Marco Pegoraro

Elisabetta Benevento, Marco Pegoraro, Mattia Antoniazzi et al.

The discipline of process mining has a solid track record of successful applications to the healthcare domain. Within such research space, we conducted a case study related to the Intensive Care Unit (ICU) ward of the Uniklinik Aachen hospital in Germany. The aim of this work is twofold: developing a normative model representing the clinical guidelines for the treatment of COVID-19 patients, and analyzing the adherence of the observed behavior (recorded in the information system of the hospital) to such guidelines. We show that, through conformance checking techniques, it is possible to analyze the care process for COVID-19 patients, highlighting the main deviations from the clinical guidelines. The results provide physicians with useful indications for improving the process and ensuring service quality and patient satisfaction. We share the resulting model as an open-source BPMN file.

Mohammadreza Fani Sani, Mozhgan Vazifehdoostirani, Gyunam Park et al.

Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, most of the state-of-the-art methods for predictive monitoring require the training of complex machine learning models, which is often inefficient. Moreover, most of these methods require a hyper-parameter optimization that requires several repetitions of the training process which is not feasible in many real-life applications. In this paper, we propose an instance selection procedure that allows sampling training process instances for prediction models. We show that our instance selection procedure allows for a significant increase of training speed for next activity and remaining time prediction methods while maintaining reliable levels of prediction accuracy.

Mohammadreza Fani Sani, Mozhgan Vazifehdoostirani, Gyunam Park et al.

Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, state-of-the-art methods for predictive monitoring require the training of complex machine learning models, which is often inefficient. This paper proposes an instance selection procedure that allows sampling training process instances for prediction models. We show that our sampling method allows for a significant increase of training speed for next activity prediction methods while maintaining reliable levels of prediction accuracy.

Marco Pegoraro, Merih Seran Uysal, Tom-Hendrik Hülsmann et al.

Among the many sources of event data available today, a prominent one is user interaction data. User activity may be recorded during the use of an application or website, resulting in a type of user interaction data often called click data. An obstacle to the analysis of click data using process mining is the lack of a case identifier in the data. In this paper, we show a case and user study for event-case correlation on click data, in the context of user interaction events from a mobility sharing company. To reconstruct the case notion of the process, we apply a novel method to aggregate user interaction data in separate user sessions-interpreted as cases-based on neural networks. To validate our findings, we qualitatively discuss the impact of process mining analyses on the resulting well-formed event log through interviews with process experts.

Marco Pegoraro, Sanketh Vedula, Aviv A. Rosenberg et al.

Quantile regression (QR) is a statistical tool for distribution-free estimation of conditional quantiles of a target variable given explanatory features. QR is limited by the assumption that the target distribution is univariate and defined on an Euclidean domain. Although the notion of quantiles was recently extended to multi-variate distributions, QR for multi-variate distributions on manifolds remains underexplored, even though many important applications inherently involve data distributed on, e.g., spheres (climate and geological phenomena), and tori (dihedral angles in proteins). By leveraging optimal transport theory and c-concave functions, we meaningfully define conditional vector quantile functions of high-dimensional variables on manifolds (M-CVQFs). Our approach allows for quantile estimation, regression, and computation of conditional confidence sets and likelihoods. We demonstrate the approach's efficacy and provide insights regarding the meaning of non-Euclidean quantiles through synthetic and real data experiments.

Marco Pegoraro, Riccardo Marin, Arianna Rampini et al.

In graph learning, maps between graphs and their subgraphs frequently arise. For instance, when coarsening or rewiring operations are present along the pipeline, one needs to keep track of the corresponding nodes between the original and modified graphs. Classically, these maps are represented as binary node-to-node correspondence matrices and used as-is to transfer node-wise features between the graphs. In this paper, we argue that simply changing this map representation can bring notable benefits to graph learning tasks. Drawing inspiration from recent progress in geometry processing, we introduce a spectral representation for maps that is easy to integrate into existing graph learning models. This spectral representation is a compact and straightforward plug-in replacement and is robust to topological changes of the graphs. Remarkably, the representation exhibits structural properties that make it interpretable, drawing an analogy with recent results on smooth manifolds. We demonstrate the benefits of incorporating spectral maps in graph learning pipelines, addressing scenarios where a node-to-node map is not well defined, or in the absence of exact isomorphism. Our approach bears practical benefits in knowledge distillation and hierarchical learning, where we show comparable or improved performance at a fraction of the computational cost.

Marco Pegoraro, Merih Seran Uysal, Tom-Hendrik Hülsmann et al.

Modern software systems are able to record vast amounts of user actions, stored for later analysis. One of the main types of such user interaction data is click data: the digital trace of the actions of a user through the graphical elements of an application, website or software. While readily available, click data is often missing a case notion: an attribute linking events from user interactions to a specific process instance in the software. In this paper, we propose a neural network-based technique to determine a case notion for click data, thus enabling process mining and other process analysis techniques on user interaction data. We describe our method, show its scalability to datasets of large dimensions, and we validate its efficacy through a user study based on the segmented event log resulting from interaction data of a mobility sharing company. Interviews with domain experts in the company demonstrate that the case notion obtained by our method can lead to actionable process insights.

Marco Pegoraro, Jonas Seng, Dustin Heller et al.

Disciplines such as business process management and process mining aid organizations by discovering insights about processes on the basis of recorded event data. However, an obstacle to process analysis is data multi-modality: for instance, data in video form are not directly interpretable as events. In this work, we present SnapLog, an approach to extract event data from videos by converting frames to feature vectors using image embeddings and performing temporal segmentation through frame-wise similarity matrices. A generalized few-shot classification is then used to assign labels to the video segments, yielding labeled, timestamped sub-sequences of frames that are interpretable as events. Conventional process mining techniques can be used to analyze the resulting data. We show that our approach produces logs that accurately reflect the process in the videos.

Marco Pegoraro

Process mining is a subfield of process science that analyzes event data collected in databases called event logs. Recently, novel types of event data have become of interest due to the wide industrial application of process mining analyses. In this paper, we examine uncertain event data. Such data contain meta-attributes describing the amount of imprecision tied with attributes recorded in an event log. We provide examples of uncertain event data, present the state of the art in regard of uncertainty in process mining, and illustrate open challenges related to this research direction.

Marco Pegoraro

With the widespread adoption of process mining in organizations, the field of process science is seeing an increase in the demand for ad-hoc analysis techniques of non-standard event data. An example of such data are uncertain event data: events characterized by a described and quantified attribute imprecision. This paper outlines a research project aimed at developing process mining techniques able to extract insights from uncertain data. We set the basis for this research topic, recapitulate the available literature, and define a future outlook.

Arvid Lepsien, Marco Pegoraro, Frederik Fonger et al.

Various kinds of uncertainty can occur in event logs, e.g., due to flawed recording, data quality issues, or the use of probabilistic models for activity recognition. Stochastically known event logs make these uncertainties transparent by encoding multiple possible realizations for events. However, the number of realizations encoded by a stochastically known log grows exponentially with its size, making exhaustive exploration infeasible even for moderately sized event logs. Thus, considering only the top-K most probable realizations has been proposed in the literature. In this paper, we implement an efficient algorithm to calculate a top-K realization ranking of an event log under event independence within O(Kn), where n is the number of uncertain events in the log. This algorithm is used to investigate the benefit of top-K rankings over top-1 interpretations of stochastically known event logs. Specifically, we analyze the usefulness of top-K rankings against different properties of the input data. We show that the benefit of a top-K ranking depends on the length of the input event log and the distribution of the event probabilities. The results highlight the potential of top-K rankings to enhance uncertainty-aware process mining techniques.

Marco Pegoraro, Evan Atherton, Bruno Roy et al.

Learning natural body motion remains challenging due to the strong coupling between spatial geometry and temporal dynamics. Embedding motion in phase manifolds, latent spaces that capture local periodicity, has proven effective for motion prediction; however, existing approaches lack scalability and remain confined to specific settings. We introduce FunPhase, a functional periodic autoencoder that learns a phase manifold for motion and replaces discrete temporal decoding with a function-space formulation, enabling smooth trajectories that can be sampled at arbitrary temporal resolutions. FunPhase supports downstream tasks such as super-resolution and partial-body motion completion, generalizes across skeletons and datasets, and unifies motion prediction and generation within a single interpretable manifold. Our model achieves substantially lower reconstruction error than prior periodic autoencoder baselines while enabling a broader range of applications and performing on par with state-of-the-art motion generation methods.

Francesco Vitale, Marco Pegoraro, Wil M. P. van der Aalst et al.

The business processes of organizations may deviate from normal control flow due to disruptive anomalies, including unknown, skipped, and wrongly-ordered activities. To identify these control-flow anomalies, process mining can check control-flow correctness against a reference process model through conformance checking, an explainable set of algorithms that allows linking any deviations with model elements. However, the effectiveness of conformance checking-based techniques is negatively affected by noisy event data and low-quality process models. To address these shortcomings and support the development of competitive and explainable conformance checking-based techniques for control-flow anomaly detection, we propose a novel process mining-based feature extraction approach with alignment-based conformance checking. This variant aligns the deviating control flow with a reference process model; the resulting alignment can be inspected to extract additional statistics such as the number of times a given activity caused mismatches. We integrate this approach into a flexible and explainable framework for developing techniques for control-flow anomaly detection. The framework combines process mining-based feature extraction and dimensionality reduction to handle high-dimensional feature sets, achieve detection effectiveness, and support explainability. The results show that the framework techniques implementing our approach outperform the baseline conformance checking-based techniques while maintaining the explainable nature of conformance checking. We also provide an explanation of why existing conformance checking-based techniques may be ineffective.

Harry H. Beyel, Marlo Verket, Viki Peeva et al.

Process mining in healthcare presents a range of challenges when working with different types of data within the healthcare domain. There is high diversity considering the variety of data collected from healthcare processes: operational processes given by claims data, a collection of events during surgery, data related to pre-operative and post-operative care, and high-level data collections based on regular ambulant visits with no apparent events. In this case study, a data set from the last category is analyzed. We apply process-mining techniques on sparse patient heart failure data and investigate whether an information gain towards several research questions is achievable. Here, available data are transformed into an event log format, and process discovery and conformance checking are applied. Additionally, patients are split into different cohorts based on comorbidities, such as diabetes and chronic kidney disease, and multiple statistics are compared between the cohorts. Conclusively, we apply decision mining to determine whether a patient will have a cardiovascular outcome and whether a patient will die.

Tsung-Hao Huang, Tarek Junied, Marco Pegoraro et al.

Process discovery aims to automatically derive process models from historical execution data (event logs). While various process discovery algorithms have been proposed in the last 25 years, there is no consensus on a dominating discovery algorithm. Selecting the most suitable discovery algorithm remains a challenge due to competing quality measures and diverse user requirements. Manually selecting the most suitable process discovery algorithm from a range of options for a given event log is a time-consuming and error-prone task. This paper introduces ProReco, a Process discovery Recommender system designed to recommend the most appropriate algorithm based on user preferences and event log characteristics. ProReco incorporates state-of-the-art discovery algorithms, extends the feature pools from previous work, and utilizes eXplainable AI (XAI) techniques to provide explanations for its recommendations.

Marco Fumero, Marco Pegoraro, Valentino Maiorca et al.

Neural models learn data representations that lie on low-dimensional manifolds, yet modeling the relation between these representational spaces is an ongoing challenge. By integrating spectral geometry principles into neural modeling, we show that this problem can be better addressed in the functional domain, mitigating complexity, while enhancing interpretability and performances on downstream tasks. To this end, we introduce a multi-purpose framework to the representation learning community, which allows to: (i) compare different spaces in an interpretable way and measure their intrinsic similarity; (ii) find correspondences between them, both in unsupervised and weakly supervised settings, and (iii) to effectively transfer representations between distinct spaces. We validate our framework on various applications, ranging from stitching to retrieval tasks, and on multiple modalities, demonstrating that Latent Functional Maps can serve as a swiss-army knife for representation alignment.

Marco Pegoraro, Clémentine Dominé, Emanuele Rodolà et al.

Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules. In this paper, we investigate the optimal representation for predicting the binding sites in the two molecules and emphasize the importance of geometric information. Specifically, we compare different geometric deep learning methods applied to proteins' inner (I-GEP) and outer (O-GEP) structures. We incorporate 3D coordinates and spectral geometric descriptors as input features to fully leverage the geometric information. Our research suggests that surface-based models are more efficient than other methods, and our O-GEP experiments have achieved state-of-the-art results with significant performance improvements.

Marco Pegoraro, Madhavi Bangalore Shankara Narayana, Elisabetta Benevento et al.

The recent increase in the availability of medical data, possible through automation and digitization of medical equipment, has enabled more accurate and complete analysis on patients' medical data through many branches of data science. In particular, medical records that include timestamps showing the history of a patient have enabled the representation of medical information as sequences of events, effectively allowing to perform process mining analyses. In this paper, we will present some preliminary findings obtained with established process mining techniques in regard of the medical data of patients of the Uniklinik Aachen hospital affected by the recent epidemic of COVID-19. We show that process mining techniques are able to reconstruct a model of the ICU treatments for COVID patients.

Marco Pegoraro, Bianka Bakullari, Merih Seran Uysal et al.

Process mining is a scientific discipline that analyzes event data, often collected in databases called event logs. Recently, uncertain event logs have become of interest, which contain non-deterministic and stochastic event attributes that may represent many possible real-life scenarios. In this paper, we present a method to reliably estimate the probability of each of such scenarios, allowing their analysis. Experiments show that the probabilities calculated with our method closely match the true chances of occurrence of specific outcomes, enabling more trustworthy analyses on uncertain data.

Marco Pegoraro, Simone Melzi, Umberto Castellani et al.

Many natural shapes have most of their characterizing features concentrated over a few regions in space. For example, humans and animals have distinctive head shapes, while inorganic objects like chairs and airplanes are made of well-localized functional parts with specific geometric features. Often, these features are strongly correlated -- a modification of facial traits in a quadruped should induce changes to the body structure. However, in shape modelling applications, these types of edits are among the hardest ones; they require high precision, but also a global awareness of the entire shape. Even in the deep learning era, obtaining manipulable representations that satisfy such requirements is an open problem posing significant constraints. In this work, we address this problem by defining a data-driven model upon a family of linear operators (variants of the mesh Laplacian), whose spectra capture global and local geometric properties of the shape at hand. Modifications to these spectra are translated to semantically valid deformations of the corresponding surface. By explicitly decoupling the global from the local surface features, our pipeline allows to perform local edits while simultaneously maintaining a global stylistic coherence. We empirically demonstrate how our learning-based model generalizes to shape representations not seen at training time, and we systematically analyze different choices of local operators over diverse shape categories.

Marco Pegoraro, Merih Seran Uysal, David Benedikt Georgi et al.

The real-time prediction of business processes using historical event data is an important capability of modern business process monitoring systems. Existing process prediction methods are able to also exploit the data perspective of recorded events, in addition to the control-flow perspective. However, while well-structured numerical or categorical attributes are considered in many prediction techniques, almost no technique is able to utilize text documents written in natural language, which can hold information critical to the prediction task. In this paper, we illustrate the design, implementation, and evaluation of a novel text-aware process prediction model based on Long Short-Term Memory (LSTM) neural networks and natural language models. The proposed model can take categorical, numerical and textual attributes in event data into account to predict the activity and timestamp of the next event, the outcome, and the cycle time of a running process instance. Experiments show that the text-aware model is able to outperform state-of-the-art process prediction methods on simulated and real-world event logs containing textual data.

Marco Pegoraro, Merih Seran Uysal, Wil M. P. van der Aalst

The discipline of process mining aims to study processes in a data-driven manner by analyzing historical process executions, often employing Petri nets. Event data, extracted from information systems (e.g. SAP), serve as the starting point for process mining. Recently, novel types of event data have gathered interest among the process mining community, including uncertain event data. Uncertain events, process traces and logs contain attributes that are characterized by quantified imprecisions, e.g., a set of possible attribute values. The PROVED tool helps to explore, navigate and analyze such uncertain event data by abstracting the uncertain information using behavior graphs and nets, which have Petri nets semantics. Based on these constructs, the tool enables discovery and conformance checking.

Marco Pegoraro, Merih Seran Uysal, Wil M. P. van der Aalst

The strong impulse to digitize processes and operations in companies and enterprises have resulted in the creation and automatic recording of an increasingly large amount of process data in information systems. These are made available in the form of event logs. Process mining techniques enable the process-centric analysis of data, including automatically discovering process models and checking if event data conform to a given model. In this paper, we analyze the previously unexplored setting of uncertain event logs. In such event logs uncertainty is recorded explicitly, i.e., the time, activity and case of an event may be unclear or imprecise. In this work, we define a taxonomy of uncertain event logs and models, and we examine the challenges that uncertainty poses on process discovery and conformance checking. Finally, we show how upper and lower bounds for conformance can be obtained by aligning an uncertain trace onto a regular process model.

Marco Pegoraro, Merih Seran Uysal, Wil M. P. van der Aalst

Modern information systems are able to collect event data in the form of event logs. Process mining techniques allow to discover a model from event data, to check the conformance of an event log against a reference model, and to perform further process-centric analyses. In this paper, we consider uncertain event logs, where data is recorded together with explicit uncertainty information. We describe a technique to discover a directly-follows graph from such event data which retains information about the uncertainty in the process. We then present experimental results of performing inductive mining over the directly-follows graph to obtain models representing the certain and uncertain part of the process.

Marco Pegoraro, Wil M. P. van der Aalst

Nowadays, more and more process data are automatically recorded by information systems, and made available in the form of event logs. Process mining techniques enable process-centric analysis of data, including automatically discovering process models and checking if event data conform to a certain model. In this paper we analyze the previously unexplored setting of uncertain event logs: logs where quantified uncertainty is recorded together with the corresponding data. We define a taxonomy of uncertain event logs and models, and we examine the challenges that uncertainty poses on process discovery and conformance checking. Finally, we show how upper and lower bounds for conformance can be obtained aligning an uncertain trace onto a regular process model.