Search

Portfolio optimization tasks describe sequential decision problems in which the investor's wealth is distributed across a set of assets. Allocation constraints are used to enforce minimal or maximal investments into particular subsets of assets to control for objectives such as limiting the portfolio's exposure to a certain sector due to environmental concerns. Although methods for constrained Reinforcement Learning (CRL) can optimize policies while considering allocation constraints, it can be observed that these general methods yield suboptimal results. In this paper, we propose a novel approach to handle allocation constraints based on a decomposition of the constraint action space into a set of unconstrained allocation problems. In particular, we examine this approach for the case of two constraints. For example, an investor may wish to invest at least a certain percentage of the portfolio into green technologies while limiting the investment in the fossil energy sector. We show that the action space of the task is equivalent to the decomposed action space, and introduce a new reinforcement learning (RL) approach CAOSD, which is built on top of the decomposition. The experimental evaluation on real-world Nasdaq-100 data demonstrates that our approach consistently outperforms state-of-the-art CRL benchmarks for portfolio optimization.

Recent trends in Video Instance Segmentation (VIS) have seen a growing reliance on online methods to model complex and lengthy video sequences. However, the degradation of representation and noise accumulation of the online methods, especially during occlusion and abrupt changes, pose substantial challenges. Transformer-based query propagation provides promising directions at the cost of quadratic memory attention. However, they are susceptible to the degradation of instance features due to the above-mentioned challenges and suffer from cascading effects. The detection and rectification of such errors remain largely underexplored. To this end, we introduce \textbf{GRAtt-VIS}, \textbf{G}ated \textbf{R}esidual \textbf{Att}ention for \textbf{V}ideo \textbf{I}nstance \textbf{S}egmentation. Firstly, we leverage a Gumbel-Softmax-based gate to detect possible errors in the current frame. Next, based on the gate activation, we rectify degraded features from its past representation. Such a residual configuration alleviates the need for dedicated memory and provides a continuous stream of relevant instance features. Secondly, we propose a novel inter-instance interaction using gate activation as a mask for self-attention. This masking strategy dynamically restricts the unrepresentative instance queries in the self-attention and preserves vital information for long-term tracking. We refer to this novel combination of Gated Residual Connection and Masked Self-Attention as \textbf{GRAtt} block, which can easily be integrated into the existing propagation-based framework. Further, GRAtt blocks significantly reduce the attention overhead and simplify dynamic temporal modeling. GRAtt-VIS achieves state-of-the-art performance on YouTube-VIS and the highly challenging OVIS dataset, significantly improving over previous methods. Code is available at \url{https://github.com/Tanveer81/GRAttVIS}., Comment: 14 pages, 5 tables, 9 figures

Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply integrates clip retrieval and grounding into a single network capable of processing long videos into multiple granular levels, e.g., clips and frames. Its core component is a novel transformer encoder, RG-Encoder, that unifies the two stages through shared features and mutual optimization. The encoder incorporates a sparse attention mechanism and an attention loss to model both granularity jointly. Moreover, we introduce a contrastive clip sampling technique to mimic the long video paradigm closely during training. RGNet surpasses prior methods, showcasing state-of-the-art performance on long video temporal grounding (LVTG) datasets MAD and Ego4D., Comment: The code is released at https://github.com/Tanveer81/RGNet

Do we need active learning? The rise of strong deep semi-supervised methods raises doubt about the usability of active learning in limited labeled data settings. This is caused by results showing that combining semi-supervised learning (SSL) methods with a random selection for labeling can outperform existing active learning (AL) techniques. However, these results are obtained from experiments on well-established benchmark datasets that can overestimate the external validity. However, the literature lacks sufficient research on the performance of active semi-supervised learning methods in realistic data scenarios, leaving a notable gap in our understanding. Therefore we present three data challenges common in real-world applications: between-class imbalance, within-class imbalance, and between-class similarity. These challenges can hurt SSL performance due to confirmation bias. We conduct experiments with SSL and AL on simulated data challenges and find that random sampling does not mitigate confirmation bias and, in some cases, leads to worse performance than supervised learning. In contrast, we demonstrate that AL can overcome confirmation bias in SSL in these realistic settings. Our results provide insights into the potential of combining active and semi-supervised learning in the presence of common real-world challenges, which is a promising direction for robust methods when learning with limited labeled data in real-world applications., Comment: Accepted @ ECML PKDD 2023. This is the author's version of the work. The definitive Version of Record will be published in the Proceedings of ECML PKDD 2023

Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data. To keep annotation costs low, active graph learning focuses on selecting the most qualitative subset of nodes that maximizes label efficiency. However, deciding which heuristic is best suited for an unlabeled graph to increase label efficiency is a persistent challenge. Existing solutions either neglect aligning the learned model and the sampling method or focus only on limited selection aspects. They are thus sometimes worse or only equally good as random sampling. In this work, we introduce a novel active graph learning approach called DiffusAL, showing significant robustness in diverse settings. Toward better transferability between different graph structures, we combine three independent scoring functions to identify the most informative node samples for labeling in a parameter-free way: i) Model Uncertainty, ii) Diversity Component, and iii) Node Importance computed via graph diffusion heuristics. Most of our calculations for acquisition and training can be pre-processed, making DiffusAL more efficient compared to approaches combining diverse selection criteria and similarly fast as simpler heuristics. Our experiments on various benchmark datasets show that, unlike previous methods, our approach significantly outperforms random selection in 100% of all datasets and labeling budgets tested., Comment: Accepted @ ECML PKDD 2023. This is the author's version of the work. The definitive Version of Record will be published in the Proceedings of ECML PKDD 2023

Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches. However, their reliance on the whole video and the immense computational complexity caused by full Spatio-temporal attention limit them in real-life applications such as processing lengthy videos. In this paper, we propose a single-stage transformer-based efficient online VIS framework named InstanceFormer, which is especially suitable for long and challenging videos. We propose three novel components to model short-term and long-term dependency and temporal coherence. First, we propagate the representation, location, and semantic information of prior instances to model short-term changes. Second, we propose a novel memory cross-attention in the decoder, which allows the network to look into earlier instances within a certain temporal window. Finally, we employ a temporal contrastive loss to impose coherence in the representation of an instance across all frames. Memory attention and temporal coherence are particularly beneficial to long-range dependency modeling, including challenging scenarios like occlusion. The proposed InstanceFormer outperforms previous online benchmark methods by a large margin across multiple datasets. Most importantly, InstanceFormer surpasses offline approaches for challenging and long datasets such as YouTube-VIS-2021 and OVIS. Code is available at https://github.com/rajatkoner08/InstanceFormer.

Argumentation is one of society's foundational pillars, and, sparked by advances in NLP and the vast availability of text data, automated mining of arguments receives increasing attention. A decisive property of arguments is their strength or quality. While there are works on the automated estimation of argument strength, their scope is narrow: they focus on isolated datasets and neglect the interactions with related argument mining tasks, such as argument identification, evidence detection, or emotional appeal. In this work, we close this gap by approaching argument quality estimation from multiple different angles: Grounded on rich results from thorough empirical evaluations, we assess the generalization capabilities of argument quality estimation across diverse domains, the interplay with related argument mining tasks, and the impact of emotions on perceived argument strength. We find that generalization depends on a sufficient representation of different domains in the training part. In zero-shot transfer and multi-task experiments, we reveal that argument quality is among the more challenging tasks but can improve others. Finally, we show that emotions play a minor role in argument quality than is often assumed.

During different steps in the process of discovering drug candidates for diseases, it can be supportive to identify groups of molecules that share similar properties, i.e. common overall structural similarity. The existing methods for computing (dis)similarities between chemical structures rely on a priori domain knowledge. Here we investigate the clustering of compounds that are applied on embeddings generated from a recently published Mol2Vec technique which enables an entirely unsupervised vector representation of compounds. A research question we address in this work is: do existent well-known clustering algorithms such as k-means or hierarchical clustering methods yield meaningful clusters on the Mol2Vec embeddings? Further, we investigate how far subspace clustering can be utilized to compress the data by reducing the dimensionality of the compounds vector representation. Our first conducted experiments on a set of COVID-19 drug candidates reveal that well-established methods yield meaningful clusters. Preliminary results from subspace clusterings indicate that a compression of the vector representations seems viable.

High-quality arguments are an essential part of decision-making. Automatically predicting the quality of an argument is a complex task that recently got much attention in argument mining. However, the annotation effort for this task is exceptionally high. Therefore, we test uncertainty-based active learning (AL) methods on two popular argument-strength data sets to estimate whether sample-efficient learning can be enabled. Our extensive empirical evaluation shows that uncertainty-based acquisition functions can not surpass the accuracy reached with the random acquisition on these data sets.

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the same scale, i.e., all attention heads are in the same resolution, resulting in the limited power of the Transformer. To remedy this, we propose a novel and efficient structure named Adaptive Multi-Resolution Attention (AdaMRA for short), which scales linearly to sequence length in terms of time and space. Specifically, we leverage a multi-resolution multi-head attention mechanism, enabling attention heads to capture long-range contextual information in a coarse-to-fine fashion. Moreover, to capture the potential relations between query representation and clues of different attention granularities, we leave the decision of which resolution of attention to use to query, which further improves the model's capacity compared to vanilla Transformer. In an effort to reduce complexity, we adopt kernel attention without degrading the performance. Extensive experiments on several benchmarks demonstrate the effectiveness and efficiency of our model by achieving a state-of-the-art performance-efficiency-memory trade-off. To facilitate AdaMRA utilization by the scientific community, the code implementation will be made publicly available., Comment: 11 pages

Malicious software (malware) poses an increasing threat to the security of communication systems as the number of interconnected mobile devices increases exponentially. While some existing malware detection and classification approaches successfully leverage network traffic data, they treat network flows between pairs of endpoints independently and thus fail to leverage rich communication patterns present in the complete network. Our approach first extracts flow graphs and subsequently classifies them using a novel edge feature-based graph neural network model. We present three variants of our base model, which support malware detection and classification in supervised and unsupervised settings. We evaluate our approach on flow graphs that we extract from a recently published dataset for mobile malware detection that addresses several issues with previously available datasets. Experiments on four different prediction tasks consistently demonstrate the advantages of our approach and show that our graph neural network model can boost detection performance by a significant margin.

Message passing neural networks have recently evolved into a state-of-the-art approach to representation learning on graphs. Existing methods perform synchronous message passing along all edges in multiple subsequent rounds and consequently suffer from various shortcomings: Propagation schemes are inflexible since they are restricted to $k$-hop neighborhoods and insensitive to actual demands of information propagation. Further, long-range dependencies cannot be modeled adequately and learned representations are based on correlations of fixed locality. These issues prevent existing methods from reaching their full potential in terms of prediction performance. Instead, we consider a novel asynchronous message passing approach where information is pushed only along the most relevant edges until convergence. Our proposed algorithm can equivalently be formulated as a single synchronous message passing iteration using a suitable neighborhood function, thus sharing the advantages of existing methods while addressing their central issues. The resulting neural network utilizes a node-adaptive receptive field derived from meaningful sparse node neighborhoods. In addition, by learning and combining node representations over differently sized neighborhoods, our model is able to capture correlations on multiple scales. We further propose variants of our base model with different inductive bias. Empirical results are provided for semi-supervised node classification on five real-world datasets following a rigorous evaluation protocol. We find that our models outperform competitors on all datasets in terms of accuracy with statistical significance. In some cases, our models additionally provide faster runtime.

Peer reviewing is a central process in modern research and essential for ensuring high quality and reliability of published work. At the same time, it is a time-consuming process and increasing interest in emerging fields often results in a high review workload, especially for senior researchers in this area. How to cope with this problem is an open question and it is vividly discussed across all major conferences. In this work, we propose an Argument Mining based approach for the assistance of editors, meta-reviewers, and reviewers. We demonstrate that the decision process in the field of scientific publications is driven by arguments and automatic argument identification is helpful in various use-cases. One of our findings is that arguments used in the peer-review process differ from arguments in other domains making the transfer of pre-trained models difficult. Therefore, we provide the community with a new peer-review dataset from different computer science conferences with annotated arguments. In our extensive empirical evaluation, we show that Argument Mining can be used to efficiently extract the most relevant parts from reviews, which are paramount for the publication decision. The process remains interpretable since the extracted arguments can be highlighted in a review without detaching them from their context.

Unlabeled data is often abundant in the clinic, making machine learning methods based on semi-supervised learning a good match for this setting. Despite this, they are currently receiving relatively little attention in medical image analysis literature. Instead, most practitioners and researchers focus on supervised or transfer learning approaches. The recently proposed MixMatch and FixMatch algorithms have demonstrated promising results in extracting useful representations while requiring very few labels. Motivated by these recent successes, we apply MixMatch and FixMatch in an ophthalmological diagnostic setting and investigate how they fare against standard transfer learning. We find that both algorithms outperform the transfer learning baseline on all fractions of labelled data. Furthermore, our experiments show that exponential moving average (EMA) of model parameters, which is a component of both algorithms, is not needed for our classification problem, as disabling it leaves the outcome unchanged. Our code is available online: https://github.com/Valentyn1997/oct-diagn-semi-supervised, Comment: KDAH-CIKM-2020

Subspace clustering has established itself as a state-of-the-art approach to clustering high-dimensional data. In particular, methods relying on the self-expressiveness property have recently proved especially successful. However, they suffer from two major shortcomings: First, a quadratic-size coefficient matrix is learned directly, preventing these methods from scaling beyond small datasets. Secondly, the trained models are transductive and thus cannot be used to cluster out-of-sample data unseen during training. Instead of learning self-expression coefficients directly, we propose a novel metric learning approach to learn instead a subspace affinity function using a siamese neural network architecture. Consequently, our model benefits from a constant number of parameters and a constant-size memory footprint, allowing it to scale to considerably larger datasets. In addition, we can formally show that out model is still able to exactly recover subspace clusters given an independence assumption. The siamese architecture in combination with a novel geometric classifier further makes our model inductive, allowing it to cluster out-of-sample data. Additionally, non-linear clusters can be detected by simply adding an auto-encoder module to the architecture. The whole model can then be trained end-to-end in a self-supervised manner. This work in progress reports promising preliminary results on the MNIST dataset. In the spirit of reproducible research, me make all code publicly available. In future work we plan to investigate several extensions of our model and to expand experimental evaluation.

In this work, we focus on the problem of retrieving relevant arguments for a query claim covering diverse aspects. State-of-the-art methods rely on explicit mappings between claims and premises, and thus are unable to utilize large available collections of premises without laborious and costly manual annotation. Their diversity approach relies on removing duplicates via clustering which does not directly ensure that the selected premises cover all aspects. This work introduces a new multi-step approach for the argument retrieval problem. Rather than relying on ground-truth assignments, our approach employs a machine learning model to capture semantic relationships between arguments. Beyond that, it aims to cover diverse facets of the query, instead of trying to identify duplicates explicitly. Our empirical evaluation demonstrates that our approach leads to a significant improvement in the argument retrieval task even though it requires less data.

The acquisition of spatio-temporal data in top-class sport has become an integral part of performance analysis. Currently, data is mainly captured by camera, but the use of radio-based positioning systems seems to be promising. The dissertation describes new applications of radio-based positioning systems for the acquisition of spatio-temporal data in sports. The articles are dedicated to system validation in football and pattern recognition for the automatic detection of sprint parameters in athletics., Die Erfassung von Positionsdaten im Spitzensport ist mittlerweile ein fester Bestandteil der Wettkampfdiagnostik. Aktuell werden diese hauptsächlich kamera-basiert erfasst, jedoch scheint der Einsatz von funkbasierten Ortungssystemen vielversprechend zu sein. Die Dissertation beschreibt neue Anwendungsmöglichkeiten von funkbasierten Ortungssystemen für die Erfassung von Positionsdaten im Sport. Die Einzelbeiträge widmen sich der Systemvalidierung im Fußball, sowie der Mustererkennung zur automatischen Detektion von Sprintparametern in der Leichtathletik.

The acquisition of spatio-temporal data in top-class sport has become an integral part of performance analysis. Currently, data is mainly captured by camera, but the use of radio-based positioning systems seems to be promising. The dissertation describes new applications of radio-based positioning systems for the acquisition of spatio-temporal data in sports. The articles are dedicated to system validation in football and pattern recognition for the automatic detection of sprint parameters in athletics., Die Erfassung von Positionsdaten im Spitzensport ist mittlerweile ein fester Bestandteil der Wettkampfdiagnostik. Aktuell werden diese hauptsächlich kamera-basiert erfasst, jedoch scheint der Einsatz von funkbasierten Ortungssystemen vielversprechend zu sein. Die Dissertation beschreibt neue Anwendungsmöglichkeiten von funkbasierten Ortungssystemen für die Erfassung von Positionsdaten im Sport. Die Einzelbeiträge widmen sich der Systemvalidierung im Fußball, sowie der Mustererkennung zur automatischen Detektion von Sprintparametern in der Leichtathletik.

The acquisition of spatio-temporal data in top-class sport has become an integral part of performance analysis. Currently, data is mainly captured by camera, but the use of radio-based positioning systems seems to be promising. The dissertation describes new applications of radio-based positioning systems for the acquisition of spatio-temporal data in sports. The articles are dedicated to system validation in football and pattern recognition for the automatic detection of sprint parameters in athletics., Die Erfassung von Positionsdaten im Spitzensport ist mittlerweile ein fester Bestandteil der Wettkampfdiagnostik. Aktuell werden diese hauptsächlich kamera-basiert erfasst, jedoch scheint der Einsatz von funkbasierten Ortungssystemen vielversprechend zu sein. Die Dissertation beschreibt neue Anwendungsmöglichkeiten von funkbasierten Ortungssystemen für die Erfassung von Positionsdaten im Sport. Die Einzelbeiträge widmen sich der Systemvalidierung im Fußball, sowie der Mustererkennung zur automatischen Detektion von Sprintparametern in der Leichtathletik.

In this work, we focus on the problem of entity alignment in Knowledge Graphs (KG) and we report on our experiences when applying a Graph Convolutional Network (GCN) based model for this task. Variants of GCN are used in multiple state-of-the-art approaches and therefore it is important to understand the specifics and limitations of GCN-based models. Despite serious efforts, we were not able to fully reproduce the results from the original paper and after a thorough audit of the code provided by authors, we concluded, that their implementation is different from the architecture described in the paper. In addition, several tricks are required to make the model work and some of them are not very intuitive. We provide an extensive ablation study to quantify the effects these tricks and changes of architecture have on final performance. Furthermore, we examine current evaluation approaches and systematize available benchmark datasets. We believe that people interested in KG matching might profit from our work, as well as novices entering the field

In this work we address the problem of argument search. The purpose of argument search is the distillation of pro and contra arguments for requested topics from large text corpora. In previous works, the usual approach is to use a standard search engine to extract text parts which are relevant to the given topic and subsequently use an argument recognition algorithm to select arguments from them. The main challenge in the argument recognition task, which is also known as argument mining, is that often sentences containing arguments are structurally similar to purely informative sentences without any stance about the topic. In fact, they only differ semantically. Most approaches use topic or search term information only for the first search step and therefore assume that arguments can be classified independently of a topic. We argue that topic information is crucial for argument mining, since the topic defines the semantic context of an argument. Precisely, we propose different models for the classification of arguments, which take information about a topic of an argument into account. Moreover, to enrich the context of a topic and to let models understand the context of the potential argument better, we integrate information from different external sources such as Knowledge Graphs or pre-trained NLP models. Our evaluation shows that considering topic information, especially in connection with external information, provides a significant performance boost for the argument mining task.

Although various visual interfaces for digital libraries have been developed in prototypical systems, very few of these visual approaches have been integrated into today's digital libraries. In this position paper we argue that this is most likely due to the fact that the evaluation results of most visual systems lack comparability. There is no fix standard on how to evaluate visual interactive user interfaces. Therefore it is not possible to identify which approach is more suitable for a certain context. We feel that the comparability of evaluation results could be improved by building a common evaluation setup consisting of a reference system, based on a standardized corpus with fixed tasks and a panel for possible participants. (author's abstract)

The acquisition of data and its analysis has become a common yet critical task in many areas of modern economy and research. Unfortunately, the ever-increasing scale of datasets has long outgrown the capacities and abilities humans can muster to extract information from them and gain new knowledge. For this reason, research areas like data mining and knowledge discovery steadily gain importance. The algorithms they provide for the extraction of knowledge are mandatory prerequisites that enable people to analyze large amounts of information. Among the approaches offered by these areas, clustering is one of the most fundamental. By finding groups of similar objects inside the data, it aims to identify meaningful structures that constitute new knowledge. Clustering results are also often used as input for other analysis techniques like classification or forecasting. As clustering extracts new and unknown knowledge, it obviously has no access to any form of ground truth. For this reason, clustering results have a hypothetical character and must be interpreted with respect to the application domain. This makes clustering very challenging and leads to an extensive and diverse landscape of available algorithms. Most of these are expert tools that are tailored to a single narrowly defined application scenario. Over the years, this specialization has become a major trend that arose to counter the inherent uncertainty of clustering by including as much domain specifics as possible into algorithms. While customized methods often improve result quality, they become more and more complicated to handle and lose versatility. This creates a dilemma especially for amateur users whose numbers are increasing as clustering is applied in more and more domains. While an abundance of tools is offered, guidance is severely lacking and users are left alone with critical tasks like algorithm selection, parameter configuration and the interpretation and adjustment of results. This thesis aims

The acquisition of data and its analysis has become a common yet critical task in many areas of modern economy and research. Unfortunately, the ever-increasing scale of datasets has long outgrown the capacities and abilities humans can muster to extract information from them and gain new knowledge. For this reason, research areas like data mining and knowledge discovery steadily gain importance. The algorithms they provide for the extraction of knowledge are mandatory prerequisites that enable people to analyze large amounts of information. Among the approaches offered by these areas, clustering is one of the most fundamental. By finding groups of similar objects inside the data, it aims to identify meaningful structures that constitute new knowledge. Clustering results are also often used as input for other analysis techniques like classification or forecasting. As clustering extracts new and unknown knowledge, it obviously has no access to any form of ground truth. For this reason, clustering results have a hypothetical character and must be interpreted with respect to the application domain. This makes clustering very challenging and leads to an extensive and diverse landscape of available algorithms. Most of these are expert tools that are tailored to a single narrowly defined application scenario. Over the years, this specialization has become a major trend that arose to counter the inherent uncertainty of clustering by including as much domain specifics as possible into algorithms. While customized methods often improve result quality, they become more and more complicated to handle and lose versatility. This creates a dilemma especially for amateur users whose numbers are increasing as clustering is applied in more and more domains. While an abundance of tools is offered, guidance is severely lacking and users are left alone with critical tasks like algorithm selection, parameter configuration and the interpretation and adjustment of results. This thesis aims

The acquisition of data and its analysis has become a common yet critical task in many areas of modern economy and research. Unfortunately, the ever-increasing scale of datasets has long outgrown the capacities and abilities humans can muster to extract information from them and gain new knowledge. For this reason, research areas like data mining and knowledge discovery steadily gain importance. The algorithms they provide for the extraction of knowledge are mandatory prerequisites that enable people to analyze large amounts of information. Among the approaches offered by these areas, clustering is one of the most fundamental. By finding groups of similar objects inside the data, it aims to identify meaningful structures that constitute new knowledge. Clustering results are also often used as input for other analysis techniques like classification or forecasting. As clustering extracts new and unknown knowledge, it obviously has no access to any form of ground truth. For this reason, clustering results have a hypothetical character and must be interpreted with respect to the application domain. This makes clustering very challenging and leads to an extensive and diverse landscape of available algorithms. Most of these are expert tools that are tailored to a single narrowly defined application scenario. Over the years, this specialization has become a major trend that arose to counter the inherent uncertainty of clustering by including as much domain specifics as possible into algorithms. While customized methods often improve result quality, they become more and more complicated to handle and lose versatility. This creates a dilemma especially for amateur users whose numbers are increasing as clustering is applied in more and more domains. While an abundance of tools is offered, guidance is severely lacking and users are left alone with critical tasks like algorithm selection, parameter configuration and the interpretation and adjustment of results. This thesis aims

The acquisition of data and its analysis has become a common yet critical task in many areas of modern economy and research. Unfortunately, the ever-increasing scale of datasets has long outgrown the capacities and abilities humans can muster to extract information from them and gain new knowledge. For this reason, research areas like data mining and knowledge discovery steadily gain importance. The algorithms they provide for the extraction of knowledge are mandatory prerequisites that enable people to analyze large amounts of information. Among the approaches offered by these areas, clustering is one of the most fundamental. By finding groups of similar objects inside the data, it aims to identify meaningful structures that constitute new knowledge. Clustering results are also often used as input for other analysis techniques like classification or forecasting. As clustering extracts new and unknown knowledge, it obviously has no access to any form of ground truth. For this reason, clustering results have a hypothetical character and must be interpreted with respect to the application domain. This makes clustering very challenging and leads to an extensive and diverse landscape of available algorithms. Most of these are expert tools that are tailored to a single narrowly defined application scenario. Over the years, this specialization has become a major trend that arose to counter the inherent uncertainty of clustering by including as much domain specifics as possible into algorithms. While customized methods often improve result quality, they become more and more complicated to handle and lose versatility. This creates a dilemma especially for amateur users whose numbers are increasing as clustering is applied in more and more domains. While an abundance of tools is offered, guidance is severely lacking and users are left alone with critical tasks like algorithm selection, parameter configuration and the interpretation and adjustment of results. This thesis aims

Analyzing high dimensional data is a challenging task. For these data it is known that traditional clustering algorithms fail to detect meaningful patterns. As a solution, subspace clustering techniques have been introduced. They analyze arbitrary subspace projections of the data to detect clustering structures. In this paper, we present our subspace clustering extension for KDD frameworks, termed KDD-SC. In contrast to existing subspace clustering toolkits, our solution neither is a standalone product nor is it tightly coupled to a specific KDD framework. Our extension is realized by a common codebase and easy-to-use plugins for three of the most popular KDD frameworks, namely KNIME, RapidMiner, and WEKA. KDD-SC extends these frameworks such that they offer a wide range of different subspace clustering functionalities. It provides a multitude of algorithms, data generators, evaluation measures, and visualization techniques specifically designed for subspace clustering. These functionalities integrate seamlessly with the frameworks' existing features such that they can be flexibly combined. KDD-SC is publicly available on our website., Comment: 8 pages, 8 figures

This report documents the program and the outcomes of Dagstuhl Seminar 12081 “Information Visualization, Visual Data Mining and Machine Learning”. The aim of the seminar was to tighten the links between the information visualisation community and the machine learning community in order to explore how each field can benefit from the other and how to go beyond current hybridization successes.

This report documents the program and the outcomes of Dagstuhl Seminar 12081 ``Information Visualization, Visual Data Mining and Machine Learning''. The aim of the seminar was to tighten the links between the information visualisation community and the machine learning community in order to explore how each field can benefit from the other and how to go beyond current hybridization successes.

This report documents the program and the outcomes of Dagstuhl Seminar 12081 ``Information Visualization, Visual Data Mining and Machine Learning''. The aim of the seminar was to tighten the links between the information visualisation community and the machine learning community in order to explore how each field can benefit from the other and how to go beyond current hybridization successes.

Detecting outliers is an important task for many applications including fraud detection or consistency validation in real world data. Particularly in the presence of uncertain data or imprecise data, similar objects regularly deviate in their attribute values. The notion of outliers has thus to be defined carefully. When considering outlier detection as a task which is complementary to clustering, binary decisions whether an object is regarded to be an outlier or not seem to be near at hand. For high-dimensional data, however, objects may belong to different clusters in different subspaces. More fine-grained concepts to define outliers are therefore demanded. By our new OutRank approach, we address outlier detection in heterogeneous high dimensional data and propose a novel scoring function that provides a consistent model for ranking outliers in the presence of different attribute types. Preliminary experiments demonstrate the potential for successful detection and reasonable ranking of outliers in high dimensional data sets.

Detecting outliers is an important task for many applications including fraud detection or consistency validation in real world data. Particularly in the presence of uncertain data or imprecise data, similar objects regularly deviate in their attribute values. The notion of outliers has thus to be defined carefully. When considering outlier detection as a task which is complementary to clustering, binary decisions whether an object is regarded to be an outlier or not seem to be near at hand. For high-dimensional data, however, objects may belong to different clusters in different subspaces. More fine-grained concepts to define outliers are therefore demanded. By our new OutRank approach, we address outlier detection in heterogeneous high dimensional data and propose a novel scoring function that provides a consistent model for ranking outliers in the presence of different attribute types. Preliminary experiments demonstrate the potential for successful detection and reasonable ranking of outliers in high dimensional data sets.

This paper investigates the use of virtual reality (VR) technologies to facilitate the analysis of plant biological data in distinctive steps in the application pipeline. Reconstructed three-dimensional biological models (primary polygonal models) transferred to a virtual environment support scientists' collaborative exploration of biological datasets so that they obtain accurate analysis results and uncover information hidden in the data. Examples of the use of virtual reality in practice are provided and a complementary user study was performed.

This paper investigates the use of virtual reality (VR) technologies to facilitate the analysis of plant biological data in distinctive steps in the application pipeline. Reconstructed three-dimensional biological models (primary polygonal models) transferred to a virtual environment support scientists' collaborative exploration of biological datasets so that they obtain accurate analysis results and uncover information hidden in the data. Examples of the use of virtual reality in practice are provided and a complementary user study was performed.

This paper investigates the use of virtual reality (VR) technologies to facilitate the analysis of plant biological data in distinctive steps in the application pipeline. Reconstructed three-dimensional biological models (primary polygonal models) transferred to a virtual environment support scientists' collaborative exploration of biological datasets so that they obtain accurate analysis results and uncover information hidden in the data. Examples of the use of virtual reality in practice are provided and a complementary user study was performed.

This paper investigates the use of virtual reality (VR) technologies to facilitate the analysis of plant biological data in distinctive steps in the application pipeline. Reconstructed three-dimensional biological models (primary polygonal models) transferred to a virtual environment support scientists' collaborative exploration of biological datasets so that they obtain accurate analysis results and uncover information hidden in the data. Examples of the use of virtual reality in practice are provided and a complementary user study was performed.

Increasingly large multimedia databases in life sciences, e-commerce, or monitoring applications cannot be browsed manually, but require automatic knowledge discovery in databases (KDD) techniques to detect novel and interesting patterns. One of the major tasks in KDD, clustering, aims at grouping similar objects into clusters, separating dissimilar objects. Density-based clustering has been shown to detect arbitrarily shaped clusters even in noisy data bases. In high-dimensional data bases, meaningful clusters can no longer be detected due to the "curse of dimensionality". Consequently, subspace clustering searches for clusters hidden in any subset of the set of dimensions. As the number of subspaces is exponential in the number of dimensions, traditional approaches use fixed pruning thresholds. This results in dimensionality bias, i.e. with growing dimensionality, more clusters are missed. Clustering information is very useful for applications like fraud detection where outliers, i.e. objects which differ from all clusters, are searched. In subspace clustering, an object may be an outlier with respect to some groups, but not with respect to others, leading to possibly conflicting information. We propose a density-based unbiased subspace clustering model for outlier detection. We define outliers with respect to all maximal and non-redundant subspace clusters, taking their distance (deviation in attribute values), relevance (number of attributes covered) and support (number of objects covered) into account. We demonstrate the quality of our subspace clustering results in experiments on real world and synthetic databases and discuss our outlier model.

Increasingly large multimedia databases in life sciences, e-commerce, or monitoring applications cannot be browsed manually, but require automatic knowledge discovery in databases (KDD) techniques to detect novel and interesting patterns. One of the major tasks in KDD, clustering, aims at grouping similar objects into clusters, separating dissimilar objects. Density-based clustering has been shown to detect arbitrarily shaped clusters even in noisy data bases. In high-dimensional data bases, meaningful clusters can no longer be detected due to the "curse of dimensionality". Consequently, subspace clustering searches for clusters hidden in any subset of the set of dimensions. As the number of subspaces is exponential in the number of dimensions, traditional approaches use fixed pruning thresholds. This results in dimensionality bias, i.e. with growing dimensionality, more clusters are missed. Clustering information is very useful for applications like fraud detection where outliers, i.e. objects which differ from all clusters, are searched. In subspace clustering, an object may be an outlier with respect to some groups, but not with respect to others, leading to possibly conflicting information. We propose a density-based unbiased subspace clustering model for outlier detection. We define outliers with respect to all maximal and non-redundant subspace clusters, taking their distance (deviation in attribute values), relevance (number of attributes covered) and support (number of objects covered) into account. We demonstrate the quality of our subspace clustering results in experiments on real world and synthetic databases and discuss our outlier model.

Similarity search in large multimedia databases requires ef- ficient query processing based on suitable similarity models. Similarity models consist of a feature extraction step as well as a distance defined for these features, and they demand an efficient algorithm for retrieving similar objects under this model. In this work, we focus on the Earth Movers Distance (EMD), a recently introduced similarity model which has been successfully employed in numerous applications and has been reported as well reflecting human perceptual similarity. As its computation is complex, the direct application of the EMD to large, high-dimensional databases is not feasible. To remedy this and allow users to benefit from the high quality of the model even in larger settings, we developed various lower bounds for the EMD to be used in index-supported multistep query processing algorithms. We prove that our algorithms are complete, thus producing no false drops. We also show that it is highly efficient as experiments on large image databases with high-dimensional features demonstrate.

Similarity search in large multimedia databases requires ef- ficient query processing based on suitable similarity models. Similarity models consist of a feature extraction step as well as a distance defined for these features, and they demand an efficient algorithm for retrieving similar objects under this model. In this work, we focus on the Earth Movers Distance (EMD), a recently introduced similarity model which has been successfully employed in numerous applications and has been reported as well reflecting human perceptual similarity. As its computation is complex, the direct application of the EMD to large, high-dimensional databases is not feasible. To remedy this and allow users to benefit from the high quality of the model even in larger settings, we developed various lower bounds for the EMD to be used in index-supported multistep query processing algorithms. We prove that our algorithms are complete, thus producing no false drops. We also show that it is highly efficient as experiments on large image databases with high-dimensional features demonstrate.

A lot of information on the web is geographically referenced. Discovering and linking this information poses eminent research challenges to the geospatial semantic web, with regards to the representation and manipulation of geographic data. Towards addressing these challenges, this work explores the potential of the current semantic web languages and tools. In particular, an integrated logical framework of rules and ontologies, using current W3C standards, is assessed for modeling geospatial ontologies of place encoding both symbolic and geometric references to place locations. Spatial reasoning is incorporated in the framework to facilitate the deduction of implicit semantics and for expressing spatial integrity constraints. The logical framework is then extended with geo-computation engines that offer more effective manipulations of geometric information. Example data sets mined from web resources are used to demonstrate and evaluate both frameworks, offering insights to their potentials and limitations.