Heiner Stuckenschmidt

Andrej Tschalzev, Nick Erickson, Yuyang Wang et al.

Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures. At the same time, feature engineering remains a critical yet underexplored component of real-world modeling pipelines that is entirely absent from modern benchmarks, which creates an unquantified evaluation gap. In this work, we introduce TabPrep, a lightweight preprocessing pipeline composed of feature generators that are carefully designed to target three specific structural data patterns. We show that many widely used model classes exhibit predictable blind spots to these patterns and that systematic feature engineering alone can establish new peak performance. Across the TabArena benchmark, integrating TabPrep into model training and tuning consistently improves performance for tree-based, neural, linear, and foundation models, often surpassing gains achieved by model-centric innovations alone. TabPrep outperforms previous automated feature engineering approaches in performance, efficiency, and applicability across datasets, enabling integration into large-scale benchmarks. By releasing TabPrep (see https://github.com/atschalz/tabprep), we enable researchers to integrate feature engineering into their benchmarking setup, filling a longstanding gap in tabular evaluations.

Andrej Tschalzev, Sascha Marton, Stefan Lüdtke et al.

Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of model-centric evaluation setups with overly standardized data preprocessing. This paper demonstrates that such model-centric evaluations are biased, as real-world modeling pipelines often require dataset-specific preprocessing and feature engineering. Therefore, we propose a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and implement expert-level preprocessing pipelines for each dataset. We conduct experiments with different preprocessing pipelines and hyperparameter optimization (HPO) regimes to quantify the impact of model selection, HPO, feature engineering, and test-time adaptation. Our main findings are: 1. After dataset-specific feature engineering, model rankings change considerably, performance differences decrease, and the importance of model selection reduces. 2. Recent models, despite their measurable progress, still significantly benefit from manual feature engineering. This holds true for both tree-based models and neural networks. 3. While tabular data is typically considered static, samples are often collected over time, and adapting to distribution shifts can be important even in supposedly static data. These insights suggest that research efforts should be directed toward a data-centric perspective, acknowledging that tabular data requires feature engineering and often exhibits temporal characteristics. Our framework is available under: https://github.com/atschalz/dc_tabeval.

Sascha Marton, Stefan Lüdtke, Christian Bartelt et al.

Despite the success of deep learning for text and image data, tree-based ensemble models are still state-of-the-art for machine learning with heterogeneous tabular data. However, there is a significant need for tabular-specific gradient-based methods due to their high flexibility. In this paper, we propose $\text{GRANDE}$, $\text{GRA}$die$\text{N}$t-Based $\text{D}$ecision Tree $\text{E}$nsembles, a novel approach for learning hard, axis-aligned decision tree ensembles using end-to-end gradient descent. GRANDE is based on a dense representation of tree ensembles, which affords to use backpropagation with a straight-through operator to jointly optimize all model parameters. Our method combines axis-aligned splits, which is a useful inductive bias for tabular data, with the flexibility of gradient-based optimization. Furthermore, we introduce an advanced instance-wise weighting that facilitates learning representations for both, simple and complex relations, within a single model. We conducted an extensive evaluation on a predefined benchmark with 19 classification datasets and demonstrate that our method outperforms existing gradient-boosting and deep learning frameworks on most datasets. The method is available under: https://github.com/s-marton/GRANDE

Sascha Marton, Stefan Lüdtke, Christian Bartelt et al.

We consider generating explanations for neural networks in cases where the network's training data is not accessible, for instance due to privacy or safety issues. Recently, $\mathcal{I}$-Nets have been proposed as a sample-free approach to post-hoc, global model interpretability that does not require access to training data. They formulate interpretation as a machine learning task that maps network representations (parameters) to a representation of an interpretable function. In this paper, we extend the $\mathcal{I}$-Net framework to the cases of standard and soft decision trees as surrogate models. We propose a suitable decision tree representation and design of the corresponding $\mathcal{I}$-Net output layers. Furthermore, we make $\mathcal{I}$-Nets applicable to real-world tasks by considering more realistic distributions when generating the $\mathcal{I}$-Net's training data. We empirically evaluate our approach against traditional global, post-hoc interpretability approaches and show that it achieves superior results when the training data is not accessible.

Sascha Marton, Tim Grams, Florian Vogt et al.

Reinforcement learning (RL) has seen significant success across various domains, but its adoption is often limited by the black-box nature of neural network policies, making them difficult to interpret. In contrast, symbolic policies allow representing decision-making strategies in a compact and interpretable way. However, learning symbolic policies directly within on-policy methods remains challenging. In this paper, we introduce SYMPOL, a novel method for SYMbolic tree-based on-POLicy RL. SYMPOL employs a tree-based model integrated with a policy gradient method, enabling the agent to learn and adapt its actions while maintaining a high level of interpretability. We evaluate SYMPOL on a set of benchmark RL tasks, demonstrating its superiority over alternative tree-based RL approaches in terms of performance and interpretability. Unlike existing methods, it enables gradient-based, end-to-end learning of interpretable, axis-aligned decision trees within standard on-policy RL algorithms. Therefore, SYMPOL can become the foundation for a new class of interpretable RL based on decision trees. Our implementation is available under: https://github.com/s-marton/sympol

David Friede, Christian Reimers, Heiner Stuckenschmidt et al.

Recent successes in image generation, model-based reinforcement learning, and text-to-image generation have demonstrated the empirical advantages of discrete latent representations, although the reasons behind their benefits remain unclear. We explore the relationship between discrete latent spaces and disentangled representations by replacing the standard Gaussian variational autoencoder (VAE) with a tailored categorical variational autoencoder. We show that the underlying grid structure of categorical distributions mitigates the problem of rotational invariance associated with multivariate Gaussian distributions, acting as an efficient inductive prior for disentangled representations. We provide both analytical and empirical findings that demonstrate the advantages of discrete VAEs for learning disentangled representations. Furthermore, we introduce the first unsupervised model selection strategy that favors disentangled representations.

Nils Wilken, Lea Cohausz, Christian Bartelt et al.

Goal recognition is an important problem in many application domains (e.g., pervasive computing, intrusion detection, computer games, etc.). In many application scenarios, it is important that goal recognition algorithms can recognize goals of an observed agent as fast as possible. However, many early approaches in the area of Plan Recognition As Planning, require quite large amounts of computation time to calculate a solution. Mainly to address this issue, recently, Pereira et al. developed an approach that is based on planning landmarks and is much more computationally efficient than previous approaches. However, the approach, as proposed by Pereira et al., also uses trivial landmarks (i.e., facts that are part of the initial state and goal description are landmarks by definition). In this paper, we show that it does not provide any benefit to use landmarks that are part of the initial state in a planning landmark based goal recognition approach. The empirical results show that omitting initial state landmarks for goal recognition improves goal recognition performance.

Lukas Kirchdorfer, Cathrin Elich, Simon Kutsche et al. · eth-zurich

With the rise of neural networks in various domains, multi-task learning (MTL) gained significant relevance. A key challenge in MTL is balancing individual task losses during neural network training to improve performance and efficiency through knowledge sharing across tasks. To address these challenges, we propose a novel task-weighting method by building on the most prevalent approach of Uncertainty Weighting and computing analytically optimal uncertainty-based weights, normalized by a softmax function with tunable temperature. Our approach yields comparable results to the combinatorially prohibitive, brute-force approach of Scalarization while offering a more cost-effective yet high-performing alternative. We conduct an extensive benchmark on various datasets and architectures. Our method consistently outperforms six other common weighting methods. Furthermore, we report noteworthy experimental findings for the practical application of MTL. For example, larger networks diminish the influence of weighting methods, and tuning the weight decay has a low impact compared to the learning rate.

Simon Ott, Christian Meilicke, Heiner Stuckenschmidt

Within this paper, we show that the evaluation protocol currently used for inductive link prediction is heavily flawed as it relies on ranking the true entity in a small set of randomly sampled negative entities. Due to the limited size of the set of negatives, a simple rule-based baseline can achieve state-of-the-art results, which simply ranks entities higher based on the validity of their type. As a consequence of these insights, we reevaluate current approaches for inductive link prediction on several benchmarks using the link prediction protocol usually applied to the transductive setting. As some inductive methods suffer from scalability issues when evaluated in this setting, we propose and apply additionally an improved sampling protocol, which does not suffer from the problem mentioned above. The results of our evaluation differ drastically from the results reported in so far.

Andrej Tschalzev, Paul Nitschke, Lukas Kirchdorfer et al.

Neural networks often assume independence among input data samples, disregarding correlations arising from inherent clustering patterns in real-world datasets (e.g., due to different sites or repeated measurements). Recently, mixed effects neural networks (MENNs) which separate cluster-specific 'random effects' from cluster-invariant 'fixed effects' have been proposed to improve generalization and interpretability for clustered data. However, existing methods only allow for approximate quantification of cluster effects and are limited to regression and binary targets with only one clustering feature. We present MC-GMENN, a novel approach employing Monte Carlo methods to train Generalized Mixed Effects Neural Networks. We empirically demonstrate that MC-GMENN outperforms existing mixed effects deep learning models in terms of generalization performance, time complexity, and quantification of inter-cluster variance. Additionally, MC-GMENN is applicable to a wide range of datasets, including multi-class classification tasks with multiple high-cardinality categorical features. For these datasets, we show that MC-GMENN outperforms conventional encoding and embedding methods, simultaneously offering a principled methodology for interpreting the effects of clustering patterns.

Nils Wilken, Lea Cohausz, Johannes Schaum et al.

Goal recognition is an important problem in many application domains (e.g., pervasive computing, intrusion detection, computer games, etc.). In many application scenarios it is important that goal recognition algorithms can recognize goals of an observed agent as fast as possible and with minimal domain knowledge. Hence, in this paper, we propose a hybrid method for online goal recognition that combines a symbolic planning landmark based approach and a data-driven goal recognition approach and evaluate it in a real-world cooking scenario. The empirical results show that the proposed method is not only significantly more efficient in terms of computation time than the state-of-the-art but also improves goal recognition performance. Furthermore, we show that the utilized planning landmark based approach, which was so far only evaluated on artificial benchmark domains, achieves also good recognition performance when applied to a real-world cooking scenario.

Nils Wilken, Lea Cohausz, Johannes Schaum et al.

An important feature of pervasive, intelligent assistance systems is the ability to dynamically adapt to the current needs of their users. Hence, it is critical for such systems to be able to recognize those goals and needs based on observations of the user's actions and state of the environment. In this work, we investigate the application of two state-of-the-art, planning-based plan recognition approaches in a real-world setting. So far, these approaches were only evaluated in artificial settings in combination with agents that act perfectly rational. We show that such approaches have difficulties when used to recognize the goals of human subjects, because human behaviour is typically not perfectly rational. To overcome this issue, we propose an extension to the existing approaches through a classification-based method trained on observed behaviour data. We empirically show that the proposed extension not only outperforms the purely planning-based- and purely data-driven goal recognition methods but is also able to recognize the correct goal more reliably, especially when only a small number of observations were seen. This substantially improves the usefulness of hybrid goal recognition approaches for intelligent assistance systems, as recognizing a goal early opens much more possibilities for supportive reactions of the system.

Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt

Outlier explanation is the task of identifying a set of features that distinguish a sample from normal data, which is important for downstream (human) decision-making. Existing methods are based on beam search in the space of feature subsets. They quickly becomes computationally expensive, as they require to run an outlier detection algorithm from scratch for each feature subset. To alleviate this problem, we propose a novel outlier explanation algorithm based on Sum-Product Networks (SPNs), a class of probabilistic circuits. Our approach leverages the tractability of marginal inference in SPNs to compute outlier scores in feature subsets. By using SPNs, it becomes feasible to perform backwards elimination instead of the usual forward beam search, which is less susceptible to missing relevant features in an explanation, especially when the number of features is large. We empirically show that our approach achieves state-of-the-art results for outlier explanation, outperforming recent search-based as well as deep learning-based explanation methods

Lukas Kirchdorfer, Robert Blümel, Timotheus Kampik et al.

Business process simulation (BPS) is a versatile technique for estimating process performance across various scenarios. Traditionally, BPS approaches employ a control-flow-first perspective by enriching a process model with simulation parameters. Although such approaches can mimic the behavior of centrally orchestrated processes, such as those supported by workflow systems, current control-flow-first approaches cannot faithfully capture the dynamics of real-world processes that involve distinct resource behavior and decentralized decision-making. Recognizing this issue, this paper introduces AgentSimulator, a resource-first BPS approach that discovers a multi-agent system from an event log, modeling distinct resource behaviors and interaction patterns to simulate the underlying process. Our experiments show that AgentSimulator achieves state-of-the-art simulation accuracy with significantly lower computation times than existing approaches while providing high interpretability and adaptability to different types of process-execution scenarios.

Nils Wilken, Lea Cohausz, Christian Bartelt et al.

We present a new approach to goal recognition that involves comparing observed facts with their expected probabilities. These probabilities depend on a specified goal g and initial state s0. Our method maps these probabilities and observed facts into a real vector space to compute heuristic values for potential goals. These values estimate the likelihood of a given goal being the true objective of the observed agent. As obtaining exact expected probabilities for observed facts in an observation sequence is often practically infeasible, we propose and empirically validate a method for approximating these probabilities. Our empirical results show that the proposed approach offers improved goal recognition precision compared to state-of-the-art techniques while reducing computational complexity.

Sascha Marton, Stefan Lüdtke, Christian Bartelt et al.

Decision Trees (DTs) are commonly used for many machine learning tasks due to their high degree of interpretability. However, learning a DT from data is a difficult optimization problem, as it is non-convex and non-differentiable. Therefore, common approaches learn DTs using a greedy growth algorithm that minimizes the impurity locally at each internal node. Unfortunately, this greedy procedure can lead to inaccurate trees. In this paper, we present a novel approach for learning hard, axis-aligned DTs with gradient descent. The proposed method uses backpropagation with a straight-through operator on a dense DT representation, to jointly optimize all tree parameters. Our approach outperforms existing methods on binary classification benchmarks and achieves competitive results for multi-class tasks. The method is available under: https://github.com/s-marton/GradTree

Keyvan Amiri Elyasi, Han van der Aa, Heiner Stuckenschmidt

We present PGTNet, an approach that transforms event logs into graph datasets and leverages graph-oriented data for training Process Graph Transformer Networks to predict the remaining time of business process instances. PGTNet consistently outperforms state-of-the-art deep learning approaches across a diverse range of 20 publicly available real-world event logs. Notably, our approach is most promising for highly complex processes, where existing deep learning approaches encounter difficulties stemming from their limited ability to learn control-flow relationships among process activities and capture long-range dependencies. PGTNet addresses these challenges, while also being able to consider multiple process perspectives during the learning process.

Julia Gastinger, Christian Meilicke, Federico Errica et al.

Temporal Knowledge Graph (TKG) Forecasting aims at predicting links in Knowledge Graphs for future timesteps based on a history of Knowledge Graphs. To this day, standardized evaluation protocols and rigorous comparison across TKG models are available, but the importance of simple baselines is often neglected in the evaluation, which prevents researchers from discerning actual and fictitious progress. We propose to close this gap by designing an intuitive baseline for TKG Forecasting based on predicting recurring facts. Compared to most TKG models, it requires little hyperparameter tuning and no iterative training. Further, it can help to identify failure modes in existing approaches. The empirical findings are quite unexpected: compared to 11 methods on five datasets, our baseline ranks first or third in three of them, painting a radically different picture of the predictive quality of the state of the art.

Andrej Tschalzev, Lennart Purucker, Stefan Lüdtke et al.

Data repositories have accumulated a large number of tabular datasets from various domains. Machine Learning researchers are actively using these datasets to evaluate novel approaches. Consequently, data repositories have an important standing in tabular data research. They not only host datasets but also provide information on how to use them in supervised learning tasks. In this paper, we argue that, despite great achievements in usability, the unreflected usage of datasets from data repositories may have led to reduced research quality and scientific rigor. We present examples from prominent recent studies that illustrate the problematic use of datasets from OpenML, a large data repository for tabular data. Our illustrations help users of data repositories avoid falling into the traps of (1) using suboptimal model selection strategies, (2) overlooking strong baselines, and (3) inappropriate preprocessing. In response, we discuss possible solutions for how data repositories can prevent the inappropriate use of datasets and become the cornerstones for improved overall quality of empirical research studies.

Julia Gastinger, Christian Meilicke, Heiner Stuckenschmidt

We address the task of temporal knowledge graph (TKG) forecasting by introducing a fully explainable method based on temporal rules. Motivated by recent work proposing a strong baseline using recurrent facts, our approach learns four simple types of rules with a confidence function that considers both recency and frequency. Evaluated on nine datasets, our method matches or surpasses the performance of eight state-of-the-art models and two baselines, while providing fully interpretable predictions.

Lukas Kirchdorfer, Konrad Özdemir, Stjepan Kusenic et al.

Business Process Simulation (BPS) is a critical tool for analyzing and improving organizational processes by estimating the impact of process changes. A key component of BPS is the case-arrival model, which determines the pattern of new case entries into a process. Although accurate case-arrival modeling is essential for reliable simulations, as it influences waiting and overall cycle times, existing approaches often rely on oversimplified static distributions of inter-arrival times. These approaches fail to capture the dynamic and temporal complexities inherent in organizational environments, leading to less accurate and reliable outcomes. To address this limitation, we propose Auto Time Kernel Density Estimation (AT-KDE), a divide-and-conquer approach that models arrival times of processes by incorporating global dynamics, day-of-week variations, and intraday distributional changes, ensuring both precision and scalability. Experiments conducted across 20 diverse processes demonstrate that AT-KDE is far more accurate and robust than existing approaches while maintaining sensible execution time efficiency.

Konrad Özdemir, Lukas Kirchdorfer, Keyvan Amiri Elyasi et al.

Business process simulation (BPS) is a key tool for analyzing and optimizing organizational workflows, supporting decision-making by estimating the impact of process changes. The reliability of such estimates depends on the ability of a BPS model to accurately mimic the process under analysis, making rigorous accuracy evaluation essential. However, the state-of-the-art approach to evaluating BPS models has two key limitations. First, it treats simulation as a forecasting problem, testing whether models can predict unseen future events. This fails to assess how well a model captures the as-is process, particularly when process behavior changes from train to test period. Thus, it becomes difficult to determine whether poor results stem from an inaccurate model or the inherent complexity of the data, such as unpredictable drift. Second, the evaluation approach strongly relies on Earth Mover's Distance-based metrics, which can obscure temporal patterns and thus yield misleading conclusions about simulation quality. To address these issues, we propose a novel framework that evaluates simulation quality based on its ability to generate representative process behavior. Instead of comparing simulated logs to future real-world executions, we evaluate whether predictive process monitoring models trained on simulated data perform comparably to those trained on real data for downstream analysis tasks. Empirical results show that our framework not only helps identify sources of discrepancies but also distinguishes between model accuracy and data complexity, offering a more meaningful way to assess BPS quality.

Patrick Betz, Nathanael Stelzner, Christian Meilicke et al.

In this technical report, we investigate the predictive performance differences of a rule-based approach and the GNN architectures NBFNet and A*Net with respect to knowledge graph completion. For the two most common benchmarks, we find that a substantial fraction of the performance difference can be explained by one unique negative pattern on each dataset that is hidden from the rule-based approach. Our findings add a unique perspective on the performance difference of different model classes for knowledge graph completion: Models can achieve a predictive performance advantage by penalizing scores of incorrect facts opposed to providing high scores for correct facts.

Julia Gastinger, Shenyang Huang, Mikhail Galkin et al.

Multi-relational temporal graphs are powerful tools for modeling real-world data, capturing the evolving and interconnected nature of entities over time. Recently, many novel models are proposed for ML on such graphs intensifying the need for robust evaluation and standardized benchmark datasets. However, the availability of such resources remains scarce and evaluation faces added complexity due to reproducibility issues in experimental protocols. To address these challenges, we introduce Temporal Graph Benchmark 2.0 (TGB 2.0), a novel benchmarking framework tailored for evaluating methods for predicting future links on Temporal Knowledge Graphs and Temporal Heterogeneous Graphs with a focus on large-scale datasets, extending the Temporal Graph Benchmark. TGB 2.0 facilitates comprehensive evaluations by presenting eight novel datasets spanning five domains with up to 53 million edges. TGB 2.0 datasets are significantly larger than existing datasets in terms of number of nodes, edges, or timestamps. In addition, TGB 2.0 provides a reproducible and realistic evaluation pipeline for multi-relational temporal graphs. Through extensive experimentation, we observe that 1) leveraging edge-type information is crucial to obtain high performance, 2) simple heuristic baselines are often competitive with more complex methods, 3) most methods fail to run on our largest datasets, highlighting the need for research on more scalable methods.

Patrick Betz, Stefan Lüdtke, Christian Meilicke et al.

Rule learning approaches for knowledge graph completion are efficient, interpretable and competitive to purely neural models. The rule aggregation problem is concerned with finding one plausibility score for a candidate fact which was simultaneously predicted by multiple rules. Although the problem is ubiquitous, as data-driven rule learning can result in noisy and large rulesets, it is underrepresented in the literature and its theoretical foundations have not been studied before in this context. In this work, we demonstrate that existing aggregation approaches can be expressed as marginal inference operations over the predicting rules. In particular, we show that the common Max-aggregation strategy, which scores candidates based on the rule with the highest confidence, has a probabilistic interpretation. Finally, we propose an efficient and overlooked baseline which combines the previous strategies and is competitive to computationally more expensive approaches.

Kilian Theil, Dirk Hovy, Heiner Stuckenschmidt

How much does a CEO's personality impact the performance of their company? Management theory posits a great influence, but it is difficult to show empirically -- there is a lack of publicly available self-reported personality data of top managers. Instead, we propose a text-based personality regressor using crowd-sourced Myers--Briggs Type Indicator (MBTI) assessments. The ratings have a high internal and external validity and can be predicted with moderate to strong correlations for three out of four dimensions. Providing evidence for the upper echelons theory, we demonstrate that the predicted CEO personalities have explanatory power of financial risk.

Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt

Sum-Product Networks (SPNs) are expressive probabilistic models that provide exact, tractable inference. They achieve this efficiency by making use of local independence. On the other hand, mixtures of exchangeable variable models (MEVMs) are a class of tractable probabilistic models that make use of exchangeability of discrete random variables to render inference tractable. Exchangeability, which arises naturally in relational domains, has not been considered for efficient representation and inference in SPNs yet. The contribution of this paper is a novel probabilistic model which we call Exchangeability-Aware Sum-Product Networks (XSPNs). It contains both SPNs and MEVMs as special cases, and combines the ability of SPNs to efficiently learn deep probabilistic models with the ability of MEVMs to efficiently handle exchangeable random variables. We introduce a structure learning algorithm for XSPNs and empirically show that they can be more accurate than conventional SPNs when the data contains repeated, interchangeable parts.

Christiann Bartelt, Sascha Marton, Heiner Stuckenschmidt

We present xRAI an approach for extracting symbolic representations of the mathematical function a neural network was supposed to learn from the trained network. The approach is based on the idea of training a so-called interpretation network that receives the weights and biases of the trained network as input and outputs the numerical representation of the function the network was supposed to learn that can be directly translated into a symbolic representation. We show that interpretation nets for different classes of functions can be trained on synthetic data offline using Boolean functions and low-order polynomials as examples. We show that the training is rather efficient and the quality of the results are promising. Our work aims to provide a contribution to the problem of better understanding neural decision making by making the target function explicit

Jovita Lukasik, David Friede, Heiner Stuckenschmidt et al.

In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest. Due to the high computational costs, most recent approaches to NAS as well as the few available benchmarks only provide limited search spaces. In this paper we propose a surrogate model for neural architecture performance prediction built upon Graph Neural Networks (GNN). We demonstrate the effectiveness of this surrogate model on neural architecture performance prediction for structurally unknown architectures (i.e. zero shot prediction) by evaluating the GNN on several experiments on the NAS-Bench-101 dataset.

Christian Meilicke, Melisachew Wudage Chekol, Manuel Fink et al.

Most of todays work on knowledge graph completion is concerned with sub-symbolic approaches that focus on the concept of embedding a given graph in a low dimensional vector space. Against this trend, we propose an approach called AnyBURL that is rooted in the symbolic space. Its core algorithm is based on sampling paths, which are generalized into Horn rules. Previously published results show that the prediction quality of AnyBURL is on the same level as current state of the art with the additional benefit of offering an explanation for the predicted fact. In this paper, we are concerned with two extensions of AnyBURL. Firstly, we change AnyBURLs interpretation of rules from $Θ$-subsumption into $Θ$-subsumption under Object Identity. Secondly, we introduce reinforcement learning to better guide the sampling process. We found out that reinforcement learning helps finding more valuable rules earlier in the search process. We measure the impact of both extensions and compare the resulting approach with current state of the art approaches. Our results show that AnyBURL outperforms most sub-symbolic methods.

David Friede, Jovita Lukasik, Heiner Stuckenschmidt et al.

In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest. In the past, NAS was hardly accessible to researchers without access to large-scale compute systems, due to very long compute times for the recurrent search and evaluation of new candidate architectures. The NAS-Bench-101 dataset facilitates a paradigm change towards classical methods such as supervised learning to evaluate neural architectures. In this paper, we propose a graph encoder built upon Graph Neural Networks (GNN). We demonstrate the effectiveness of the proposed encoder on NAS performance prediction for seen architecture types as well an unseen ones (i.e., zero shot prediction). We also provide a new variational-sequential graph autoencoder (VS-GAE) based on the proposed graph encoder. The VS-GAE is specialized on encoding and decoding graphs of varying length utilizing GNNs. Experiments on different sampling methods show that the embedding space learned by our VS-GAE increases the stability on the accuracy prediction task.

Federico Nanni, Goran Glavas, Ines Rehbein et al.

During the last fifteen years, automatic text scaling has become one of the key tools of the Text as Data community in political science. Prominent text scaling algorithms, however, rely on the assumption that latent positions can be captured just by leveraging the information about word frequencies in documents under study. We challenge this traditional view and present a new, semantically aware text scaling algorithm, SemScale, which combines recent developments in the area of computational linguistics with unsupervised graph-based clustering. We conduct an extensive quantitative analysis over a collection of speeches from the European Parliament in five different languages and from two different legislative terms, and show that a scaling approach relying on semantic document representations is often better at capturing known underlying political dimensions than the established frequency-based (i.e., symbolic) scaling method. We further validate our findings through a series of experiments focused on text preprocessing and feature selection, document representation, scaling of party manifestos, and a supervised extension of our algorithm. To catalyze further research on this new branch of text scaling methods, we release a Python implementation of SemScale with all included data sets and evaluation procedures.

Joerg Schoenfisch, Janno von Stulpnagel, Jens Ortmann et al.

IT infrastructure is a crucial part in most of today's business operations. High availability and reliability, and short response times to outages are essential. Thus a high amount of tool support and automation in risk management is desirable to decrease outages. We propose a new approach for calculating the root cause for an observed failure in an IT infrastructure. Our approach is based on Abduction in Markov Logic Networks. Abduction aims to find an explanation for a given observation in the light of some background knowledge. In failure diagnosis, the explanation corresponds to the root cause, the observation to the failure of a component, and the background knowledge to the dependency graph extended by potential risks. We apply a method to extend a Markov Logic Network in order to conduct abductive reasoning, which is not naturally supported in this formalism. Our approach exhibits a high amount of reusability and enables users without specific knowledge of a concrete infrastructure to gain viable insights in the case of an incident. We implemented the method in a tool and illustrate its suitability for root cause analysis by applying it to a sample scenario.

Melisachew Wudage Chekol, Jakob Huber, Heiner Stuckenschmidt

We present $\mathcal{MEL}^{++}$ (M denotes Markov logic networks) an extension of the log-linear description logics $\mathcal{EL}^{++}$-LL with concrete domains, nominals, and instances. We use Markov logic networks (MLNs) in order to find the most probable, classified and coherent $\mathcal{EL}^{++}$ ontology from an $\mathcal{MEL}^{++}$ knowledge base. In particular, we develop a novel way to deal with concrete domains (also known as datatypes) by extending MLN's cutting plane inference (CPI) algorithm.

Jan Noessner, Mathias Niepert, Heiner Stuckenschmidt

RockIt is a maximum a-posteriori (MAP) query engine for statistical relational models. MAP inference in graphical models is an optimization problem which can be compiled to integer linear programs (ILPs). We describe several advances in translating MAP queries to ILP instances and present the novel meta-algorithm cutting plane aggregation (CPA). CPA exploits local context-specific symmetries and bundles up sets of linear constraints. The resulting counting constraints lead to more compact ILPs and make the symmetry of the ground model more explicit to state-of-the-art ILP solvers. Moreover, RockIt parallelizes most parts of the MAP inference pipeline taking advantage of ubiquitous shared-memory multi-core architectures. We report on extensive experiments with Markov logic network (MLN) benchmarks showing that RockIt outperforms the state-of-the-art systems Alchemy, Markov TheBeast, and Tuffy both in terms of efficiency and quality of results.

Christian Meilicke, Ondrej Sváb-Zamazal, Cássia Trojahn et al.

In the field of ontology matching, the most systematic evaluation of matching systems is established by the Ontology Alignment Evaluation Initiative (OAEI), which is an annual campaign for evaluating ontology matching systems organized by different groups of researchers. In this paper, we report on the results of an intermediary OAEI campaign called OAEI 2011.5. The evaluations of this campaign are divided in five tracks. Three of these tracks are new or have been improved compared to previous OAEI campaigns. Overall, we evaluated 18 matching systems. We discuss lessons learned, in terms of scalability, multilingual issues and the ability do deal with real world cases from different domains.