Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularization-猫眼课题宝

DOI：

10.48550/arxiv.2311.05795

发表时间：

2023-11

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Russell Hart;Linlin Yu;Yifei Lou;Feng Chen

在过去的几十年里，深度神经网络取得了巨大的成功，但它们没有得到很好的校准，而且经常产生不可靠的预测。大量文献依赖于不确定性量化来评估学习模型的可靠性，这对于离分布（OOD）检测和误分类检测的应用尤为重要。我们对相互依赖节点级分类的不确定性量化感兴趣。我们基于优化不确定性交叉熵（UCE）损失函数的图后验网络（GPNs）开始分析。我们描述了广泛使用的UCE损耗的理论限制。为了减轻这些缺点，我们提出了一种基于距离的正则化方法，鼓励聚类的OOD节点在潜在空间中保持聚类。我们在8个标准数据集上进行了广泛的对比实验，并证明了所提出的正则化方法在OOD检测和错误分类检测方面都优于最先进的方法。

Deep neural networks have achieved significant success in the last decades, but they are not well-calibrated and often produce unreliable predictions. A large number of literature relies on uncertainty quantification to evaluate the reliability of a learning model, which is particularly important for applications of out-of-distribution (OOD) detection and misclassification detection. We are interested in uncertainty quantification for interdependent node-level classification. We start our analysis based on graph posterior networks (GPNs) that optimize the uncertainty cross-entropy (UCE)-based loss function. We describe the theoretical limitations of the widely-used UCE loss. To alleviate the identified drawbacks, we propose a distance-based regularization that encourages clustered OOD nodes to remain clustered in the latent space. We conduct extensive comparison experiments on eight standard datasets and demonstrate that the proposed regularization outperforms the state-of-the-art in both OOD detection and misclassification detection.

Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularization

文献摘要

相似文献