The Evidential regression network (ENet) estimates a continuous target and its predictive uncertainty without costly Bayesian model averaging. However, it is possible that the target is inaccurately predicted due to the gradient shrinkage problem of the original loss function of the ENet, the negative log marginal likelihood (NLL) loss. In this paper, the objective is to improve the prediction accuracy of the ENet while maintaining its efficient uncertainty estimation by resolving the gradient shrinkage problem. A multi-task learning (MTL) framework, referred to as MT-ENet, is proposed to accomplish this aim. In the MTL, we define the Lipschitz modified mean squared error (MSE) loss function as another loss and add it to the existing NLL loss. The Lipschitz modified MSE loss is designed to mitigate the gradient conflict with the NLL loss by dynamically adjusting its Lipschitz constant. By doing so, the Lipschitz MSE loss does not disturb the uncertainty estimation of the NLL loss. The MT-ENet enhances the predictive accuracy of the ENet without losing uncertainty estimation capability on the synthetic dataset and real-world benchmarks, including drug-target affinity (DTA) regression. Furthermore, the MT-ENet shows remarkable calibration and out-of-distribution detection capability on the DTA benchmarks.
翻译:在本文中,目标是提高ENet的预测准确性,同时通过解决梯度缩进问题来保持其有效的不确定性估计。为了实现这一目标,建议了一个称为MT-ENet的多任务学习框架(MT-ENet),以实现这一目标。在MTL中,我们将Lipschitz修改过的平方差错(MSE)损失函数定义为另一个损失,并将其添加到现有的NLLL损失中。Lipschitz修改的MSE损失是为了通过动态调整Lipschitz的常数来减轻与NLLL损失的梯度冲突。这样做,Lipschitz MSE损失并不扰乱NLLL损失的不确定性估计。MT-ENet提高了ENet的预测性准确性,同时又不丧失了合成数据设定和基准的不确定性估计能力。Libschite-MTA-MT-MT基准, 包括Greamal-DA-DMT-MT的精确性测试能力。