Lena Stempfle

Lena Stempfle, Ashkan Panahi, Fredrik D. Johansson

Missing values are unavoidable in many applications of machine learning and present challenges both during training and at test time. When variables are missing in recurring patterns, fitting separate pattern submodels have been proposed as a solution. However, fitting models independently does not make efficient use of all available data. Conversely, fitting a single shared model to the full data set relies on imputation which often leads to biased results when missingness depends on unobserved factors. We propose an alternative approach, called sharing pattern submodels, which i) makes predictions that are robust to missing values at test time, ii) maintains or improves the predictive power of pattern submodels, and iii) has a short description, enabling improved interpretability. Parameter sharing is enforced through sparsity-inducing regularization which we prove leads to consistent estimation. Finally, we give conditions for when a sharing model is optimal, even when both missingness and the target outcome depend on unobserved variables. Classification and regression experiments on synthetic and real-world data sets demonstrate that our models achieve a favorable tradeoff between pattern specialization and information sharing.

Vinith M. Suriyakumar, Ayush Sekhari, Lena Stempfle et al.

Auditing the fine-tunes of open-weight generative models for harmful specialization has become a new governance challenge for model hosting platforms. The standard toolkit, generative evaluation via curated prompts or red-teaming, does not scale to platform-level auditing and breaks down entirely for domains like CSAM where generation is legally constrained. This motivates the Evaluation without Generation problem: assessing model capabilities without producing outputs. We argue that in such settings, capability must be inferred from the model's state, either its parameters or internal representations, rather than its outputs. We introduce Gaussian probing, a method that characterizes how LoRA adaptors perturb a model's internal representations by measuring responses to Gaussian latent ensembles. Unlike raw-weight baselines, Gaussian probing reliably distinguishes benign from harmful specialization without sampling outputs. We demonstrate effectiveness in high-risk domains, including detecting models specialized for child sexual abuse material (CSAM), where output-based evaluation is legally and ethically constrained. Our results show that Gaussian probing provides a scalable non-generative alternative for evaluating high-risk generative systems and remains robust to weight rescaling, a representative adversarial manipulation.

Lena Stempfle, Fredrik D. Johansson

Rule models are often preferred in prediction tasks with tabular inputs as they can be easily interpreted using natural language and provide predictive performance on par with more complex models. However, most rule models' predictions are undefined or ambiguous when some inputs are missing, forcing users to rely on statistical imputation models or heuristics like zero imputation, undermining the interpretability of the models. In this work, we propose fitting concise yet precise rule models that learn to avoid relying on features with missing values and, therefore, limit their reliance on imputation at test time. We develop MINTY, a method that learns rules in the form of disjunctions between variables that act as replacements for each other when one or more is missing. This results in a sparse linear rule model, regularized to have small dependence on features with missing values, that allows a trade-off between goodness of fit, interpretability, and robustness to missing values at test time. We demonstrate the value of MINTY in experiments using synthetic and real-world data sets and find its predictive performance comparable or favorable to baselines, with smaller reliance on features with missing values.

Sana Tonekaboni, Lena Stempfle, Adibvafa Fallahpour et al.

Foundation models trained on large-scale de-identified electronic health records (EHRs) hold promise for clinical applications. However, their capacity to memorize patient information raises important privacy concerns. In this work, we introduce a suite of black-box evaluation tests to assess privacy-related memorization risks in foundation models trained on structured EHR data. Our framework includes methods for probing memorization at both the embedding and generative levels, and aims to distinguish between model generalization and harmful memorization in clinically relevant settings. We contextualize memorization in terms of its potential to compromise patient privacy, particularly for vulnerable subgroups. We validate our approach on a publicly available EHR foundation model and release an open-source toolkit to facilitate reproducible and collaborative privacy assessments in healthcare AI.

Lena Stempfle, Arthur James, Julie Josse et al.

Inherently interpretable machine learning (IML) models offer valuable support for clinical decision-making but face challenges when features contain missing values. Traditional approaches, such as imputation or discarding incomplete records, are often impractical in scenarios where data is missing at test time. We surveyed 55 clinicians from 29 French trauma centers, collecting 20 complete responses to study their interaction with three IML models in a real-world clinical setting for predicting hemorrhagic shock with missing values. Our findings reveal that while clinicians recognize the value of interpretability and are familiar with common IML approaches, traditional imputation techniques often conflict with their intuition. Instead of imputing unobserved values, they rely on observed features combined with medical intuition and experience. As a result, methods that natively handle missing values are preferred. These findings underscore the need to integrate clinical reasoning into future IML models to enhance human-computer interaction.

Lena Stempfle, Anton Matsson, Newton Mwai et al.

Handling missing values at test time is challenging for machine learning models, especially when aiming for both high accuracy and interpretability. Established approaches often add bias through imputation or excessive model complexity via missingness indicators. Moreover, either method can obscure interpretability, making it harder to understand how the model utilizes the observed variables in predictions. We propose missingness-avoiding (MA) machine learning, a general framework for training models to rarely require the values of missing (or imputed) features at test time. We create tailored MA learning algorithms for decision trees, tree ensembles, and sparse linear models by incorporating classifier-specific regularization terms in their learning objectives. The tree-based models leverage contextual missingness by reducing reliance on missing values based on the observed context. Experiments on real-world datasets demonstrate that MA-DT, MA-LASSO, MA-RF, and MA-GBT effectively reduce the reliance on features with missing values while maintaining predictive performance competitive with their unregularized counterparts. This shows that our framework gives practitioners a powerful tool to maintain interpretability in predictions with test-time missing values.

Anton Matsson, Lena Stempfle, Yaochen Rao et al.

Modeling policies for sequential clinical decision-making based on observational data is useful for describing treatment practices, standardizing frequent patterns in treatment, and evaluating alternative policies. For each task, it is essential that the policy model is interpretable. Learning accurate models requires effectively capturing the state of a patient, either through sequence representation learning or carefully crafted summaries of their medical history. While recent work has favored the former, it remains a question as to how histories should best be represented for interpretable policy modeling. Focused on model fit, we systematically compare diverse approaches to summarizing patient history for interpretable modeling of clinical policies across four sequential decision-making tasks. We illustrate differences in the policies learned using various representations by breaking down evaluations by patient subgroups, critical states, and stages of treatment, highlighting challenges specific to common use cases. We find that interpretable sequence models using learned representations perform on par with black-box models across all tasks. Interpretable models using hand-crafted representations perform substantially worse when ignoring history entirely, but are made competitive by incorporating only a few aggregated and recent elements of patient history. The added benefits of using a richer representation are pronounced for subgroups and in specific use cases. This underscores the importance of evaluating policy models in the context of their intended use.