Florian Pfisterer

Lennart Schneider, Florian Pfisterer, Janek Thomas et al.

The goal of Quality Diversity Optimization is to generate a collection of diverse yet high-performing solutions to a given problem at hand. Typical benchmark problems are, for example, finding a repertoire of robot arm configurations or a collection of game playing strategies. In this paper, we propose a set of Quality Diversity Optimization problems that tackle hyperparameter optimization of machine learning models - a so far underexplored application of Quality Diversity Optimization. Our benchmark problems involve novel feature functions, such as interpretability or resource usage of models. To allow for fast and efficient benchmarking, we build upon YAHPO Gym, a recently proposed open source benchmarking suite for hyperparameter optimization that makes use of high performing surrogate models and returns these surrogate model predictions instead of evaluating the true expensive black box function. We present results of an initial experimental study comparing different Quality Diversity optimizers on our benchmark problems. Furthermore, we discuss future directions and challenges of Quality Diversity Optimization in the context of hyperparameter optimization.

Hilde Weerts, Florian Pfisterer, Matthias Feurer et al.

The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducing barriers for novices. However, decisions derived from ML models can reproduce, amplify, or even introduce unfairness in our societies, causing harm to (groups of) individuals. In response, researchers have started to propose AutoML systems that jointly optimize fairness and predictive performance to mitigate fairness-related harm. However, fairness is a complex and inherently interdisciplinary subject, and solely posing it as an optimization problem can have adverse side effects. With this work, we aim to raise awareness among developers of AutoML systems about such limitations of fairness-aware AutoML, while also calling attention to the potential of AutoML as a tool for fairness research. We present a comprehensive overview of different ways in which fairness-related harm can arise and the ensuing implications for the design of fairness-aware AutoML. We conclude that while fairness cannot be automated, fairness-aware AutoML can play an important role in the toolbox of ML practitioners. We highlight several open technical challenges for future work in this direction. Additionally, we advocate for the creation of more user-centered assistive systems designed to tackle challenges encountered in fairness work

Florian Karl, Tobias Pielok, Julia Moosbauer et al.

Hyperparameter optimization constitutes a large part of typical modern machine learning workflows. This arises from the fact that machine learning methods and corresponding preprocessing steps often only yield optimal performance when hyperparameters are properly tuned. But in many applications, we are not only interested in optimizing ML pipelines solely for predictive accuracy; additional metrics or constraints must be considered when determining an optimal configuration, resulting in a multi-objective optimization problem. This is often neglected in practice, due to a lack of knowledge and readily available software implementations for multi-objective hyperparameter optimization. In this work, we introduce the reader to the basics of multi-objective hyperparameter optimization and motivate its usefulness in applied ML. Furthermore, we provide an extensive survey of existing optimization strategies, both from the domain of evolutionary algorithms and Bayesian optimization. We illustrate the utility of MOO in several specific ML applications, considering objectives such as operating conditions, prediction time, sparseness, fairness, interpretability and robustness.

Matthias Feurer, Katharina Eggensperger, Edward Bergman et al.

Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To resolve this, we provide a novel evaluation protocol that allows measuring the generalization performance of MHPO methods and studying its capabilities for comparing two optimization experiments.

Lennart Schneider, Florian Pfisterer, Paul Kent et al.

Neural architecture search (NAS) has been studied extensively and has grown to become a research field with substantial impact. While classical single-objective NAS searches for the architecture with the best performance, multi-objective NAS considers multiple objectives that should be optimized simultaneously, e.g., minimizing resource usage along the validation error. Although considerable progress has been made in the field of multi-objective NAS, we argue that there is some discrepancy between the actual optimization problem of practical interest and the optimization problem that multi-objective NAS tries to solve. We resolve this discrepancy by formulating the multi-objective NAS problem as a quality diversity optimization (QDO) problem and introduce three quality diversity NAS optimizers (two of them belonging to the group of multifidelity optimizers), which search for high-performing yet diverse architectures that are optimal for application-specific niches, e.g., hardware constraints. By comparing these optimizers to their multi-objective counterparts, we demonstrate that quality diversity NAS in general outperforms multi-objective NAS with respect to quality of solutions and efficiency. We further show how applications and future NAS research can thrive on QDO.

Moritz Herrmann, Florian Pfisterer, Fabian Scheipl

Outlier or anomaly detection is an important task in data analysis. We discuss the problem from a geometrical perspective and provide a framework that exploits the metric structure of a data set. Our approach rests on the manifold assumption, i.e., that the observed, nominally high-dimensional data lie on a much lower dimensional manifold and that this intrinsic structure can be inferred with manifold learning methods. We show that exploiting this structure significantly improves the detection of outlying observations in high-dimensional data. We also suggest a novel, mathematically precise, and widely applicable distinction between distributional and structural outliers based on the geometry and topology of the data manifold that clarifies conceptual ambiguities prevalent throughout the literature. Our experiments focus on functional data as one class of structured high-dimensional data, but the framework we propose is completely general and we include image and graph data applications. Our results show that the outlier structure of high-dimensional and non-tabular data can be detected and visualized using manifold learning methods and quantified using standard outlier scoring methods applied to the manifold embedding vectors.

Raphael Sonabend, Florian Pfisterer, Alan Mishler et al.

Algorithmic fairness is an increasingly important field concerned with detecting and mitigating biases in machine learning models. There has been a wealth of literature for algorithmic fairness in regression and classification however there has been little exploration of the field for survival analysis. Survival analysis is the prediction task in which one attempts to predict the probability of an event occurring over time. Survival predictions are particularly important in sensitive settings such as when utilising machine learning for diagnosis and prognosis of patients. In this paper we explore how to utilise existing survival metrics to measure bias with group fairness metrics. We explore this in an empirical experiment with 29 survival datasets and 8 measures. We find that measures of discrimination are able to capture bias well whereas there is less clarity with measures of calibration and scoring rules. We suggest further areas for research including prediction-based fairness metrics for distribution predictions.

Jan Simson, Florian Pfisterer, Christoph Kern

A vast number of systems across the world use algorithmic decision making (ADM) to (partially) automate decisions that have previously been made by humans. The downstream effects of ADM systems critically depend on the decisions made during a systems' design, implementation, and evaluation, as biases in data can be mitigated or reinforced along the modeling pipeline. Many of these decisions are made implicitly, without knowing exactly how they will influence the final system. To study this issue, we draw on insights from the field of psychology and introduce the method of multiverse analysis for algorithmic fairness. In our proposed method, we turn implicit decisions during design and evaluation into explicit ones and demonstrate their fairness implications. By combining decisions, we create a grid of all possible "universes" of decision combinations. For each of these universes, we compute metrics of fairness and performance. Using the resulting dataset, one can investigate the variability and robustness of fairness scores and see how and which decisions impact fairness. We demonstrate how multiverse analyses can be used to better understand fairness implications of design and evaluation decisions using an exemplary case study of predicting public health care coverage for vulnerable populations. Our results highlight how decisions regarding the evaluation of a system can lead to vastly different fairness metrics for the same model. This is problematic, as a nefarious actor could optimise or "hack" a fairness metric to portray a discriminating model as fair merely by changing how it is evaluated. We illustrate how a multiverse analysis can help to address this issue.

Florian Pfisterer, Lennart Schneider, Julia Moosbauer et al.

When developing and analyzing new hyperparameter optimization methods, it is vital to empirically evaluate and compare them on well-curated benchmark suites. In this work, we propose a new set of challenging and relevant benchmark problems motivated by desirable properties and requirements for such benchmarks. Our new surrogate-based benchmark collection consists of 14 scenarios that in total constitute over 700 multi-fidelity hyperparameter optimization problems, which all enable multi-objective hyperparameter optimization. Furthermore, we empirically compare surrogate-based benchmarks to the more widely-used tabular benchmarks, and demonstrate that the latter may produce unfaithful results regarding the performance ranking of HPO methods. We examine and compare our benchmark collection with respect to defined requirements and propose a single-objective as well as a multi-objective benchmark suite on which we compare 7 single-objective and 7 multi-objective optimizers in a benchmark experiment. Our software is available at [https://github.com/slds-lmu/yahpo_gym].

Julia Moosbauer, Martin Binder, Lennart Schneider et al.

Automated hyperparameter optimization (HPO) has gained great popularity and is an important ingredient of most automated machine learning frameworks. The process of designing HPO algorithms, however, is still an unsystematic and manual process: Limitations of prior work are identified and the improvements proposed are -- even though guided by expert knowledge -- still somewhat arbitrary. This rarely allows for gaining a holistic understanding of which algorithmic components are driving performance, and carries the risk of overlooking good algorithmic design choices. We present a principled approach to automated benchmark-driven algorithm design applied to multifidelity HPO (MF-HPO): First, we formalize a rich space of MF-HPO candidates that includes, but is not limited to common HPO algorithms, and then present a configurable framework covering this space. To find the best candidate automatically and systematically, we follow a programming-by-optimization approach and search over the space of algorithm candidates via Bayesian optimization. We challenge whether the found design choices are necessary or could be replaced by more naive and simpler ones by performing an ablation analysis. We observe that using a relatively simple configuration, in some ways simpler than established methods, performs very well as long as some critical configuration parameters have the right value.

Lennart Schneider, Florian Pfisterer, Martin Binder et al.

Neural architecture search (NAS) promises to make deep learning accessible to non-experts by automating architecture engineering of deep neural networks. BANANAS is one state-of-the-art NAS method that is embedded within the Bayesian optimization framework. Recent experimental findings have demonstrated the strong performance of BANANAS on the NAS-Bench-101 benchmark being determined by its path encoding and not its choice of surrogate model. We present experimental results suggesting that the performance of BANANAS on the NAS-Bench-301 benchmark is determined by its acquisition function optimizer, which minimally mutates the incumbent.

Pieter Gijsbers, Florian Pfisterer, Jan N. van Rijn et al.

Hyperparameter optimization in machine learning (ML) deals with the problem of empirically learning an optimal algorithm configuration from data, usually formulated as a black-box optimization problem. In this work, we propose a zero-shot method to meta-learn symbolic default hyperparameter configurations that are expressed in terms of the properties of the dataset. This enables a much faster, but still data-dependent, configuration of the ML algorithm, compared to standard hyperparameter optimization approaches. In the past, symbolic and static default values have usually been obtained as hand-crafted heuristics. We propose an approach of learning such symbolic configurations as formulas of dataset properties from a large set of prior evaluations on multiple datasets by optimizing over a grammar of expressions using an evolutionary algorithm. We evaluate our method on surrogate empirical performance models as well as on real data across 6 ML algorithms on more than 100 datasets and demonstrate that our method indeed finds viable symbolic defaults.

David Rügamer, Chris Kolb, Cornelius Fritz et al.

In this paper we describe the implementation of semi-structured deep distributional regression, a flexible framework to learn conditional distributions based on the combination of additive regression models and deep networks. Our implementation encompasses (1) a modular neural network building system based on the deep learning library \pkg{TensorFlow} for the fusion of various statistical and deep learning approaches, (2) an orthogonalization cell to allow for an interpretable combination of different subnetworks, as well as (3) pre-processing steps necessary to set up such models. The software package allows to define models in a user-friendly manner via a formula interface that is inspired by classical statistical model frameworks such as \pkg{mgcv}. The packages' modular design and functionality provides a unique resource for both scalable estimation of complex statistical models and the combination of approaches from deep learning and statistics. This allows for state-of-the-art predictive performance while simultaneously retaining the indispensable interpretability of classical statistical models.

Florian Pargent, Florian Pfisterer, Janek Thomas et al.

Since most machine learning (ML) algorithms are designed for numerical inputs, efficiently encoding categorical variables is a crucial aspect in data analysis. A common problem are high cardinality features, i.e. unordered categorical predictor variables with a high number of levels. We study techniques that yield numeric representations of categorical variables which can then be used in subsequent ML applications. We focus on the impact of these techniques on a subsequent algorithm's predictive performance, and -- if possible -- derive best practices on when to use which technique. We conducted a large-scale benchmark experiment, where we compared different encoding strategies together with five ML algorithms (lasso, random forest, gradient boosting, k-nearest neighbors, support vector machine) using datasets from regression, binary- and multiclass- classification settings. In our study, regularized versions of target encoding (i.e. using target predictions based on the feature levels in the training set as a new numerical feature) consistently provided the best results. Traditionally widely used encodings that make unreasonable assumptions to map levels to integers (e.g. integer encoding) or to reduce the number of levels (possibly based on target information, e.g. leaf encoding) before creating binary indicator variables (one-hot or dummy encoding) were not as effective in comparison.

Ashrya Agrawal, Florian Pfisterer, Bernd Bischl et al.

We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse rather than better. A rigorous evaluation of the debiasing treatment effect requires extensive cross-validation beyond what is usually done. We demonstrate that this phenomenon can be explained as a consequence of bias-variance trade-off, with an increase in variance necessitated by imposing a fairness constraint. Follow-up experiments validate the theoretical prediction that the estimation variance depends strongly on the base rates of the protected class. Considering fairness--performance trade-offs justifies the counterintuitive notion that partial debiasing can actually yield better results in practice on out-of-sample data.

David Rügamer, Florian Pfisterer, Bernd Bischl

We present neural mixture distributional regression (NMDR), a holistic framework to estimate complex finite mixtures of distributional regressions defined by flexible additive predictors. Our framework is able to handle a large number of mixtures of potentially different distributions in high-dimensional settings, allows for efficient and scalable optimization and can be applied to recent concepts that combine structured regression models with deep neural networks. While many existing approaches for mixture models address challenges in optimization of such and provide results for convergence under specific model assumptions, our approach is assumption-free and instead makes use of optimizers well-established in deep learning. Through extensive numerical experiments and a high-dimensional deep learning application we provide evidence that the proposed approach is competitive to existing approaches and works well in more complex scenarios.

Florian Pfisterer, Laura Beggel, Xudong Sun et al.

Time series classification problems have drawn increasing attention in the machine learning and statistical community. Closely related is the field of functional data analysis (FDA): it refers to the range of problems that deal with the analysis of data that is continuously indexed over some domain. While often employing different methods, both fields strive to answer similar questions, a common example being classification or regression problems with functional covariates. We study methods from functional data analysis, such as functional generalized additive models, as well as functionality to concatenate (functional-) feature extraction or basis representations with traditional machine learning algorithms like support vector machines or classification trees. In order to assess the methods and implementations, we run a benchmark on a wide variety of representative (time series) data sets, with in-depth analysis of empirical results, and strive to provide a reference ranking for which method(s) to use for non-expert practitioners. Additionally, we provide a software framework in R for functional data analysis for supervised learning, including machine learning and more linear approaches from statistics. This allows convenient access, and in connection with the machine-learning toolbox mlr, those methods can now also be tuned and benchmarked.

Florian Pfisterer, Janek Thomas, Bernd Bischl

Building models from data is an integral part of the majority of data science workflows. While data scientists are often forced to spend the majority of the time available for a given project on data cleaning and exploratory analysis, the time available to practitioners to build actual models from data is often rather short due to time constraints for a given project. AutoML systems are currently rising in popularity, as they can build powerful models without human oversight. In this position paper, we aim to discuss the impact of the rising popularity of such systems and how a user-centered interface for such systems could look like. More importantly, we also want to point out features that are currently missing in those systems and start to explore better usability of such systems from a data-scientists perspective.

Florian Pfisterer, Stefan Coors, Janek Thomas et al.

AutoML systems are currently rising in popularity, as they can build powerful models without human oversight. They often combine techniques from many different sub-fields of machine learning in order to find a model or set of models that optimize a user-supplied criterion, such as predictive performance. The ultimate goal of such systems is to reduce the amount of time spent on menial tasks, or tasks that can be solved better by algorithms while leaving decisions that require human intelligence to the end-user. In recent years, the importance of other criteria, such as fairness and interpretability, and many others have become more and more apparent. Current AutoML frameworks either do not allow to optimize such secondary criteria or only do so by limiting the system's choice of models and preprocessing steps. We propose to optimize additional criteria defined by the user directly to guide the search towards an optimal machine learning pipeline. In order to demonstrate the need and usefulness of our approach, we provide a simple multi-criteria AutoML system and showcase an exemplary application.

Xudong Sun, Andrea Bommert, Florian Pfisterer et al.

A novel machine learning optimization process coined Restrictive Federated Model Selection (RFMS) is proposed under the scenario, for example, when data from healthcare units can not leave the site it is situated on and it is forbidden to carry out training algorithms on remote data sites due to either technical or privacy and trust concerns. To carry out a clinical research under this scenario, an analyst could train a machine learning model only on local data site, but it is still possible to execute a statistical query at a certain cost in the form of sending a machine learning model to some of the remote data sites and get the performance measures as feedback, maybe due to prediction being usually much cheaper. Compared to federated learning, which is optimizing the model parameters directly by carrying out training across all data sites, RFMS trains model parameters only on one local data site but optimizes hyper-parameters across other data sites jointly since hyper-parameters play an important role in machine learning performance. The aim is to get a Pareto optimal model with respective to both local and remote unseen prediction losses, which could generalize well across data sites. In this work, we specifically consider high dimensional data with shifted distributions over data sites. As an initial investigation, Bayesian Optimization especially multi-objective Bayesian Optimization is used to guide an adaptive hyper-parameter optimization process to select models under the RFMS scenario. Empirical results show that solely using the local data site to tune hyper-parameters generalizes poorly across data sites, compared to methods that utilize the local and remote performances. Furthermore, in terms of dominated hypervolumes, multi-objective Bayesian Optimization algorithms show increased performance across multiple data sites among other candidates.

Florian Pfisterer, Jan N. van Rijn, Philipp Probst et al.

The performance of modern machine learning methods highly depends on their hyperparameter configurations. One simple way of selecting a configuration is to use default settings, often proposed along with the publication and implementation of a new algorithm. Those default values are usually chosen in an ad-hoc manner to work good enough on a wide variety of datasets. To address this problem, different automatic hyperparameter configuration algorithms have been proposed, which select an optimal configuration per dataset. This principled approach usually improves performance but adds additional algorithmic complexity and computational costs to the training procedure. As an alternative to this, we propose learning a set of complementary default values from a large database of prior empirical results. Selecting an appropriate configuration on a new dataset then requires only a simple, efficient and embarrassingly parallel search over this set. We demonstrate the effectiveness and efficiency of the approach we propose in comparison to random search and Bayesian Optimization.

Julia Schiffner, Bernd Bischl, Michel Lang et al.

This document provides and in-depth introduction to the mlr framework for machine learning experiments in R.