mlsanityData to 7 Oct 2026

SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry

arXiv 2603.01168 ↗First posted 1 Mar 2026cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

24 of 35 references.

References · 24

  1. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  2. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
  3. 2024Estimating Epistemic and Aleatoric Uncertainty with a Single Modelcited by 52
  4. 2020Causal Inference under Networked Interference and Intervention Policy Enhancementcited by 37
  5. 2023Robust Multi-Agent Reinforcement Learning with State Uncertaintycited by 35
  6. 2021Calibrated and Sharp Uncertainties in Deep Learning via Density Estimationcited by 33
  7. 2023Introducing an Improved Information-Theoretic Measure of Predictive Uncertaintycited by 28
  8. 2022Self-supervised Hypergraph Representation Learning for Sociological Analysiscited by 27
  9. 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
  10. 2024A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guidecited by 22
  11. 2023A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifoldcited by 21
  12. 2023CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosiscited by 16
12 more
  1. 2020Identifying Possible Rumor Spreaders on Twitter: A Weak Supervised Learning Approachcited by 13
  2. 2022Higher-order interactions shape collective dynamics differently in hypergraphs and simplicial complexescited by 12
  3. 2022Using Embeddings for Causal Estimation of Peer Influence in Social Networkscited by 9
  4. 2025MA-DPR: Manifold-aware Distance Metrics for Dense Passage Retrievalcited by 8
  5. 2024Geodesic Causal Inferencecited by 7
  6. 2025Causal Spherical Hypergraph Networks for Modelling Social Uncertaintycited by 5
  7. 2023Causal Inference under Network Interference Using a Mixture of Randomized Experimentscited by 4
  8. 2024vMF-Contact: Uncertainty-aware Evidential Learning for Probabilistic Contact-grasp in Noisy Cluttercited by 4
  9. 2024Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKAcited by 2
  10. 2024A solution for the mean parametrization of the von Mises-Fisher distributioncited by 1
  11. 2025Higher-order Interaction Matters: Dynamic Hypergraph Neural Networks for Epidemic Modelingcited by 1
  12. 2025From News to Returns: A Granger-Causal Hypergraph Transformer on the Spherecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Noise Floor Audit for Agent Benchmarkscited by 0