用随机集建模节点不确定性，提升GNN的可信度判断能力
Random-Set Graph Neural Networks
- 将节点不确定性建模为有限随机集，通过信念函数框架实现
- 在9个图数据集上验证，显著提升不确定性量化效果
- 适合需要可信预测的工业场景，如自动驾驶感知系统
不确定性量化已成为理解图神经网络（GNN）生成数据表征的重要因素。尽管其预测能力在工业应用中极具价值，但数据固有的不确定性（如缺失边、过平滑）会严重影响性能。其中，偶然不确定性源于噪声和不完整数据，而认知不确定性则源于对系统或模型知识不足（如图拓扑或节点特征表示），可通过获取更多信息缓解。本文提出一种新框架，采用信念函数（有限随机集）形式对节点级认知不确定性进行建模。所提出的随机集图神经网络（RS-GNN）具备信念函数输出头，可预测类别上的随机集，从而同时获得精确的概率预测与认知不确定性度量。在包括Nuscenes和ROAD在内的9个图学习数据集上的大量实验表明，RS-GNN在不确定性量化方面表现卓越。
原文摘要 · Abstract (English)
Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, the inherent uncertainty induced by the nature of the data is a huge mitigating factor to GNN performance. While aleatoric uncertainty is the result of noisy and incomplete stochastic data such as missing edges or over-smoothing, epistemic uncertainty arises from lack of knowledge about a system or model (e.g., a graph's topology or node feature representation), which can be reduced by gathering more data and information. In this paper, we propose an original new framework in which node-level epistemic uncertainty is modelled in a belief function (finite random set) formalism. The resulting Random-Set Graph Neural Networks have a belief-function head predicting a random set over the list of classes, from which both a precise probability prediction and a measure of epistemic uncertainty can be obtained. Extensive experiments on 9 different graph learning datasets, including real-world autonomous driving benchmarks as such Nuscene and ROAD, demonstrate RS-GNN's superior uncertainty quantification capabilities
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。