Eyke Hüllermeier

Eli Verwimp, Rahaf Aljundi, Shai Ben-David et al. · deepmind

Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past. In this work, we take a step back, and ask: "Why should one care about continual learning in the first place?". We set the stage by examining recent continual learning papers published at four major machine learning conferences, and show that memory-constrained settings dominate the field. Then, we discuss five open problems in machine learning, and even though they might seem unrelated to continual learning at first sight, we show that continual learning will inevitably be part of their solution. These problems are model editing, personalization and specialization, on-device learning, faster (re-)training and reinforcement learning. Finally, by comparing the desiderata from these unsolved problems and the current assumptions in continual learning, we highlight and discuss four future directions for continual learning research. We hope that this work offers an interesting perspective on the future of continual learning, while displaying its potential value and the paths we have to pursue in order to make it successful. This work is the result of the many discussions the authors had at the Dagstuhl seminar on Deep Continual Learning, in March 2023.

Santo M. A. R. Thies, Viktor Bengs, Timo Kaufmann et al.

Calibration, the alignment of predicted probabilities with true outcome frequencies, is essential for reliable decision-making. While extensively studied for classification and regression, calibration has not been formally addressed for probabilistic label ranking, where the goal is to predict a distribution over orderings of a label set. Naively treating rankings as classes ignores their structure and fails to capture important modalities such as pairwise and top-k predictions. We formalize calibration for label ranking and develop a hierarchy of notions covering full rankings, sub-rankings, and top-k rankings. We prove that full-rank calibration implies the others but not conversely, and sub-ranking and top-k calibration are incomparable. Empirically, we find popular label ranking models are often poorly calibrated, with substantial differences between sub-ranking and top-k metrics. Applying our framework to RLHF reward models, we find that calibration correlates strongly but not perfectly with benchmark accuracy, suggesting it captures a meaningful quality dimension beyond top-1 accuracy. These findings motivate future work on understanding the downstream effects of miscalibration and developing methods to correct it.

Navid Ansari, Alireza Javanmardi, Eyke Hüllermeier et al.

Bayesian optimization (BO) provides a powerful framework for optimizing black-box, expensive-to-evaluate functions. It is therefore an attractive tool for engineering design problems, typically involving multiple objectives. Thanks to the rapid advances in fabrication and measurement methods as well as parallel computing infrastructure, querying many design problems can be heavily parallelized. This class of problems challenges BO with an unprecedented setup where it has to deal with very large batches, shifting its focus from sample efficiency to iteration efficiency. We present a novel Bayesian optimization framework specifically tailored to address these limitations. Our key contribution is a highly scalable, sample-based acquisition function that performs a non-dominated sorting of not only the objectives but also their associated uncertainty. We show that our acquisition function in combination with different Bayesian neural network surrogates is effective in data-intensive environments with a minimal number of iterations. We demonstrate the superiority of our method by comparing it with state-of-the-art multi-objective optimizations. We perform our evaluation on two real-world problems -- airfoil design and 3D printing -- showcasing the applicability and efficiency of our approach. Our code is available at: https://github.com/an-on-ym-ous/lbn_mobo

Lisa Wimmer, Yusuf Sale, Paul Hofman et al.

The quantification of aleatoric and epistemic uncertainty in terms of conditional entropy and mutual information, respectively, has recently become quite common in machine learning. While the properties of these measures, which are rooted in information theory, seem appealing at first glance, we identify various incoherencies that call their appropriateness into question. In addition to the measures themselves, we critically discuss the idea of an additive decomposition of total uncertainty into its aleatoric and epistemic constituents. Experiments across different computer vision tasks support our theoretical findings and raise concerns about current practice in uncertainty quantification.

Viktor Bengs, Eyke Hüllermeier, Willem Waegeman

Uncertainty quantification has received increasing attention in machine learning in the recent past. In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard. The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify. In this paper, we analyse a recent proposal based on the idea of a second-order learner, which yields predictions in the form of distributions over probability distributions. While standard (first-order) learners can be trained to predict accurate probabilities, namely by minimising suitable loss functions on sample data, we show that loss minimisation does not work for second-order predictors: The loss functions proposed for inducing such predictors do not incentivise the learner to represent its epistemic uncertainty in a faithful way.

Fabian Fumagalli, Maximilian Muschalik, Patrick Kolpaczki et al.

Predominately in explainable artificial intelligence (XAI) research, the Shapley value (SV) is applied to determine feature attributions for any black box model. Shapley interaction indices extend the SV to define any-order feature interactions. Defining a unique Shapley interaction index is an open research question and, so far, three definitions have been proposed, which differ by their choice of axioms. Moreover, each definition requires a specific approximation technique. Here, we propose SHAPley Interaction Quantification (SHAP-IQ), an efficient sampling-based approximator to compute Shapley interactions for arbitrary cardinal interaction indices (CII), i.e. interaction indices that satisfy the linearity, symmetry and dummy axiom. SHAP-IQ is based on a novel representation and, in contrast to existing methods, we provide theoretical guarantees for its approximation quality, as well as estimates for the variance of the point estimates. For the special case of SV, our approach reveals a novel representation of the SV and corresponds to Unbiased KernelSHAP with a greatly simplified calculation. We illustrate the computational efficiency and effectiveness by explaining language, image classification and high-dimensional synthetic models.

Patrick Kolpaczki, Viktor Bengs, Maximilian Muschalik et al.

The Shapley value, which is arguably the most popular approach for assigning a meaningful contribution value to players in a cooperative game, has recently been used intensively in explainable artificial intelligence. Its meaningfulness is due to axiomatic properties that only the Shapley value satisfies, which, however, comes at the expense of an exact computation growing exponentially with the number of agents. Accordingly, a number of works are devoted to the efficient approximation of the Shapley value, most of them revolve around the notion of an agent's marginal contribution. In this paper, we propose with SVARM and Stratified SVARM two parameter-free and domain-independent approximation algorithms based on a representation of the Shapley value detached from the notion of marginal contribution. We prove unmatched theoretical guarantees regarding their approximation quality and provide empirical results including synthetic games as well as common explainability use cases comparing ourselves with state-of-the-art methods.

Fabian Fumagalli, Maximilian Muschalik, Eyke Hüllermeier et al.

Explainable Artificial Intelligence (XAI) has mainly focused on static learning scenarios so far. We are interested in dynamic scenarios where data is sampled progressively, and learning is done in an incremental rather than a batch mode. We seek efficient incremental algorithms for computing feature importance (FI) measures, specifically, an incremental FI measure based on feature marginalization of absent features similar to permutation feature importance (PFI). We propose an efficient, model-agnostic algorithm called iPFI to estimate this measure incrementally and under dynamic modeling conditions including concept drift. We prove theoretical guarantees on the approximation quality in terms of expectation and variance. To validate our theoretical findings and the efficacy of our approaches compared to traditional batch PFI, we conduct multiple experimental studies on benchmark data with and without concept drift.

Yusuf Sale, Michele Caprio, Eyke Hüllermeier

Adequate uncertainty representation and quantification have become imperative in various scientific disciplines, especially in machine learning and artificial intelligence. As an alternative to representing uncertainty via one single probability measure, we consider credal sets (convex sets of probability measures). The geometric representation of credal sets as $d$-dimensional polytopes implies a geometric intuition about (epistemic) uncertainty. In this paper, we show that the volume of the geometric representation of a credal set is a meaningful measure of epistemic uncertainty in the case of binary classification, but less so for multi-class classification. Our theoretical findings highlight the crucial role of specifying and employing uncertainty measures in machine learning in an appropriate way, and for being aware of possible pitfalls.

Viktor Bengs, Eyke Hüllermeier, Willem Waegeman

It is well known that accurate probabilistic predictors can be trained through empirical risk minimisation with proper scoring rules as loss functions. While such learners capture so-called aleatoric uncertainty of predictions, various machine learning methods have recently been developed with the goal to let the learner also represent its epistemic uncertainty, i.e., the uncertainty caused by a lack of knowledge and data. An emerging branch of the literature proposes the use of a second-order learner that provides predictions in terms of distributions on probability distributions. However, recent work has revealed serious theoretical shortcomings for second-order predictors based on loss minimisation. In this paper, we generalise these findings and prove a more fundamental result: There seems to be no loss function that provides an incentive for a second-order learner to faithfully represent its epistemic uncertainty in the same manner as proper scoring rules do for standard (first-order) learners. As a main mathematical tool to prove this result, we introduce the generalised notion of second-order scoring rules.

Michele Caprio, Yusuf Sale, Eyke Hüllermeier et al.

In their seminal 1990 paper, Wasserman and Kadane establish an upper bound for the Bayes' posterior probability of a measurable set $A$, when the prior lies in a class of probability measures $\mathcal{P}$ and the likelihood is precise. They also give a sufficient condition for such upper bound to hold with equality. In this paper, we introduce a generalization of their result by additionally addressing uncertainty related to the likelihood. We give an upper bound for the posterior probability when both the prior and the likelihood belong to a set of probabilities. Furthermore, we give a sufficient condition for this upper bound to become an equality. This result is interesting on its own, and has the potential of being applied to various fields of engineering (e.g. model predictive control), machine learning, and artificial intelligence.

Maximilian Muschalik, Fabian Fumagalli, Rohit Jagtani et al.

Post-hoc explanation techniques such as the well-established partial dependence plot (PDP), which investigates feature dependencies, are used in explainable artificial intelligence (XAI) to understand black-box machine learning models. While many real-world applications require dynamic models that constantly adapt over time and react to changes in the underlying distribution, XAI, so far, has primarily considered static learning environments, where models are trained in a batch mode and remain unchanged. We thus propose a novel model-agnostic XAI framework called incremental PDP (iPDP) that extends on the PDP to extract time-dependent feature effects in non-stationary learning environments. We formally analyze iPDP and show that it approximates a time-dependent variant of the PDP that properly reacts to real and virtual concept drift. The time-sensitivity of iPDP is controlled by a single smoothing parameter, which directly corresponds to the variance and the approximation error of iPDP in a static learning environment. We illustrate the efficacy of iPDP by showcasing an example application for drift detection and conducting multiple experiments on real-world and synthetic data sets and streams.

Alireza Javanmardi, Eyke Hüllermeier

The main objective of Prognostics and Health Management is to estimate the Remaining Useful Lifetime (RUL), namely, the time that a system or a piece of equipment is still in working order before starting to function incorrectly. In recent years, numerous machine learning algorithms have been proposed for RUL estimation, mainly focusing on providing more accurate RUL predictions. However, there are many sources of uncertainty in the problem, such as inherent randomness of systems failure, lack of knowledge regarding their future states, and inaccuracy of the underlying predictive models, making it infeasible to predict the RULs precisely. Hence, it is of utmost importance to quantify the uncertainty alongside the RUL predictions. In this work, we investigate the conformal prediction (CP) framework that represents uncertainty by predicting sets of possible values for the target variable (intervals in the case of RUL) instead of making point predictions. Under very mild technical assumptions, CP formally guarantees that the actual value (true RUL) is covered by the predicted set with a degree of certainty that can be prespecified. We study three CP algorithms to conformalize any single-point RUL predictor and turn it into a valid interval predictor. Finally, we conformalize two single-point RUL predictors, deep convolutional neural networks and gradient boosting, and illustrate their performance on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) data sets.

Subhabrata Dutta, Timo Kaufmann, Goran Glavaš et al.

While there is a widespread belief that artificial general intelligence (AGI) -- or even superhuman AI -- is imminent, complex problems in expert domains are far from being solved. We argue that such problems require human-AI cooperation and that the current state of the art in generative AI is unable to play the role of a reliable partner due to a multitude of shortcomings, including difficulty to keep track of a complex solution artifact (e.g., a software program), limited support for versatile human preference expression and lack of adapting to human preference in an interactive setting. To address these challenges, we propose HAICo2, a novel human-AI co-construction framework. We take first steps towards a formalization of HAICo2 and discuss the difficult open research problems that it faces.

Thomas Mortier, Viktor Bengs, Eyke Hüllermeier et al.

Multi-class classification methods that produce sets of probabilistic classifiers, such as ensemble learning methods, are able to model aleatoric and epistemic uncertainty. Aleatoric uncertainty is then typically quantified via the Bayes error, and epistemic uncertainty via the size of the set. In this paper, we extend the notion of calibration, which is commonly used to evaluate the validity of the aleatoric uncertainty representation of a single probabilistic classifier, to assess the validity of an epistemic uncertainty representation obtained by sets of probabilistic classifiers. Broadly speaking, we call a set of probabilistic classifiers calibrated if one can find a calibrated convex combination of these classifiers. To evaluate this notion of calibration, we propose a novel nonparametric calibration test that generalizes an existing test for single probabilistic classifiers to the case of sets of probabilistic classifiers. Making use of this test, we empirically show that ensembles of deep neural networks are often not well calibrated.

Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer et al.

Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario. However, machine learning is often applied in dynamic environments, where data arrives continuously and learning must be done in an online manner. Therefore, we propose iSAGE, a time- and memory-efficient incrementalization of SAGE, which is able to react to changes in the model as well as to drift in the data-generating process. We further provide efficient feature removal methods that break (interventional) and retain (observational) feature dependencies. Moreover, we formally analyze our explanation method to show that iSAGE adheres to similar theoretical properties as SAGE. Finally, we evaluate our approach in a thorough experimental analysis based on well-established data sets and data streams with concept drift.

Alireza Javanmardi, Yusuf Sale, Paul Hofman et al.

While the predictions produced by conformal prediction are set-valued, the data used for training and calibration is supposed to be precise. In the setting of superset learning or learning from partial labels, a variant of weakly supervised learning, it is exactly the other way around: training data is possibly imprecise (set-valued), but the model induced from this data yields precise predictions. In this paper, we combine the two settings by making conformal prediction amenable to set-valued training data. We propose a generalization of the conformal prediction procedure that can be applied to set-valued training and calibration data. We prove the validity of the proposed method and present experimental studies in which it compares favorably to natural baselines.

Thomas Mortier, Eyke Hüllermeier, Krzysztof Dembczyński et al.

Set-valued prediction is a well-known concept in multi-class classification. When a classifier is uncertain about the class label for a test instance, it can predict a set of classes instead of a single class. In this paper, we focus on hierarchical multi-class classification problems, where valid sets (typically) correspond to internal nodes of the hierarchy. We argue that this is a very strong restriction, and we propose a relaxation by introducing the notion of representation complexity for a predicted set. In combination with probabilistic classifiers, this leads to a challenging inference problem for which specific combinatorial optimization algorithms are needed. We propose three methods and evaluate them on benchmark datasets: a naïve approach that is based on matrix-vector multiplication, a reformulation as a knapsack problem with conflict graph, and a recursive tree search method. Experimental results demonstrate that the last method is computationally more efficient than the other two approaches, due to a hierarchical factorization of the conditional class distribution.

Amirhossein Vahidi, Lisa Wimmer, Hüseyin Anil Gündüz et al.

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory demands. In addition, the efficiency of a deep ensemble is related to diversity among the ensemble members which is challenging for large, over-parameterized deep neural networks. Moreover, ensemble learning has not yet seen such widespread adoption, and it remains a challenging endeavor for self-supervised or unsupervised representation learning. Motivated by these challenges, we present a novel self-supervised training regime that leverages an ensemble of independent sub-networks, complemented by a new loss function designed to encourage diversity. Our method efficiently builds a sub-model ensemble with high diversity, leading to well-calibrated estimates of model uncertainty, all achieved with minimal computational overhead compared to traditional deep self-supervised ensembles. To evaluate the effectiveness of our approach, we conducted extensive experiments across various tasks, including in-distribution generalization, out-of-distribution detection, dataset corruption, and semi-supervised settings. The results demonstrate that our method significantly improves prediction reliability. Our approach not only achieves excellent accuracy but also enhances calibration, surpassing baseline performance across a wide range of self-supervised architectures in computer vision, natural language processing, and genomics data.

Mohamed Karim Belaid, Dorra El Mekki, Maximilian Rabus et al.

With the rapid growth of data availability and usage, quantifying the added value of each training data point has become a crucial process in the field of artificial intelligence. The Shapley values have been recognized as an effective method for data valuation, enabling efficient training set summarization, acquisition, and outlier removal. In this paper, we introduce "STI-KNN", an innovative algorithm that calculates the exact pair-interaction Shapley values for KNN models in O(t n^2) time, which is a significant improvement over the O(2^n)$ time complexity of baseline methods. By using STI-KNN, we can efficiently and accurately evaluate the value of individual data points, leading to improved training outcomes and ultimately enhancing the effectiveness of artificial intelligence applications.

Amirhossein Vahidi, Simon Schoßer, Lisa Wimmer et al.

In this paper, we propose a novel probabilistic self-supervised learning via Scoring Rule Minimization (ProSMIN), which leverages the power of probabilistic models to enhance representation quality and mitigate collapsing representations. Our proposed approach involves two neural networks; the online network and the target network, which collaborate and learn the diverse distribution of representations from each other through knowledge distillation. By presenting the input samples in two augmented formats, the online network is trained to predict the target network representation of the same sample under a different augmented view. The two networks are trained via our new loss function based on proper scoring rules. We provide a theoretical justification for ProSMIN's convergence, demonstrating the strict propriety of its modified scoring rule. This insight validates the method's optimization process and contributes to its robustness and effectiveness in improving representation quality. We evaluate our probabilistic model on various downstream tasks, such as in-distribution generalization, out-of-distribution detection, dataset corruption, low-shot learning, and transfer learning. Our method achieves superior accuracy and calibration, surpassing the self-supervised baseline in a wide range of experiments on large-scale datasets like ImageNet-O and ImageNet-C, ProSMIN demonstrates its scalability and real-world applicability.

Jonas Hanselle, Stefan Heid, Johannes Fürnkranz et al.

A scoring system is a simple decision model that checks a set of features, adds a certain number of points to a total score for each feature that is satisfied, and finally makes a decision by comparing the total score to a threshold. Scoring systems have a long history of active use in safety-critical domains such as healthcare and justice, where they provide guidance for making objective and accurate decisions. Given their genuine interpretability, the idea of learning scoring systems from data is obviously appealing from the perspective of explainable AI. In this paper, we propose a practically motivated extension of scoring systems called probabilistic scoring lists (PSL), as well as a method for learning PSLs from data. Instead of making a deterministic decision, a PSL represents uncertainty in the form of probability distributions, or, more generally, probability intervals. Moreover, in the spirit of decision lists, a PSL evaluates features one by one and stops as soon as a decision can be made with enough confidence. To evaluate our approach, we conduct a case study in the medical domain.

Duc Anh Nguyen, Ron Levie, Julian Lienen et al.

The notion of neural collapse refers to several emergent phenomena that have been empirically observed across various canonical classification problems. During the terminal phase of training a deep neural network, the feature embedding of all examples of the same class tend to collapse to a single representation, and the features of different classes tend to separate as much as possible. Neural collapse is often studied through a simplified model, called the unconstrained feature representation, in which the model is assumed to have "infinite expressivity" and can map each data point to any arbitrary representation. In this work, we propose a more realistic variant of the unconstrained feature representation that takes the limited expressivity of the network into account. Empirical evidence suggests that the memorization of noisy data points leads to a degradation (dilation) of the neural collapse. Using a model of the memorization-dilation (M-D) phenomenon, we show one mechanism by which different losses lead to different performances of the trained network on noisy data. Our proofs reveal why label smoothing, a modification of cross-entropy empirically observed to produce a regularization effect, leads to improved generalization in classification tasks.

Elvin Hajizada, Michael Neumeier, Edward Paxon Frady et al.

Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, both on-device processing and learning are essential for privacy and low-latency adaptation. Event cameras address the efficiency of visual sensing with sparse, asynchronous output that is naturally compatible with neuromorphic processing. Yet no prior system has deployed a continual on-device learning pipeline for event-based action recognition using neuromorphic hardware. We present CLANE, Continual Learning of Actions on Neuromorphic Hardware from Event Cameras, deployed end-to-end on Intel Loihi 2. CLANE combines a spiking 2D CNN for spatiotemporal feature extraction with CLP-SNN as its on-chip learning head, extended to action clips via a Temporal Aggregation Layer and a fixed-point Normalization Layer, both novel Loihi 2 modules. On THU E-ACT-50, a 50-class dataset captured under real-world conditions, CLANE achieves 70.4% accuracy in a continual learning task while delivering more than 100x energy reduction and 16x lower latency over a sequential CNN+GRU+CLP edge GPU baseline, validated through iso-algorithm cross-platform benchmarking across three evaluation levels.

Jonas Hanselle, Valentin Margraf, Clemens Damke et al.

The literature has proposed various robust alternatives to empirical risk minimisation to address failure modes such as distribution shift, label noise and finite-sample degeneracies. Examples include distributionally robust optimization, label smoothing, vicinal risk minimization, and Mixup. However, such approaches are typically developed in isolation, forcing practitioners to commit a priori to a single failure mode even when the dominant mode for the task is unclear. To address this, we organize a broad class of existing methods along three common design axes and derive a tractable training procedure that decomposes robust learning into sequential stages (reference distribution enrichment, input-space perturbation, label-space perturbation, and sample-level aggregation), each with a choice of stance (pessimistic, neutral, or optimistic). This results in a unified design space in which joint hyperparameter optimization can compose and configure robustness strategies suited to the task at hand. Across tabular, image, and reward modeling benchmarks, joint hyperparameter optimization is competitive with the best single-method baseline in each setting, offering a reliable default for practitioners who do not know a priori which failure mode dominates their task.

Timo Kaufmann, Yannick Metz, Daniel Keim et al.

Binary choices, as often used for reinforcement learning from human feedback (RLHF), convey only the direction of a preference. A person may choose apples over oranges and bananas over grapes, but which preference is stronger? Strength is crucial for decision-making under uncertainty and generalization of preference models, but hard to measure reliably. Metadata such as response times and inter-annotator agreement can serve as proxies for strength, but are often noisy and confounded. We propose ResponseRank to address the challenge of learning from noisy strength signals. Our method uses relative differences in proxy signals to rank responses to pairwise comparisons by their inferred preference strength. To control for systemic variation, we compare signals only locally within carefully constructed strata. This enables robust learning of utility differences consistent with strength-derived rankings while making minimal assumptions about the strength signal. Our contributions are threefold: (1) ResponseRank, a novel method that robustly learns preference strength by leveraging locally valid relative strength signals; (2) empirical evidence of improved sample efficiency and robustness across diverse tasks: synthetic preference learning (with simulated response times), language modeling (with annotator agreement), and RL control tasks (with simulated episode returns); and (3) the Pearson Distance Correlation (PDC), a novel metric that isolates cardinal utility learning from ordinal accuracy.

Clemens Damke, Eyke Hüllermeier

Graphs are commonly used in machine learning to model relationships between instances. Consider the task of predicting the political preferences of users in a social network; to solve this task one should consider, both, the features of each individual user and the relationships between them. However, oftentimes one is not interested in the label of a single instance but rather in the distribution of labels over a set of instances; e.g., when predicting the political preferences of users, the overall prevalence of a given opinion might be of higher interest than the opinion of a specific person. This label prevalence estimation task is commonly referred to as quantification learning (QL). Current QL methods for tabular data are typically based on the so-called prior probability shift (PPS) assumption which states that the label-conditional instance distributions should remain equal across the training and test data. In the graph setting, PPS generally does not hold if the shift between training and test data is structural, i.e., if the training data comes from a different region of the graph than the test data. To address such structural shifts, an importance sampling variant of the popular adjusted count quantification approach has previously been proposed. In this work, we extend the idea of structural importance sampling to the state-of-the-art KDEy quantification approach. We show that our proposed method adapts to structural shifts and outperforms standard quantification approaches.

Elvin Hajizada, Danielle Rager, Timothy Shea et al.

AI systems on edge devices face a critical challenge in open-world environments: adapting when data distributions shift and novel classes emerge. While offline training dominates current paradigms, online continual learning (OCL)--where models learn incrementally from non-stationary streams without catastrophic forgetting--remains challenging in power-constrained settings. We present a neuromorphic solution called CLP-SNN: a spiking neural network architecture for Continually Learning Prototypes and its implementation on Intel's Loihi 2 chip. Our approach introduces three innovations: (1) event-driven and spatiotemporally sparse local learning, (2) a self-normalizing three-factor learning rule maintaining weight normalization, and (3) integrated neurogenesis and metaplasticity for capacity expansion and forgetting mitigation. On OpenLORIS few-shot learning experiments, CLP-SNN achieves accuracy competitive with replay methods while being rehearsal-free. CLP-SNN delivers transformative efficiency gains: 70\times faster (0.33ms vs 23.2ms), and 5,600\times more energy efficient (0.05mJ vs 281mJ) than the best alternative OCL on edge GPU. This demonstrates that co-designed brain-inspired algorithms and neuromorphic hardware can break traditional accuracy-efficiency trade-offs for future edge AI systems.

Darius Masoum Zadeh-Jousdani, Elvin Hajizada, Eyke Hüllermeier

Robotic systems operating at the edge require efficient online learning algorithms that can continuously adapt to changing environments while processing streaming sensory data. Traditional backpropagation, while effective, conflicts with biological plausibility principles and may be suboptimal for continuous adaptation scenarios. The Predictive Coding (PC) framework offers a biologically plausible alternative with local, Hebbian-like update rules, making it suitable for neuromorphic hardware implementation. However, PC's main limitation is its computational overhead due to multiple inference iterations during training. We present Predictive Coding Network with Temporal Amortization (PCN-TA), which preserves latent states across temporal frames. By leveraging temporal correlations, PCN-TA significantly reduces computational demands while maintaining learning performance. Our experiments on the COIL-20 robotic perception dataset demonstrate that PCN-TA achieves 10% fewer weight updates compared to backpropagation and requires 50% fewer inference steps than baseline PC networks. These efficiency gains directly translate to reduced computational overhead for moving another step toward edge deployment and real-time adaptation support in resource-constrained robotic systems. The biologically-inspired nature of our approach also makes it a promising candidate for future neuromorphic hardware implementations, enabling efficient online learning at the edge.

Clemens Damke, Eyke Hüllermeier

In this work, we study the influence of domain-specific characteristics when defining a meaningful notion of predictive uncertainty on graph data. Previously, the so-called Graph Posterior Network (GPN) model has been proposed to quantify uncertainty in node classification tasks. Given a graph, it uses Normalizing Flows (NFs) to estimate class densities for each node independently and converts those densities into Dirichlet pseudo-counts, which are then dispersed through the graph using the personalized Page-Rank algorithm. The architecture of GPNs is motivated by a set of three axioms on the properties of its uncertainty estimates. We show that those axioms are not always satisfied in practice and therefore propose the family of Committe-based Uncertainty Quantification Graph Neural Networks (CUQ-GNNs), which combine standard Graph Neural Networks with the NF-based uncertainty estimation of Posterior Networks (PostNets). This approach adapts more flexibly to domain-specific demands on the properties of uncertainty estimates. We compare CUQ-GNN against GPN and other uncertainty quantification approaches on common node classification benchmarks and show that it is effective at producing useful uncertainty estimates.

Viktor Bengs, Björn Haddenhorst, Eyke Hüllermeier

We consider the task of identifying the Copeland winner(s) in a dueling bandits problem with ternary feedback. This is an underexplored but practically relevant variant of the conventional dueling bandits problem, in which, in addition to strict preference between two arms, one may observe feedback in the form of an indifference. We provide a lower bound on the sample complexity for any learning algorithm finding the Copeland winner(s) with a fixed error probability. Moreover, we propose POCOWISTA, an algorithm with a sample complexity that almost matches this lower bound, and which shows excellent empirical performance, even for the conventional dueling bandits problem. For the case where the preference probabilities satisfy a specific type of stochastic transitivity, we provide a refined version with an improved worst case sample complexity.

Sascha Henzgen, Eyke Hüllermeier

Measures of rank correlation are commonly used in statistics to capture the degree of concordance between two orderings of the same set of items. Standard measures like Kendall's tau and Spearman's rho coefficient put equal emphasis on each position of a ranking. Yet, motivated by applications in which some of the positions (typically those on the top) are more important than others, a few weighted variants of these measures have been proposed. Most of these generalizations fail to meet desirable formal properties, however. Besides, they are often quite inflexible in the sense of committing to a fixed weighing scheme. In this paper, we propose a weighted rank correlation measure on the basis of fuzzy order relations. Our measure, called scaled gamma, is related to Goodman and Kruskal's gamma rank correlation. It is parametrized by a fuzzy equivalence relation on the rank positions, which in turn is specified conveniently by a so-called scaling function. This approach combines soundness with flexibility: it has a sound formal foundation and allows for weighing rank positions in a flexible way.

Mohamed Karim Belaid, Eyke Hüllermeier, Maximilian Rabus et al.

In recent years, Explainable AI (xAI) attracted a lot of attention as various countries turned explanations into a legal right. xAI allows for improving models beyond the accuracy metric by, e.g., debugging the learned pattern and demystifying the AI's behavior. The widespread use of xAI brought new challenges. On the one hand, the number of published xAI algorithms underwent a boom, and it became difficult for practitioners to select the right tool. On the other hand, some experiments did highlight how easy data scientists could misuse xAI algorithms and misinterpret their results. To tackle the issue of comparing and correctly using feature importance xAI algorithms, we propose Compare-xAI, a benchmark that unifies all exclusive functional testing methods applied to xAI algorithms. We propose a selection protocol to shortlist non-redundant functional tests from the literature, i.e., each targeting a specific end-user requirement in explaining a model. The benchmark encapsulates the complexity of evaluating xAI methods into a hierarchical scoring of three levels, namely, targeting three end-user groups: researchers, practitioners, and laymen in xAI. The most detailed level provides one score per test. The second level regroups tests into five categories (fidelity, fragility, stability, simplicity, and stress tests). The last level is the aggregated comprehensibility score, which encapsulates the ease of correctly interpreting the algorithm's output in one easy to compare value. Compare-xAI's interactive user interface helps mitigate errors in interpreting xAI results by quickly listing the recommended xAI solutions for each ML task and their current limitations. The benchmark is made available at https://karim-53.github.io/cxai/

Jasmin Brandt, Elias Schede, Viktor Bengs et al.

We study the algorithm configuration (AC) problem, in which one seeks to find an optimal parameter configuration of a given target algorithm in an automated way. Recently, there has been significant progress in designing AC approaches that satisfy strong theoretical guarantees. However, a significant gap still remains between the practical performance of these approaches and state-of-the-art heuristic methods. To this end, we introduce AC-Band, a general approach for the AC problem based on multi-armed bandits that provides theoretical guarantees while exhibiting strong practical performance. We show that AC-Band requires significantly less computation time than other AC approaches providing theoretical guarantees while still yielding high-quality configurations.

Julian Lienen, Caglar Demir, Eyke Hüllermeier

In semi-supervised learning, the paradigm of self-training refers to the idea of learning from pseudo-labels suggested by the learner itself. Across various domains, corresponding methods have proven effective and achieve state-of-the-art performance. However, pseudo-labels typically stem from ad-hoc heuristics, relying on the quality of the predictions though without guaranteeing their validity. One such method, so-called credal self-supervised learning, maintains pseudo-supervision in the form of sets of (instead of single) probability distributions over labels, thereby allowing for a flexible yet uncertainty-aware labeling. Again, however, there is no justification beyond empirical effectiveness. To address this deficiency, we make use of conformal prediction, an approach that comes with guarantees on the validity of set-valued predictions. As a result, the construction of credal sets of labels is supported by a rigorous theoretical foundation, leading to better calibrated and less error-prone supervision for unlabeled data. Along with this, we present effective algorithms for learning from credal self-supervision. An empirical study demonstrates excellent calibration properties of the pseudo-supervision, as well as the competitiveness of our method on several benchmark datasets.

Svenja Uhlemeyer, Julian Lienen, Eyke Hüllermeier et al.

For open world applications, deep neural networks (DNNs) need to be aware of previously unseen data and adaptable to evolving environments. Furthermore, it is desirable to detect and learn novel classes which are not included in the DNNs underlying set of semantic classes in an unsupervised fashion. The method proposed in this article builds upon anomaly detection to retrieve out-of-distribution (OoD) data as candidates for new classes. We thereafter extend the DNN by $k$ empty classes and fine-tune it on the OoD data samples. To this end, we introduce two loss functions, which 1) entice the DNN to assign OoD samples to the empty classes and 2) to minimize the inner-class feature distances between them. Thus, instead of ground truth which contains labels for the different novel classes, the DNN obtains a single OoD label together with a distance matrix, which is computed in advance. We perform several experiments for image classification and semantic segmentation, which demonstrate that a DNN can extend its own semantic space by multiple classes without having access to ground truth.

Santo M. A. R. Thies, Hubert Baniecki, R. Teal Witter et al.

Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this limitation, we introduce ProxySHAP. ProxySHAP reconciles the high sample efficiency of tree-based proxy models with a principled path to consistency via residual correction. On a theoretical level, we derive a polynomial-time generalization of interventional TreeSHAP to compute exact interaction indices for tree ensembles, successfully bypassing exponential tree-depth dependencies in prior methods. Furthermore, we formally analyze the residual adjustment strategy, characterizing the specific conditions under which Maximum Sample Reuse (MSR) corrects proxy bias without its variance scaling exponentially with interaction size. Extensive benchmarking demonstrates that ProxySHAP sets a new state-of-the-art standard for approximation quality, including in large-scale applications with thousands of features. By achieving the lowest error in both small- and large-budget regimes, ProxySHAP significantly outperforms the prior best estimators ProxySPEX and KernelSHAP-IQ, while also delivering superior performance on downstream explainability tasks.

Jasmin Brandt, Marcel Wever, Dimitrios Iliadis et al.

Hyperparameter optimization (HPO) is concerned with the automated search for the most appropriate hyperparameter configuration (HPC) of a parameterized machine learning algorithm. A state-of-the-art HPO method is Hyperband, which, however, has its own parameters that influence its performance. One of these parameters, the maximal budget, is especially problematic: If chosen too small, the budget needs to be increased in hindsight and, as Hyperband is not incremental by design, the entire algorithm must be re-run. This is not only costly but also comes with a loss of valuable knowledge already accumulated. In this paper, we propose incremental variants of Hyperband that eliminate these drawbacks, and show that these variants satisfy theoretical guarantees qualitatively similar to those for the original Hyperband with the "right" budget. Moreover, we demonstrate their practical utility in experiments with benchmark data sets.

Jiawen Wang, Pritha Gupta, Ivan Habernal et al.

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these attacks. This paper studies effective prompt injection attacks against the $\mathbf{14}$ most popular open-source LLMs on five attack benchmarks. Current metrics only consider successful attacks, whereas our proposed Attack Success Probability (ASP) also captures uncertainty in the model's response, reflecting ambiguity in attack feasibility. By comprehensively analyzing the effectiveness of prompt injection attacks, we propose a simple and effective hypnotism attack; results show that this attack causes aligned language models, including Stablelm2, Mistral, Openchat, and Vicuna, to generate objectionable behaviors, achieving around $90$% ASP. They also indicate that our ignore prefix attacks can break all $\mathbf{14}$ open-source LLMs, achieving over $60$% ASP on a multi-categorical dataset. We find that moderately well-known LLMs exhibit higher vulnerability to prompt injection attacks, highlighting the need to raise public awareness and prioritize efficient mitigation strategies.

Timo Kaufmann, Paul Weng, Viktor Bengs et al.

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of preference-based reinforcement learning (PbRL), it stands at the intersection of artificial intelligence and human-computer interaction. This positioning offers a promising avenue to enhance the performance and adaptability of intelligent systems while also improving the alignment of their objectives with human values. The training of large language models (LLMs) has impressively demonstrated this potential in recent years, where RLHF played a decisive role in directing the model's capabilities toward human objectives. This article provides a comprehensive overview of the fundamentals of RLHF, exploring the intricate dynamics between RL agents and human input. While recent focus has been on RLHF for LLMs, our survey adopts a broader perspective, examining the diverse applications and wide-ranging impact of the technique. We delve into the core principles that underpin RLHF, shedding light on the symbiotic relationship between algorithms and human feedback, and discuss the main research trends in the field. By synthesizing the current landscape of RLHF research, this article aims to provide researchers as well as practitioners with a comprehensive understanding of this rapidly growing field of research.

Marie Brockschmidt, Santo M. A. R. Thies, Maresa Schröder et al.

In causal inference, confounders are variables that influence both treatment decisions and outcomes. However, unlike as in randomized clinical trials, the treatment assignment mechanism in observational studies is not known, and it is thus unclear which covariates act as confounders. Here, we aim to generate insight for causal inference and answer: which of the observed covariates act as confounders? We introduce ConfoundingSHAP, a Shapley-based method for attributing confounding strength to individual covariates. Our contributions are twofold. First, we propose a Shapley game targeted to infer the confounding strength of the covariates. Our resulting Shapley values differ from the standard applications of SHAP explanations on causal targets, such as understanding treatment effect heterogeneity, which are ill-suited for our task. Second, as our task requires evaluating the value function over many adjustment sets, we provide a scalable TabPFN-based estimation that avoids exhaustive refitting. We demonstrate the practical value across various datasets, where ConfoundingSHAP provides informative explanations of which observed covariates drive confounding and thereby helps to provide more insight for causal inference in practice.

Kanta Yamaoka, Sumantrak Mukherjee, Thomas Gärtner et al.

Large language models (LLMs) have shown potential in identifying qualitative causal relations, but their ability to perform quantitative causal reasoning -- estimating effect sizes that parametrize functional relationships -- remains underexplored in continuous domains. We introduce Linear-LLM-SCM, a plug-and-play benchmarking framework for evaluating LLMs on linear Gaussian structural causal model (SCM) parametrization when the DAG is given. The framework decomposes a DAG into local parent-child sets and prompts an LLM to produce a regression-style structural equation per node, which is aggregated and compared against available ground-truth parameters. Our experiments show several challenges in such benchmarking tasks, namely, strong stochasticity in the results in some of the models and susceptibility to DAG misspecification via spurious edges in the continuous domains. Across models, we observe substantial variability in coefficient estimates for some settings and sensitivity to structural and semantic perturbations, highlighting current limitations of LLMs as quantitative causal parameterizers. We also open-sourced the benchmarking framework so that researchers can utilize their DAGs and any off-the-shelf LLMs plug-and-play for evaluation in their domains effortlessly.

Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier et al.

Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional benchmarks based on automatic validation struggle to measure such traits. Evaluation methods using human feedback such as Chatbot Arena have emerged as a popular alternative. These methods infer "better" personality and other desirable traits implicitly by ranking multiple model responses relative to each other. Recent issues with model releases highlight limitations of these existing opaque evaluation approaches: a major model was rolled back over sycophantic personality issues, models were observed overfitting to such feedback-based leaderboards. Despite these known issues, limited public tooling exists to explicitly evaluate model personality. We introduce Feedback Forensics: an open-source toolkit to track AI personality changes, both those encouraged by human (or AI) feedback, and those exhibited across AI models trained and evaluated on such feedback. Leveraging AI annotators, our toolkit enables investigating personality via Python API and browser app. We demonstrate the toolkit's usefulness in two steps: (A) first we analyse the personality traits encouraged in popular human feedback datasets including Chatbot Arena, MultiPref and PRISM; and (B) then use our toolkit to analyse how much popular models exhibit such traits. We release (1) our Feedback Forensics toolkit alongside (2) a web app tracking AI personality in popular models and feedback datasets as well as (3) the underlying annotation data at https://github.com/rdnfn/feedback-forensics.

Valentin Margraf, Marcel Wever, Sandra Gilhuber et al.

In settings where only a budgeted amount of labeled data can be afforded, active learning seeks to devise query strategies for selecting the most informative data points to be labeled, aiming to enhance learning algorithms' efficiency and performance. Numerous such query strategies have been proposed and compared in the active learning literature. However, the community still lacks standardized benchmarks for comparing the performance of different query strategies. This particularly holds for the combination of query strategies with different learning algorithms into active learning pipelines and examining the impact of the learning algorithm choice. To close this gap, we propose ALPBench, which facilitates the specification, execution, and performance monitoring of active learning pipelines. It has built-in measures to ensure evaluations are done reproducibly, saving exact dataset splits and hyperparameter settings of used algorithms. In total, ALPBench consists of 86 real-world tabular classification datasets and 5 active learning settings, yielding 430 active learning problems. To demonstrate its usefulness and broad compatibility with various learning algorithms and query strategies, we conduct an exemplary study evaluating 9 query strategies paired with 8 learning algorithms in 2 different settings. We provide ALPBench here: https://github.com/ValentinMargraf/ActiveLearningPipelines.

Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier et al.

Feedback data is widely used for fine-tuning and evaluating state-of-the-art AI models. Pairwise text preferences, where human or AI annotators select the "better" of two options, are particularly common. Such preferences are used to train (reward) models or to rank models with aggregate statistics. For many applications it is desirable to understand annotator preferences in addition to modelling them - not least because extensive prior work has shown various unintended biases in preference datasets. Yet, preference datasets remain challenging to interpret. Neither black-box reward models nor statistics can answer why one text is preferred over another. Manual interpretation of the numerous (long) response pairs is usually equally infeasible. In this paper, we introduce the Inverse Constitutional AI (ICAI) problem, formulating the interpretation of pairwise text preference data as a compression task. In constitutional AI, a set of principles (a constitution) is used to provide feedback and fine-tune AI models. ICAI inverts this process: given a feedback dataset, we aim to extract a constitution that best enables a large language model (LLM) to reconstruct the original annotations. We propose a corresponding ICAI algorithm and validate its generated constitutions quantitatively based on annotation reconstruction accuracy on several datasets: (a) synthetic feedback data with known principles; (b) AlpacaEval cross-annotated human feedback data; (c) crowdsourced Chatbot Arena data; and (d) PRISM data from diverse demographic groups. As a short and interpretable representation of the original dataset, generated constitutions have many potential use cases: help identify undesirable annotator biases, understand model performance better, scale feedback to unseen data, or adapt models to individual user or group preferences. We release the source code at https://github.com/rdnfn/icai.

Michael Dellnitz, Eyke Hüllermeier, Marvin Lücke et al.

Many problems in science and engineering require an efficient numerical approximation of integrals or solutions to differential equations. For systems with rapidly changing dynamics, an equidistant discretization is often inadvisable as it either results in prohibitively large errors or computational effort. To this end, adaptive schemes, such as solvers based on Runge--Kutta pairs, have been developed which adapt the step size based on local error estimations at each step. While the classical schemes apply very generally and are highly efficient on regular systems, they can behave sub-optimal when an inefficient step rejection mechanism is triggered by structurally complex systems such as chaotic systems. To overcome these issues, we propose a method to tailor numerical schemes to the problem class at hand. This is achieved by combining simple, classical quadrature rules or ODE solvers with data-driven time-stepping controllers. Compared with learning solution operators to ODEs directly, it generalises better to unseen initial data as our approach employs classical numerical schemes as base methods. At the same time it can make use of identified structures of a problem class and, therefore, outperforms state-of-the-art adaptive schemes. Several examples demonstrate superior efficiency. Source code is available at https://github.com/lueckem/quadrature-ML.

Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer et al.

While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box models. As a remedy, the Shapley value (SV) is a well-known concept in explainable artificial intelligence (XAI) research for quantifying additive feature attributions of predictions. The model-specific TreeSHAP methodology solves the exponential complexity for retrieving exact SVs from tree-based models. Expanding beyond individual feature attribution, Shapley interactions reveal the impact of intricate feature interactions of any order. In this work, we present TreeSHAP-IQ, an efficient method to compute any-order additive Shapley interactions for predictions of tree-based models. TreeSHAP-IQ is supported by a mathematical framework that exploits polynomial arithmetic to compute the interaction scores in a single recursive traversal of the tree, akin to Linear TreeSHAP. We apply TreeSHAP-IQ on state-of-the-art tree ensembles and explore interactions on well-established benchmark datasets.

Mira Jürgens, Nis Meinert, Viktor Bengs et al.

Trustworthy ML systems should not only return accurate predictions, but also a reliable representation of their uncertainty. Bayesian methods are commonly used to quantify both aleatoric and epistemic uncertainty, but alternative approaches, such as evidential deep learning methods, have become popular in recent years. The latter group of methods in essence extends empirical risk minimization (ERM) for predicting second-order probability distributions over outcomes, from which measures of epistemic (and aleatoric) uncertainty can be extracted. This paper presents novel theoretical insights of evidential deep learning, highlighting the difficulties in optimizing second-order loss functions and interpreting the resulting epistemic uncertainty measures. With a systematic setup that covers a wide range of approaches for classification, regression and counts, it provides novel insights into issues of identifiability and convergence in second-order loss minimization, and the relative (rather than absolute) nature of epistemic uncertainty measures.

Theodore Papamarkou, Pierre Alquier, Matthias Bauer et al.

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many resources to invest. While the usefulness and feasibility of Bayesian approaches remain unclear for LLM inference, this position paper argues that the control layer of an agentic AI system (that orchestrates LLMs and tools) is a clear case where Bayesian principles should shine. Bayesian decision theory provides a framework for agentic systems that can help to maintain beliefs over task-relevant latent quantities, to update these beliefs from observed agentic and human-AI interactions, and to choose actions. Making LLMs themselves explicitly Bayesian belief-updating engines remains computationally intensive and conceptually nontrivial as a general modeling target. In contrast, this paper argues that coherent decision-making requires Bayesian principles at the orchestration level of the agentic system, not necessarily the LLM agent parameters. This paper articulates practical properties for Bayesian control that fit modern agentic AI systems and human-AI collaboration, and provides concrete examples and design patterns to illustrate how calibrated beliefs and utility-aware policies can improve agentic AI orchestration.

Moritz Herrmann, F. Julian D. Lange, Katharina Eggensperger et al.

We warn against a common but incomplete understanding of empirical research in machine learning that leads to non-replicable results, makes findings unreliable, and threatens to undermine progress in the field. To overcome this alarming situation, we call for more awareness of the plurality of ways of gaining knowledge experimentally but also of some epistemic limitations. In particular, we argue most current empirical machine learning research is fashioned as confirmatory research while it should rather be considered exploratory.