习的证据不确定性估计已经针对多类问题进行了研究，但多标签设置的研究仍未开发。在本文中，我们提出了深度证据医生（DEED），这是一种新颖的确定性方法，用于估计多标签目标和不确定性。我们通过将证据先验置于原始似然函数上并使用新颖的损失函数直接估计证据分布的参数来实现这一点。此外，我们构建了一个冗余层（特别是对于高不确定性和 OOD 示例），以最大限度地减少与基于可疑预测的错误决策相关的风险。我们通过循环解码器学习证据空间和连续语义标签嵌入空间之间的映射来实现这一点。从而推断，即使在 OOD 示例的情况下，也能做出相当接近的预测，以避免灾难性后果。我们证明了 DEED 在基于修改后的多标签 MNIST 数据集的数字分类任务上的有效性，并进一步评估了它在现实电子健康记录数据集的诊断预测任务上的有效性。我们强调，就预测分数而言，我们的方法与现有最先进的方法相当，具有明显的优势，可以生成可靠、内存和时间高效的不确定性估计，并且对任何多标签 DNN 分类器的更改最小。