# Clustered Calibration: Representation-Aware Probability Calibration via Learned Subpopulations

arXiv: https://arxiv.org/abs/2510.19328 · HTML: https://mlsanity.com/paper/2510.19328/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Verified Uncertainty Calibration](https://mlsanity.com/paper/1909.10155/) (2019)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning](https://mlsanity.com/paper/2003.07329/) (2020)
- [Mitigating Bias in Calibration Error Estimation](https://mlsanity.com/paper/2012.08668/) (2020)
- [Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration](https://mlsanity.com/paper/2107.05719/) (2021)
- [Posterior calibration and exploratory analysis for natural language processing models](https://mlsanity.com/paper/1508.05154/) (2015)
- [Local Calibration: Metrics and Recalibration](https://mlsanity.com/paper/2102.10809/) (2021)
- [Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques](https://mlsanity.com/paper/1908.11528/) (2019)
- [DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks](https://mlsanity.com/paper/1710.00486/) (2017)
- [Can a calibration metric be both testable and actionable?](https://mlsanity.com/paper/2502.19851/) (2025)

## Abstract (arXiv)

Ensuring that predicted probabilities align with observed frequencies is critical in high-stakes domains such as clinical decision support, autonomous driving and financial risk assessment. Existing calibration methods typically apply a single global transformation or rely on post-hoc binning over predicted confidences, limiting their ability to exploit heterogeneous reliability across sub-populations. We propose Clustered Calibration, a representation-aware framework that identifies sub-populations via clustering in learned feature spaces (e.g., coverage vectors, SHAP values, CNN activations, Transformer embeddings) and fits a soft mixture of cluster-specific parametric calibrators under hierarchical shrinkage toward a global mapping. This design yields context-specific calibration while maintaining global stability. Across six tabular datasets and additional image and text benchmarks, clustered calibration consistently improves or matches strong global calibrators in terms of negative log-likelihood and Brier score, while preserving AUC and accuracy. We further show, both analytically and empirically, that fixed-bin Expected Calibration Error (ECE) can mis-rank soft, region-aware calibrators even when proper scoring rules improve, and we advocate for log-loss and Brier as more reliable bases for model selection in such settings.