Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS

Filters

1
Reset filters

Settings
Now showing 1 - 10 of 808
  • Publication
    An Optimization for Convolutional Network Layers Using the Viola-Jones Framework and Ternary Weight Networks
    ( 2021-12-09)
    Agombar, Rhys
    ;
    Bauckhage, Christian
    ;
    Lübbering, Max
    ;
    Sifa, Rafet
    Neural networks have the potential to be extremely powerful for computer vision related tasks, but can be computationally expensive. Classical methods, by comparison, tend to be relatively light weight, albeit not as powerful. In this paper, we propose a method of combining parts from a classical system, called the Viola-Jones Object Detection Framework, with a modern ternary neural network to improve the efficiency of a convolutional neural net by replacing convolutional filters with a set of custom ones inspired by the framework. This reduces the number of operations needed for computing feature values with negligible effects on overall accuracy, allowing for a more optimized network.
  • Publication
    Decoupling Autoencoders for Robust One-vs-Rest Classification
    ( 2021-10-20)
    Lübbering, Max
    ;
    Gebauer, Michael
    ;
    Ramamurthy, Rajkumar
    ;
    Bauckhage, Christian
    ;
    Sifa, Rafet
    One-vs-Rest (OVR) classification aims to distinguish a single class of interest from other classes. The concept of novelty detection and robustness to dataset shift becomes crucial in OVR when the scope of the rest class extends from the classes observed during training to unseen and possibly unrelated classes. In this work, we propose a novel architecture, namely Decoupling Autoencoder (DAE) to tackle the common issue of robustness w.r.t. out-of-distribution samples which is prevalent in classifiers such as multi-layer perceptrons (MLP) and ensemble architectures. Experiments on plain classification, outlier detection, and dataset shift tasks show DAE to achieve robust performance across these tasks compared to the baselines, which tend to fail completely, when exposed to dataset shift. W hile DAE and the baselines yield rather uncalibrated predictions on the outlier detection and dataset shift task, we found that DAE calibration is more stable across all tasks. Therefore, calibration measures applied to the classification task could also improve the calibration of the outlier detection and dataset shift scenarios for DAE.
  • Publication
    Learning Weakly Convex Sets in Metric Spaces
    ( 2021-09-10)
    Stadtländer, Eike
    ;
    Horvath, Tamas
    ;
    Wrobel, Stefan
    We introduce the notion of weak convexity in metric spaces, a generalization of ordinary convexity commonly used in machine learning. It is shown that weakly convex sets can be characterized by a closure operator and have a unique decomposition into a set of pairwise disjoint connected blocks. We give two generic efficient algorithms, an extensional and an intensional one for learning weakly convex concepts and study their formal properties. Our experimental results concerning vertex classification clearly demonstrate the excellent predictive performance of the extensional algorithm. Two non-trivial applications of the intensional algorithm to polynomial PAC-learnability are presented. The first one deals with learning k-convex Boolean functions, which are already known to be efficiently PAC-learnable. It is shown how to derive this positive result in a fairly easy way by the generic intensional algorithm. The second one is concerned with the Euclidean space equipped with the Manhattan distance. For this metric space, weakly convex sets form a union of pairwise disjoint axis-aligned hyperrectangles. We show that a weakly convex set that is consistent with a set of examples and contains a minimum number of hyperrectangles can be found in polynomial time. In contrast, this problem is known to be NP-complete if the hyperrectangles may be overlapping.
  • Publication
    Advances in Password Recovery Using Generative Deep Learning Techniques
    ( 2021-09-07)
    Biesner, David
    ;
    Cvejoski, Kostadin
    ;
    Georgiev, Bogdan
    ;
    Sifa, Rafet
    ;
    Krupicka, Erik
    Password guessing approaches via deep learning have recently been investigated with significant breakthroughs in their ability to generate novel, realistic password candidates. In the present work we study a broad collection of deep learning and probabilistic based models in the light of password guessing: attention-based deep neural networks, autoencoding mechanisms and generative adversarial networks. We provide novel generative deep-learning models in terms of variational autoencoders exhibiting state-of-art sampling performance, yielding additional latent-space features such as interpolations and targeted sampling. Lastly, we perform a thorough empirical analysis in a unified controlled framework over well-known datasets (RockYou, LinkedIn, MySpace, Youku, Zomato, Pwnd). Our results not only identify the most promising schemes driven by deep neural networks, but also illustrate the strengths of each approach in terms of generation variability and sample uniqueness.
  • Publication
    ALiBERT: Improved automated list inspection (ALI) with BERT
    ( 2021-08-16)
    Ramamurthy, Rajkumar
    ;
    Pielka, Maren
    ;
    Stenzel, Marc Robin
    ;
    Bauckhage, Christian
    ;
    Sifa, Rafet
    ;
    Khameneh, Tim Dilmaghani
    ;
    Warning, Ulrich
    ;
    Kliem, Bernd
    ;
    Loitz, Rüdiger
    We consider Automated List Inspection (ALI), a content-based text recommendation system that assists auditors in matching relevant text passages from notes in financial statements to specific law regulations. ALI follows a ranking paradigm in which a fixed number of requirements per textual passage are shown to the user. Despite achieving impressive ranking performance, the user experience can still be improved by showing a dynamic number of recommendations. Besides, existing models rely on a feature-based language model that needs to be pre-trained on a large corpus of domain-specific datasets. Moreover, they cannot be trained in an end-to-end fashion by jointly optimizing with language model parameters. In this work, we alleviate these concerns by considering a multi-label classification approach that predicts dynamic requirement sequences. We base our model on pre-trained BERT that allows us to fine-tune the whole model in an end-to-end fashion, thereby avoiding the need for training a language representation model. We conclude by presenting a detailed evaluation of the proposed model on two German financial datasets.
  • Publication
    Decision Snippet Features
    ( 2021-05-05)
    Welke, Pascal
    ;
    Alkhoury, Fouad
    ;
    Bauckhage, Christian
    ;
    Wrobel, Stefan
    Decision trees excel at interpretability of their prediction results. To achieve required prediction accuracies, however, often large ensembles of decision trees random forests are considered, reducing interpretability due to large size. Additionally, their size slows down inference on modern hardware and restricts their applicability in low-memory embedded devices. We introduce Decision Snippet Features, which are obtained from small subtrees that appear frequently in trained random forests. We subsequently show that linear models on top of these features achieve comparable and sometimes even better predictive performance than the original random forest, while reducing the model size by up to two orders of magnitude.
  • Publication
    Switching Dynamical Systems with Deep Neural Networks
    ( 2021-05-05)
    Ojeda, César
    ;
    Georgiev, Bogdan
    ;
    Cvejoski, Kostadin
    ;
    Schücker, Jannis
    ;
    Bauckhage, Christian
    ;
    Sánchez, Ramsés J.
    The problem of uncovering different dynamical regimes is of pivotal importance in time series analysis. Switching dynamical systems provide a solution for modeling physical phenomena whose time series data exhibit different dynamical modes. In this work we propose a novel variational RNN model for switching dynamics allowing for both non-Markovian and nonlinear dynamical behavior between and within dynamic modes. Attention mechanisms are provided to inform the switching distribution. We evaluate our model on synthetic and empirical datasets of diverse nature and successfully uncover different dynamical regimes and predict the switching dynamics.
  • Publication
    Auto Encoding Explanatory Examples with Stochastic Paths
    ( 2021-05-05)
    Ojeda, César
    ;
    Sánchez, Ramsés J.
    ;
    Cvejoski, Kostadin
    ;
    Schücker, Jannis
    ;
    Bauckhage, Christian
    ;
    Georgiev, Bogdan
    In this paper we ask for the main factors that determine a classifiers decision making process and uncover such factors by studying latent codes produced by auto-encoding frameworks. To deliver an explanation of a classifiers behaviour, we propose a method that provides series of examples highlighting semantic differences between the classifiers decisions. These examples are generated through interpolations in latent space. We introduce and formalize the notion of a semantic stochastic path, as a suitable stochastic process defined in feature (data) space via latent code interpolations. We then introduce the concept of semantic Lagrangians as a way to incorporate the desired classifiers behaviour and find that the solution of the associated variational problem allows for highli ghting differences in the classifier decision. Very importantly, within our framework the classifier is used as a black-box, and only its evaluation is required.
  • Publication
    Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge Graphs
    ( 2021)
    Xu, Chengjin
    ;
    Su, Fenglong
    ;
    Lehmann, Jens
    Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs). Recently, the availability of temporal KGs (TKGs) that contain time information created the need for reasoning over time in such TKGs. Existing embedding-based entity alignment approaches disregard time information that commonly exists in many large-scale KGs, leaving much room for improvement. In this paper, we focus on the task of aligning entity pairs between TKGs and propose a novel Time-aware Entity Alignment approach based on Graph Neural Networks (TEA-GNN). We embed entities, relations and timestamps of different KGs into a vector space and use GNNs to learn entity representations. To incorporate both relation and time information into the GNN structure of our model, we use a self-att ention mechanism which assigns different weights to different nodes with orthogonal transformation matrices computed from embeddings of the relevant relations and timestamps in a neighborhood. Experimental results on multiple real-world TKG datasets show that our method significantly outperforms the state-of-the-art methods due to the inclusion of time information.
  • Publication
    DistSim - Scalable Distributed in-Memory Semantic Similarity Estimation for RDF Knowledge Graphs
    ( 2021)
    Draschner, Carsten Felix
    ;
    Lehmann, Jens
    ;
    Jabeen, Hajira
    In this paper, we present DistSim, a Scalable Distributed in-Memory Semantic Similarity Estimation framework for Knowledge Graphs. DistSim provides a multitude of state-of-the-art similarity estimators. We have developed the Similarity Estimation Pipeline by combining generic software modules. For large scale RDF data, DistSim proposes MinHash with locality sensitivity hashing to achieve better scalability over all-pair similarity estimations. The modules of DistSim can be set up using a multitude of (hyper)-parameters allowing to adjust the tradeoff between information taken into account, and processing time. Furthermore, the output of the Similarity Estimation Pipeline is native RDF. DistSim is integrated into the SANSA stack, documented in scala-docs, and covered by unit tests. Addition ally, the variables and provided methods follow the Apache Spark MLlib name-space conventions. The performance of DistSim was tested over a distributed cluster, for the dimensions of data set size and processing power versus processing time, which shows the scalability of DistSim w.r.t. increasing data set sizes and processing power. DistSim is already in use for solving several RDF data analytics related use cases. Additionally, DistSim is available and integrated into the open-source GitHub project SANSA.