Christina Heinze-Deml

Sorawit Saengkyongam, Juan L. Gamella, Andrew C. Miller et al. · eth-zurich

The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require labeled data from multiple training environments, limiting their applicability when labeled data are scarce. In this work, we study domain generalization in an anti-causal setting, where the outcome causes the observed covariates. Under this structure, environment perturbations that affect the covariates do not propagate to the outcome, which motivates regularizing the model's sensitivity to these perturbations. Crucially, estimating these perturbation directions does not require labels, enabling us to leverage unlabeled data from multiple environments. We propose two methods that penalize the model's sensitivity to variations in the mean and covariance of the covariates across environments, respectively, and prove that these methods have worst-case optimality guarantees under certain classes of environments. Finally, we demonstrate the empirical performance of our approach on a controlled physical system and a physiological signal dataset.

Juyeon Heo, Christina Heinze-Deml, Oussama Elachqar et al.

Instruction-following is crucial for building AI agents with large language models (LLMs), as these models must adhere strictly to user-provided constraints and guidelines. However, LLMs often fail to follow even simple and clear instructions. To improve instruction-following behavior and prevent undesirable outputs, a deeper understanding of how LLMs' internal states relate to these outcomes is required. In this work, we investigate whether LLMs encode information in their representations that correlate with instruction-following success - a property we term knowing internally. Our analysis identifies a direction in the input embedding space, termed the instruction-following dimension, that predicts whether a response will comply with a given instruction. We find that this dimension generalizes well across unseen tasks but not across unseen instruction types. We demonstrate that modifying representations along this dimension improves instruction-following success rates compared to random changes, without compromising response quality. Further investigation reveals that this dimension is more closely related to the phrasing of prompts rather than the inherent difficulty of the task or instructions. This work provides insight into the internal workings of LLMs' instruction-following, paving the way for reliable LLM agents.

Juyeon Heo, Miao Xiong, Christina Heinze-Deml et al.

Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs' instruction-following capabilities, raising concerns about their reliability in high-stakes applications. Accurately estimating LLMs' uncertainty in adhering to instructions is critical to mitigating deployment risks. We present, to our knowledge, the first systematic evaluation of the uncertainty estimation abilities of LLMs in the context of instruction-following. Our study identifies key challenges with existing instruction-following benchmarks, where multiple factors are entangled with uncertainty stems from instruction-following, complicating the isolation and comparison across methods and models. To address these issues, we introduce a controlled evaluation setup with two benchmark versions of data, enabling a comprehensive comparison of uncertainty estimation methods under various conditions. Our findings show that existing uncertainty methods struggle, particularly when models make subtle errors in instruction following. While internal model states provide some improvement, they remain inadequate in more complex scenarios. The insights from our controlled evaluation setups provide a crucial understanding of LLMs' limitations and potential for uncertainty estimation in instruction-following tasks, paving the way for more trustworthy AI agents.

Emanuele Palumbo, Sorawit Saengkyongam, Maria R. Cervera et al.

Continuous cardiovascular monitoring can play a key role in precision health. However, some fundamental cardiac biomarkers of interest, including stroke volume and cardiac output, require invasive measurements, e.g., arterial pressure waveforms (APW). As a non-invasive alternative, photoplethysmography (PPG) measurements are routinely collected in hospital settings. Unfortunately, the prediction of key cardiac biomarkers from PPG instead of APW remains an open challenge, further complicated by the scarcity of annotated PPG measurements. As a solution, we propose a hybrid approach that uses hemodynamic simulations and unlabeled clinical data to estimate cardiovascular biomarkers directly from PPG signals. Our hybrid model combines a conditional variational autoencoder trained on paired PPG-APW data with a conditional density estimator of cardiac biomarkers trained on labeled simulated APW segments. As a key result, our experiments demonstrate that the proposed approach can detect fluctuations of cardiac output and stroke volume and outperform a supervised baseline in monitoring temporal changes in these biomarkers.

Arno Blaas, Adam Goliński, Andrew Miller et al. · apple-ml

We consider robustness to distribution shifts in the context of diagnostic models in healthcare, where the prediction target $Y$, e.g., the presence of a disease, is causally upstream of the observations $X$, e.g., a biomarker. Distribution shifts may occur, for instance, when the training data is collected in a domain with patients having particular demographic characteristics while the model is deployed on patients from a different demographic group. In the domain of applied ML for health, it is common to predict $Y$ from $X$ without considering further information about the patient. However, beyond the direct influence of the disease $Y$ on biomarker $X$, a predictive model may learn to exploit confounding dependencies (or shortcuts) between $X$ and $Y$ that are unstable under certain distribution shifts. In this work, we highlight a data generating mechanism common to healthcare settings and discuss how recent theoretical results from the causality literature can be applied to build robust predictive models. We theoretically show why ignoring covariates as well as common invariant learning approaches will in general not yield robust predictors in the studied setting, while including certain covariates into the prediction model will. In an extensive simulation study, we showcase the robustness (or lack thereof) of different predictors under various data generating processes. Lastly, we analyze the performance of the different approaches using the PTB-XL dataset, a public dataset of annotated ECG recordings.

Christina Heinze-Deml, Diane Bouchacourt

Contrarily to humans who have the ability to recombine familiar expressions to create novel ones, modern neural networks struggle to do so. This has been emphasized recently with the introduction of the benchmark dataset "gSCAN" (Ruis et al. 2020), aiming to evaluate models' performance at compositional generalization in grounded language understanding. In this work, we challenge the gSCAN benchmark by proposing a simple model that achieves surprisingly good performance on two of the gSCAN test splits. Our model is based on the observation that, to succeed on gSCAN tasks, the agent must (i) identify the target object (think) before (ii) navigating to it successfully (act). Concretely, we propose an attention-inspired modification of the baseline model from (Ruis et al. 2020), together with an auxiliary loss, that takes into account the sequential nature of steps (i) and (ii). While two compositional tasks are trivially solved with our approach, we also find that the other tasks remain unsolved, validating the relevance of gSCAN as a benchmark for evaluating models' compositional abilities.

Juan L. Gamella, Christina Heinze-Deml

A fundamental difficulty of causal learning is that causal models can generally not be fully identified based on observational data only. Interventional data, that is, data originating from different experimental environments, improves identifiability. However, the improvement depends critically on the target and nature of the interventions carried out in each experiment. Since in real applications experiments tend to be costly, there is a need to perform the right interventions such that as few as possible are required. In this work we propose a new active learning (i.e. experiment selection) framework (A-ICP) based on Invariant Causal Prediction (ICP) (Peters et al., 2016). For general structural causal models, we characterize the effect of interventions on so-called stable sets, a notion introduced by (Pfister et al., 2019). We leverage these results to propose several intervention selection policies for A-ICP which quickly reveal the direct causes of a response variable in the causal graph while maintaining the error control inherent in ICP. Empirically, we analyze the performance of the proposed policies in both population and finite-regime experiments.

Fanny Yang, Zuowen Wang, Christina Heinze-Deml

This work provides theoretical and empirical evidence that invariance-inducing regularizers can increase predictive accuracy for worst-case spatial transformations (spatial robustness). Evaluated on these adversarially transformed examples, we demonstrate that adding regularization on top of standard or adversarial training reduces the relative error by 20% for CIFAR10 without increasing the computational cost. This outperforms handcrafted networks that were explicitly designed to be spatial-equivariant. Furthermore, we observe for SVHN, known to have inherent variance in orientation, that robust training also improves standard accuracy on the test set. We prove that this no-trade-off phenomenon holds for adversarial examples from transformation groups in the infinite data limit.

Christina Heinze-Deml, Nicolai Meinshausen

When training a deep neural network for image classification, one can broadly distinguish between two types of latent features of images that will drive the classification. We can divide latent features into (i) "core" or "conditionally invariant" features $X^\text{core}$ whose distribution $X^\text{core}\vert Y$, conditional on the class $Y$, does not change substantially across domains and (ii) "style" features $X^{\text{style}}$ whose distribution $X^{\text{style}} \vert Y$ can change substantially across domains. Examples for style features include position, rotation, image quality or brightness but also more complex ones like hair color, image quality or posture for images of persons. Our goal is to minimize a loss that is robust under changes in the distribution of these style features. In contrast to previous work, we assume that the domain itself is not observed and hence a latent variable. We do assume that we can sometimes observe a typically discrete identifier or "$\mathrm{ID}$ variable". In some applications we know, for example, that two images show the same person, and $\mathrm{ID}$ then refers to the identity of the person. The proposed method requires only a small fraction of images to have $\mathrm{ID}$ information. We group observations if they share the same class and identifier $(Y,\mathrm{ID})=(y,\mathrm{id})$ and penalize the conditional variance of the prediction or the loss if we condition on $(Y,\mathrm{ID})$. Using a causal framework, this conditional variance regularization (CoRe) is shown to protect asymptotically against shifts in the distribution of the style variables. Empirically, we show that the CoRe penalty improves predictive accuracy substantially in settings where domain changes occur in terms of image quality, brightness and color while we also look at more complex changes such as changes in movement and posture.

Christina Heinze-Deml, Brian McWilliams, Nicolai Meinshausen

Privacy is crucial in many applications of machine learning. Legal, ethical and societal issues restrict the sharing of sensitive data making it difficult to learn from datasets that are partitioned between many parties. One important instance of such a distributed setting arises when information about each record in the dataset is held by different data owners (the design matrix is "vertically-partitioned"). In this setting few approaches exist for private data sharing for the purposes of statistical estimation and the classical setup of differential privacy with a "trusted curator" preparing the data does not apply. We work with the notion of $(ε,δ)$-distributed differential privacy which extends single-party differential privacy to the distributed, vertically-partitioned case. We propose PriDE, a scalable framework for distributed estimation where each party communicates perturbed random projections of their locally held features ensuring $(ε,δ)$-distributed differential privacy is preserved. For $\ell_2$-penalized supervised learning problems PriDE has bounded estimation error compared with the optimal estimates obtained without privacy constraints in the non-distributed setting. We confirm this empirically on real world and synthetic datasets.