SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry

TL;DR

SphUnc is a novel framework that combines hyperspherical representation learning with causal modeling to improve uncertainty calibration and interpretability in multi-agent systems.

Contribution

It introduces a unified geometric-causal approach that decomposes uncertainty and identifies causal influences on a hyperspherical latent space.

Findings

Demonstrates improved accuracy and calibration on social and affective benchmarks.

Provides interpretable causal signals within a geometric uncertainty framework.

Enables interventional reasoning via sample-based simulation.

Abstract

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.