Exploratory Data Analysis.
Data is big. We dig it.
How can we discover novel and interesting things from data?
How can we explore the data, and not our assumptions?
That's what we develop theory and algorithms for.
The EDA group on June 8th 2017
Four papers accepted for presentation at SDM 2021
Great success for the EDA group — four papers accepted for presentation at the 2021 SIAM International Conference on Data Mining (SDM). Alex will present his joint work with Lincen Yang on estimating conditional mutual information for discrete-continuous mixtures. Boris will present ProSeqo for mining concise yet powerful models from event sequence data. Janis will present Susan, the structural similarity random walk kernel that he developed together with Pascal Welke. Last, but not least, Kailash will present Dice for mining causal rules given confounders. Congratulations to all!
Globe to be presented at AAAI 2021
Osman and Alex will present their work on discovering fully oriented causal networks at next year's AAAI, the International Conference on Artificial Intelligence. In their work, they propose a score-based causal discovery algorithm that builds upon the algorithmic Markov condition to automatically orient all edges in the most likely causal direction. The Globe algorithm is remarkably robust and outperforms state-of-the-art score and constraint based solutions.
Two papers accepted for presentation at IEEE ICDM 2020
Joscha and Sebastian will both present a paper at this year's IEEE International Conference on Data Mining. Joscha's paper introduces the Omen algorithm for discovering patterns that do not only predict that something of interest will happen, but are also reliable in telling when this will be. Sebastian proposes a new relaxed formulation of the Maximum Entropy distribution that, through dynamic factorizations, is as accurrate yet orders of magnitudes faster than traditional approaches.
Anna explores the secret life of neural networks
With ExplaiNN, Anna Oláh proposes a highly scalable method that provides deep insight in the black box that neural networks typically are. In her Master thesis, Anna proposes to mine activation patterns between neurons in different layers in the form of robust rules. Not only does she propose an efficient and highly scalable algorithm, she also shows how we can use these rules to gain insight beyond the state of the art, both in what drives decisions for individual classes, as well as the differences between. Who knew, for example, how a neural network tells Malamutes and Huskies apart? It turns out that in the eye of a neural network, Malamutes are essentially fluffy Husky's, and Husky's are essentially sharply drawn Malamutes! Congratulations, Anna!
Edith shows what we didn't know yet
In her Master thesis, Edith Heiter studies the problem of how to factor out prior knowledge from low-dimensional embeddings. In other words, how can we visualise a high dimensional dataset, such that we reveal structure that goes beyond what we already knew? In her thesis, Edith proposes not one, but two methods to factor out arbitrary distance matrices. With Jedi she proposes to adapt the objective function of \(t\)-SNE in a well-founded manner, while with Confetti she proposes a method that allows us to factor out knowledge from arbitrary embedding algorithms. Through many experiments, she showed that both work well in practice, earning her the title Master of Science. Congratulations, Edith!
Kailash defends his Ph.D. thesis
On Monday July 3rd, Kailash Budhathoki succesfully defended his Ph.D. thesis titled 'Causal Inference on Discrete Data'. The promotion committee consisting of Profs. Dietrich Klakow, Gerhard Weikum, Tom Heskes, and Jilles Vreeken, decided that he not only passed the requirements for a degree of Doctor of Philosophy of the Natural Sciences (Dr.rer.nat.) but also awarded his thesis with the distinction Summa Cum Laude. Congratulations, Dr. Budhathoki!
Three papers accepted at ACM SIGKDD 2020
EDA will present three papers at ACM SIGKDD 2020, the flagship conference in data mining. Jonas will present his work on discovering patterns of mutual exclusivity, in which he proposed the Mexican algorithm. Panagiotis will present his work together with Frederic Penerath on how to use smoothing to measure and mine reliable functional dependencies, as well as work together with David on how to discover functional dependencies from mixed-type data.
Sandra lays an opinion-spam trap
How can we detect review spam campaigns, the groups of users that participate in these, as well as determine the spamicity of individual reviewers that actively try to hide their spamming behaviour? In her Master thesis, Sandra Sukarieh answers all three questions. The main premise is that a campaign requires multiple users and abnormal scores. Sprap identifies users that surprisingly often review products together with other users that surprisingly often score differently from the norm. Experiments show that Sprap works remarkably well in practice, without even having to consider the content of the reviews. In other words, Sandra's Master thesis campaign was a great success. Congratulations, Sandra!
Alex invited to the Heidelberg Laureate Forum
Alexander Marx has been invited to attend the Heidelberg Laureate Forum. While the actual event is postponed to next year due to Corona, he will then get to meet laureates of the most prestiguous awards in Mathematics and Computer Science, such as Turing Award winners Manuel Blum, Vinton Cerf, Richard Karp, and Judea Pearl, as well as 199 other highly talented young scientists.
Joscha joins EDA as a PhD student
Warm welcome to Joscha Cueppers as a PhD student in the EDA group! Joscha recently finished his MSc thesis with us, and now joins to pursue his PhD. He'll be working on statistically well-founded pattern discovery from structured data, such as sequences and graphs, to gain insight in the causal processes that generated this data. Welcome, Joscha!
Corinna joins EDA as a PhD student
We warmly welcome Corinna Coupette as a PhD student in the EDA group! Corinna already holds a PhD in Law, as well as a Masters degree in Informatics. She will be working both on the theory of, as well as on methods for meaningful analysis of complex graphs. The theory aspects she will work on with Christoph Lenzen of the Max Planck Institute for Informatics, while she'll work on method for graph mining with Jilles Vreeken. Welcome, Corinna!
Sebastian to present Disc at AAAI 2020
Sebastian's paper on automatically discovering and explaining the components (clusters) of a database has been accepted for presentation at the International Conference on Artificial Intelligence 2020, which will be held in New York. In his work, Sebastian proposes to partition a dataset such that we maximize likelihood, and doing so by modelling the data non-parametrically using pattern-distributions. The key idea of Disc is that these partitions and models are inherently explainable, as they non-redundantly show which patterns are common or specific to what parts of the data.
Joscha bakes a Cake
In his Master thesis, Joscha Cueppers considers the problem of discovering patterns that reliably predict future events. That is, he is interested in discovering sequential patterns from an event sequence \(X\) for which with high accuracy how long it will take until we see an interesting event happening in event sequence \(Y\). He modelled the problem using MDL, and proposes the Cake algorithm to discover a small set of non-redundant patterns that together predict \(Y\) as well as possible given \(X\). The experiments show the results are very tasty. Congratulations, Joscha!
Osman joins EDA as a PhD student
Warm welcome to Osman Ali Mian as a PhD student in the EDA group! Osman recently finished his MSc thesis with us, and now joins to pursue his PhD. He'll be working on theory and methods for doing causal inference in realistic settings – e.g. methods that scale, can deal with data from multiple sources, can deal with missing data, and so on. Welcome, Osman!
Divyam summarizes temporal graphs with Mango
Suppose we are given multiple snapshots of a graph over time, how can we discover patterns of change and similarity between them? Divyam Saran studied this problem for his Master thesis, and proposed the MDL-based Mango algorithm to discover succinct and non-redundant summaries that give clear insight in what is happening between the graphs. In a nutshell, he discovers significant structure per graph, and then uses the structures from adjacent graphs to refine the overall temporal summary – identifying growing, shrinking, and changing structures such as cliques, stars, and bi-partite subgraphs. Congratulations, Divyam!
Boris joins EDA as a PhD student
We warmly welcome Boris Wiegand as a PhD student in the EDA group! Boris is employed by the Dillinger steel works, and will work on topics related to extracting high-quality models from production logs – for example, to gain insight in patterns, bottlenecks, as well as to optimize both planning and production. He will be co-supervised by Jilles Vreeken and Dietrich Klakow. Welcome, Boris!
Osman trots the Globe
How can we discover fully oriented causal networks from observational data? In this Master thesis, Osman Ali Mian shows how we can use the Algorithmic Markov Condition to not only discover high quality causal skeletons, but at the same time orient all the edges from cause to effect. To find such networks from data, he proposes Globe, which instantiates the ideal using MDL and non-parametric multivariate regression splines. The experiments show that his proposal outperforms the state of the art constraint-based as well as score-based methods. Congratulations, Osman!
Panagiotis invited to the Heidelberg Laureate Forum
Panagiotis has been invited to attend the Heidelberg Laureate Forum. During the 3rd week of September he will he will then get to meet laureates of the most prestiguous awards in Mathematics and Computer Science, such as Turing Award winners Manuel Blum, Vinton Cerf, Richard Karp, and Yoshua Bengio, as well as 199 other highly talented young scientists.
Simina shows there's more to it than a single answer
While almost all data analysis methods produce only one single model, reality is much more complex, much more layered than that. How can we discover not one, but multiple high-quality explanations for a dataset, each of which show increasingly yet significantly more detail than the others? This is exactly the answer that Simina Ana Cotop answers in her Master thesis, in which she proposes the Grim algorithm that instantiates Kolmogorov's structure function for pattern-based summarization. Through many experiments she shows that Grim indeed returns insightful high level as well as detailed in-depth summaries. Congratulations, Simina!
IEEE ICDM 2018 Tao Li Award
The IEEE ICDM Tao Li Award recognizes excellent early career researchers for their impact on research contributions, impact, and services within the first ten years of their obtaining their PhD. This inaugural year, the award committee selected Jilles Vreeken for this honour — who is both deeply honoured, and uncharacteristically speechless.
IEEE ICDM 2018 Best Paper Award
Out of 948 submissions, the award committee of IEEE ICDM 2018 selected our paper Discovering Reliable Dependencies from Data: Hardness and Improved Algorithms by Panagiotis Mandros, Mario Boley, and Jilles Vreeken for the IEEE ICDM 2018 Best Paper Award! We will receive the award in Singapore on November 19th. Hurray!
Mario starts Tenure Track at Monash University
While we're very sad that Mario Boley will leave us, we are very happy that on October 1st 2018 he will make the next step in his career and join Monash University in Melbourne, Australia as Tenure Track faculty. We wish Mario all the best, and are looking forward to continue working together on topics such as subgroup and functional dependency discovery. Congratulations, Mario!
Two papers accepted for presentation at IEEE ICDM 2018
Kailash Budhathoki and Panagiotis Mandros will present two papers at IEEE ICDM 2018 in Singapore. Kailash will present his work on accurate causal inference on discrete data, in which he shows that by simply optimising the residual entropy we can accurately identify the most likely causal direction—with guarantees. Panagiotis will present his work on discovering reliable approximate functional dependencies, in which he shows that although this problem is NP-hard, using his optimistic estimator we can solve it exactly in reasonable time, as well as get extremely good solutions using a greedy strategy too.
Iva gives guarantees and fast algorithms for mining patterns that overlap
Iva Farag was unhappy with the fact that Slim was restricted to using patterns without overlap, and looked into the theoretical details as well as the practical algorithmics for how to alleviate this. In her Master thesis, she shows that the problem is related to weighted set cover, and based on this proposes three cover algorithms that do allow overlap, two of which give guarantees on the quality of the solution. Experiments show that with GreCo we find more succinct, more insightful patterns that are less prone to fitting noise. Congratulations, Iva!
Maha smoothly smooths discrete data
With Smoothie, Maha Aburahma proposes a parameter-free algorithm for smoothing discrete data. In short, given a noisy transaction database, the algorithm makes local adjustments such that the overall MDL-complexity of the data and model is minimised. It does so step by step, providing a continuum of increasingly smoothened data. The MDL-optimum coincides with the optimal denoised data, which lends itself for pattern mining and knowledge discovery. Congratulations, Maha!
Yuliia proposes Grip for non-parametric dependency network reconstruction
For her Master thesis, Yuliia Brendel studied how we can recover the dependency network over a multivariate continuous-valued data set, without having to assume anything about the data distribution. She did so using the notion of cumulative entropy, and proposes the Grip algorithm to robustly estimate it for multivariate case. Experiments show that Grip performs very well even for highly non-linear, highly noisy, and high dimensional data and dependencies. Congratulations, Yuliia!
Boris predicts the wear and tear of steel rolling mills
During his studies, Boris Wiegand worked at the Dillinger steel plant, where among others they use specialized rolling mills to highly precisely turn chunks of red-hot steel into plates of specified thickness. These rolls in these mills undergo incredible temprature and pressure, and hence need to be replaced ever so often. The question is, when? In his Master thesis, Boris proposed a data-driven model that outperforms the industry-standard phsyics-based model, as well as how we can use this to optimize the milling schedule. Congratulations, Boris!
Maike shows how to reverse engineer epidemics in weighted graphs
In her Master thesis, Maike Eissfeller considered the problem of how to identify which nodes were most likely responsible for starting an epidemic in a large, weighted graph. She build upon the NetSleuth algorithm, and showed how to extend the theory to weighted graphs, how to make it more robust against the non-convex score, and how to improve its results by local re-optimization. Congratulations, Maike!
Kailash explains how to be Cute at SDM
Given two discrete valued time series can we tell whether they are causally related? That is, can we tell whether \(x\) causes \(y\), or whether \(y\) causes \(x\)? In the paper he presented on May 3rd at the SIAM Data Mining Conference, Kailash shows we can do so accurately, efficiently, and without having to make assumptions on the distribution of these time series, or about the lag of the causal effect. You can find the paper and implementation here.
Tatiana shows how to robustly discretizing multivariate data
Tatiana Dembelova received her Master of Science degree for her thesis on how to how to discretize multivariate data such that we maintain the most important interactions between the attributes. In particular, she showed that existing work based on interaction distances performs less well than desired, and proposed a new approach based on footprint interactions that is highly robust against noise and the curse of dimensionality both in theory and in practice. Congratulations, Tatiana!
Robin introduces the Fire approach to discover interesting patterns
Robin Burghartz received his Master of Science degree for his thesis on how to identify interesting non-redundant pattern sets through the use of adaptive codes. Loosely speaking, he showed that when describing a row of data, if we adaptively only consider those patterns we know we can possibly use, instead of all, we can identify those patterns that stand out strongly from those already selected are chosen, leading to much smaller and much less redundant pattern sets. Congratulations, Robin!
Henrik presents Explore to efficiently discover powerlaw communities
Henrik Jilke presented his Master thesis on the efficient discovery of powerlaw-distributed communities in large graphs. He proposed a lossless score based on the Minimum Descrtipion Length principle to identify whether a subgraph stands out sufficiently to be considered a community, and gave the efficient Explore algorithm to heuristically discover the best set of such communities. Experiments validate his method is able to discover large, powerlaw-distributed communities that other methods miss. Congratulations, Henrik!
Benjamin proposes to automatically Refine ontologies for a specific corpus
Benjamin Hättasch finished his Master of Science by handing in his thesis on the automatic refinement of ontologies using compression-based learning. In a nutshell, Benjamn shows how we can efficiently describe a given text using an ontology. His main result is the Refine algorithm, that iteratively refines the ontology such that we maximize the compression. The resulting ontologies are a much better representation of the text distribution, as well as allow him to identify the key topics of the text without supervision. Congratulations, Benjamin!
Jonas receives IMPRS-CS PhD Fellowship
We are happy and proud to announce that Jonas Fischer got accepted as a PhD student in the International Max Planck Research School for Computer Science (IMPRS-CS) to pursue a PhD on the topic of algorithmic data analysis. He was already a student in the Saarbrücken Graduate School of Computer Science, and recently finished his Master thesis in Bioinformatics on the topic of highly efficient methylation calling.
David receives IMPRS-CS PhD Fellowship
We are excited to announce that David Kaltenpoth got accepted as a PhD student in the International Max Planck Research School for Computer Science (IMPRS-CS). He was already a member of the Saarbrücken Graduate School of Computer Science. He will work on the topic of information theoretic causal inference, in particular the theory and practice of determining whether potential causal dependencies are confounded.
Sebastian joins EDA as a PhD student
We warmly welcome Sebastian Dalleiger as a PhD student in the Exploratory Data Analysis group. Sebastian finished his Master's in Informatics at Saarland University in 2016, and will now join our group to work on information theoretic approaches to mining interpretable and useful structure from data.
Janis joins EDA as a PhD student
We warmly welcome Janis Kalofolias as a PhD student in the Exploratory Data Analysis group. Janis recently finished his Master's in Informatics at Saarland University, and will now join our group to work on the theoretical foundations of mining interesting patterns from data.
Alex receives IMPRS-CS PhD Fellowship
We are happy to announce that Alexander Marx got accepted as a PhD student in the International Max Planck Research School for Computer Science (IMPRS-CS) and the Saarbrücken Graduate School of Computer Science! He will work on the efficient discovery and interpretable description of interesting sub-populations in data, with the grand goals of discovering causal dependencies that lead to the discovery of novel materials.
Amir proposes BVCorr to discover non-linearly correlated segments
Amirhossein Baradaranshahroudi finished his Master of Science by handing in his thesis on fast discovery of non-linearly correlated segments in multivariate time series. In his thesis, Amir shows that through fast-fourier transformation, convolution, and pre-computation we can bring down the computational complexity of computing the distance correlation between all pairwise windows in \(O(n^4 \log n)\) instead of \(O(n^5 d)\). For discovery in long time series, he proposes an effective and efficient heuristic that only takes \(O(nwd)\) time. Congratulations, Amir!
Apratim shows how to Squish event sequences
Apratim Bhattacharyya finished his Master of Science by handing in his thesis 'Squish: Efficiently Summarising Event Sequences with Rich and Interleaving Patterns'. Squish improves over the state of the art by considering a much richer description language, allowing both nesting and interleaving of patterns, as well as both variances and partial occurrences of patterns. Moreover, Squish is not only orders of magnitude faster than the state of the art, experiments show it also discovers much better and more easily interpretable models. Congratulations, Apratim!
Beata discovers the Spaghetti in document collections
Beata Wójciak handed in her thesis 'Spaghetti: Finding Storylines in Large Collections of Documents' on the 29th of September, and so fullfilled the requirements to become a Master of Science in Informatics. In her thesis, Beata studied the problem of making sense from large, time-stamped, collections of documents, and proposed the efficient Spaghetti algorithm to discover the pattern storylines in a corpus. This allows us to draw a map showing which documents are connected, as well as easily interpret the storylines. Congratulations, Beata!
Magnus combines sketching and Slim into Skim
For this Bachelor thesis, Magnus Halbe studied whether sketching can speed up Slim. In particular, he investigated whether DHP and min-hashing can used to reliably and efficiently identify co-occurring patterns. In this thesis, titled 'Skim: Alternative Candidate Selections for Slim through Sketching', Magnus shows that the answer is 'not really.'. Whereas the sketches ably identify heavy hitters, they are less efficient in identifying more subtle patterns. He therefore proposes the Skim algorithm, that combines the best of both worlds. Congratulations, Magnus!
Polina presents CulT at KDD
Last summer, Polina Rozenshtein did an internship in our group. She presented the resulting paper `Reconstructing an Epidemic over Time' at ACM SIGKDD 2016. Together with B. Aditya Prakash and Aris Gionis we studied the problem of finding the seed nodes of an epidemic, if we are given an interaction graph, and a sparse and noisy sample of node states over time. We propose the CulT (Culprits in Time) algorithm, that reliably, efficiently, and without making any assumptions on the viral process can recover both the number and location of the original seed nodes. We give a short explanation, with kittens, on YouTube here.
Roel presents Ditto at KDD
During the summer of 2014 Roel Bertens did an internship in our group. He present the outcome `Keeping it Short and Simple: Summarising Complex Event Sequences with Multivariate Patterns' at ACM SIGKDD 2016. In this paper we propose the Ditto algorithm, an efficient heuristic for finding succinct summaries of complex event sequences with patterns that can span over multiple attributes and may include gaps. You can find the paper and implementation here, and for a short introduction, see our YouTube video here.
Kailash invited to the Heidelberg Laureate Forum
Kailash Budhathoki has been invited to attend the 4th Heidelberg Laureate Forum. During the 18th and 23rd of September 2016, he will get to meet laureates of the most prestiguous awards in Mathematics and Computer Science, such as Turing Award winners Manuel Blum, Vinton Cerf, Richard Karp, and John Hopcroft, as well as 199 other highly talented young scientists.
Panos and Jilles present Flexi, Light, and UdS at SIAM SDM
At the SIAM International Conference on Data Mining 2016, Panagiotis Mandros presented uds, which allows for Universal Dependency Analysis. That is, it is a robust and efficient measure for non-linear and multivariate correlations, which does not require any prior assumptions, yet does allow for meaningful comparison, no matter the cardinality or distribution of the subspace.
At the same venue, Jilles Vreeken presented both light, a linear-time method for detecting non-linear change points in massively high dimensional time series, as well as flexi, a highly flexible method for mining high quality subgroups through optimal discretisation, that works with virtually any quality measure.