用球面几何分解不确定性，实现多智能体系统的可解释因果推理。
SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry
- 将特征映射到单位超球面，通过信息几何融合分解不确定性。
- 在社交与情感数据集上准确率提升，校准性能更优。
- 适合需要可解释性与因果推断的复杂多智能体场景。
复杂多智能体系统中的可靠决策依赖于校准的预测和可解释的不确定性。我们提出SphUnc，一个融合超球面表征学习与结构因果建模的统一框架。该模型利用冯·米塞斯-费舍尔分布将特征映射至单位超球面潜变量，通过信息几何融合将不确定性分解为认知型与随机型成分。在球面潜变量上构建结构因果模型，实现基于样本模拟的定向影响识别与干预推理。在社交与情感基准上的实证评估表明，该方法在准确率、校准性及可解释因果信号方面均表现优异，为具有高阶交互的多智能体系统建立了几何-因果联合的不确定性感知推理基础。
原文摘要 · Abstract (English)
Reliable decision-making in complex multi-agent systems requires calibrated predictions and interpretable uncertainty. We introduce SphUnc, a unified framework combining hyperspherical representation learning with structural causal modeling. The model maps features to unit hypersphere latents using von Mises-Fisher distributions, decomposing uncertainty into epistemic and aleatoric components through information-geometric fusion. A structural causal model on spherical latents enables directed influence identification and interventional reasoning via sample-based simulation. Empirical evaluations on social and affective benchmarks demonstrate improved accuracy, better calibration, and interpretable causal signals, establishing a geometric-causal foundation for uncertainty-aware reasoning in multi-agent settings with higher-order interactions.
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。