提出可估计输出与注意力不确定性的图卷积网络，提升模型可解释性与准确率。
Variational Graph Convolutional Neural Networks
- 用变分方法构建空间与时空图卷积网络，同时估计输出和层间注意力不确定性。
- 在社交交易与人体动作识别任务中，准确率提升且不确定性估计有效。
- 适合需可信预测的场景，如金融分析、医疗诊断等关键应用。
模型不确定性估计可同时提升图卷积网络的可解释性与准确性，也可在关键应用中通过专家或额外模型验证结果。本文提出空间与时空图卷积网络的变分神经网络版本，同时估计模型输出及各层注意力的不确定性，有助于增强模型可解释性。在芬兰董事会成员数据集、NTU-60、NTU-120 和 Kinetics 数据集上的社交交易分析与基于骨架的人体动作识别任务中，模型不仅准确率提升，还成功生成了可靠的不确定性估计。
原文摘要 · Abstract (English)
Estimation of model uncertainty can help improve the explainability of Graph Convolutional Networks and the accuracy of the models at the same time. Uncertainty can also be used in critical applications to verify the results of the model by an expert or additional models. In this paper, we propose Variational Neural Network versions of spatial and spatio-temporal Graph Convolutional Networks. We estimate uncertainty in both outputs and layer-wise attentions of the models, which has the potential for improving model explainability. We showcase the benefits of these models in the social trading analysis and the skeleton-based human action recognition tasks on the Finnish board membership, NTU-60, NTU-120 and Kinetics datasets, where we show improvement in model accuracy in addition to estimated model uncertainties.
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。