mlsanityData to 14 Oct 2026

Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction

arXiv 2510.15233 ↗First posted 17 Oct 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Reliable, informative, and individual uncertainty quantification (UQ) remains missing in current ML community. This hinders the effective application of AI/ML to risk-sensitive domains. Most methods either fail to provide coverage on new data, inflate intervals so broadly that they are not actionable, or assign uncertainties that do not track actual error, especially under a distribution shift. In high-stakes drug discovery, protein-ligand affinity (PLI) prediction is especially challenging as assay noise is heterogeneous, chemical space is imbalanced and large, and practical evaluations routinely involve distribution shift. In this work, we introduce a novel uncertainty quantification method, Trustworthy Expert Split-conformal with Scaled Estimation for Efficient Reliable Adaptive intervals (TESSERA), that provides per-sample uncertainty with reliable coverage guarantee, informative and adaptive prediction interval widths that track the absolute error. We evaluate on protein-ligand binding affinity prediction under both independent and identically distributed (i.i.d.) and scaffold-based out-of-distribution (OOD) splits, comparing against strong UQ baselines. TESSERA attains near-nominal coverage and the best coverage-width trade-off as measured by the Coverage-Width Criterion (CWC), while maintaining competitive adaptivity (lowest Area Under the Sparsification Error (AUSE)). Size-Stratified Coverage (SSC) further confirms that intervals are right-sized, indicating width increases when data are scarce or noisy, and remain tight when predictions are reliable. By unifying Mixture of Expert (MoE) diversity with conformal calibration, TESSERA delivers trustworthy, tight, and adaptive uncertainties that are well-suited to selective prediction and downstream decision-making in the drug-discovery pipeline and other applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 48 references that are in the map. First posted on arXiv 17 Oct 2025.

Builds on

28 of 48 references.

References · 28

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  6. 2016End to End Learning for Self-Driving Carscited by 1,009
  7. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  8. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  9. 2017Deep Bayesian Active Learning with Image Datacited by 819
  10. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  11. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  12. 2019Conformalized Quantile Regressioncited by 629
16 more
  1. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  2. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  3. 2021Large-Scale Chemical Language Representations Capture Molecular Structure and Propertiescited by 206
  4. 2022ChemBERTa-2: Towards Chemical Foundation Modelscited by 127
  5. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  6. 2021A survey on high-dimensional Gaussian process modeling with application to Bayesian optimizationcited by 77
  7. 2020Uncertainty Quantification Using Neural Networks for Molecular Property Predictioncited by 66
  8. 2023Rethinking Tokenizer and Decoder in Masked Graph Modeling for Moleculescited by 49
  9. 2025Mahalanobis++: Improving OOD Detection via Feature Normalizationcited by 32
  10. 2017Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modelingcited by 25
  11. 2019Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernelcited by 19
  12. 2020Calibration of Model Uncertainty for Dropout Variational Inferencecited by 18
  13. 2021Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applicationscited by 17
  14. 2022Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Expertscited by 13
  15. 2025Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentationcited by 6
  16. 2016Prediction performance after learning in Gaussian process regressioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Equivariant Evidential Deep Learning for Interatomic Potentials
  2. 2025Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization
  3. 2025Fitness aligned structural modeling enables scalable virtual screening with AuroBind
  4. 2025Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design
  5. 2026Multimodal Mixture-of-Experts with Retrieval Augmentation for Protein Active Site Identification
  6. 2023Leveraging Side Information for Ligand Conformation Generation using Diffusion-Based Approaches
  7. 2026Robust Conformalized Selection with Noisy Responses
  8. 2025A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery