SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry
This addresses the need for calibrated predictions and interpretable uncertainty in complex multi-agent systems, though it appears incremental as it builds on existing representation learning and causal modeling techniques.
The paper tackles the problem of reliable decision-making in multi-agent systems by introducing SphUnc, a framework that combines hyperspherical representation learning with structural causal modeling to decompose uncertainty and enable causal identification. The result shows improved accuracy, better calibration, and interpretable causal signals on social and affective benchmarks.
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.