arXiv subjects

Mathias Niepert

Publications and source records attributed to Mathias Niepert.

At least 109 records · Page 6Linked to original sources

arXiv2018

KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features

We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features. KBLRN integrates feature types with a novel combination of neural representation learning and probabilistic product of experts models. To the best of our knowledge, KBLRN is the first approach that learns representations of knowledge bases by integrating latent, relational, and numerical features. We show that instances of KBLRN outperform existing methods on a range of knowledge base completion tasks. We contribute a novel data sets enriching commonly used knowledge base completion benchmarks with numerical features. The data sets are available under a permissive BSD-3 license. We also investigate the impact numerical features have on the KB completion performance of KBLRN.

cs.AI↗

arXiv2018

Contextual Hourglass Networks for Segmentation and Density Estimation

Hourglass networks such as the U-Net and V-Net are popular neural architectures for medical image segmentation and counting problems. Typical instances of hourglass networks contain shortcut connections between mirroring layers. These shortcut connections improve the performance and it is hypothesized that this is due to mitigating effects on the vanishing gradient problem and the ability of the model to combine feature maps from earlier and later layers. We propose a method for not only combining feature maps of mirroring layers but also feature maps of layers with different spatial dimensions. For instance, the method enables the integration of the bottleneck feature map with those of the reconstruction layers. The proposed approach is applicable to any hourglass architecture. We evaluated the contextual hourglass networks on image segmentation and object counting problems in the medical domain. We achieve competitive results outperforming popular hourglass networks by up to 17 percentage points.

cs.CV↗

arXiv2018

Towards a Spectrum of Graph Convolutional Networks

We present our ongoing work on understanding the limitations of graph convolutional networks (GCNs) as well as our work on generalizations of graph convolutions for representing more complex node attribute dependencies. Based on an analysis of GCNs with the help of the corresponding computation graphs, we propose a generalization of existing GCNs where the aggregation operations are (a) determined by structural properties of the local neighborhood graphs and (b) not restricted to weighted averages. We show that the proposed approach is strictly more expressive while requiring only a modest increase in the number of parameters and computations. We also show that the proposed generalization is identical to standard convolutional layers when applied to regular grid graphs.

cs.LG↗

arXiv2018

BrainSlug: Transparent Acceleration of Deep Learning Through Depth-First Parallelism

Neural network frameworks such as PyTorch and TensorFlow are the workhorses of numerous machine learning applications ranging from object recognition to machine translation. While these frameworks are versatile and straightforward to use, the training of and inference in deep neural networks is resource (energy, compute, and memory) intensive. In contrast to recent works focusing on algorithmic enhancements, we introduce BrainSlug, a framework that transparently accelerates neural network workloads by changing the default layer-by-layer processing to a depth-first approach, reducing the amount of data required by the computations and thus improving the performance of the available hardware caches. BrainSlug achieves performance improvements of up to 41.1% on CPUs and 35.7% on GPUs. These optimizations come at zero cost to the user as they do not require hardware changes and only need tiny adjustments to the software.

cs.DC↗

arXiv2018

TransRev: Modeling Reviews as Translations from Users to Items

The text of a review expresses the sentiment a customer has towards a particular product. This is exploited in sentiment analysis where machine learning models are used to predict the review score from the text of the review. Furthermore, the products costumers have purchased in the past are indicative of the products they will purchase in the future. This is what recommender systems exploit by learning models from purchase information to predict the items a customer might be interested in. We propose TransRev, an approach to the product recommendation problem that integrates ideas from recommender systems, sentiment analysis, and multi-relational learning into a joint learning objective. TransRev learns vector representations for users, items, and reviews. The embedding of a review is learned such that (a) it performs well as input feature of a regression model for sentiment prediction; and (b) it always translates the reviewer embedding to the embedding of the reviewed items. This allows TransRev to approximate a review embedding at test time as the difference of the embedding of each item and the user embedding. The approximated review embedding is then used with the regression model to predict the review score for each item. TransRev outperforms state of the art recommender systems on a large number of benchmark data sets. Moreover, it is able to retrieve, for each user and item, the review text from the training set whose embedding is most similar to the approximated review embedding.

cs.IR↗

arXiv2018

Representation Learning for Resource Usage Prediction

Creating a model of a computer system that can be used for tasks such as predicting future resource usage and detecting anomalies is a challenging problem. Most current systems rely on heuristics and overly simplistic assumptions about the workloads and system statistics. These heuristics are typically a one-size-fits-all solution so as to be applicable in a wide range of applications and systems environments. With this paper, we present our ongoing work of integrating systems telemetry ranging from standard resource usage statistics to kernel and library calls of applications into a machine learning model. Intuitively, such a ML model approximates, at any point in time, the state of a system and allows us to solve tasks such as resource usage prediction and anomaly detection. To achieve this goal, we leverage readily-available information that does not require any changes to the applications run on the system. We train recurrent neural networks to learn a model of the system under consideration. As a proof of concept, we train models specifically to predict future resource usage of running applications.

cs.DC↗

arXiv2017

Learning Graph Representations with Embedding Propagation

We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data. EP learns vector representations of graphs by passing two types of messages between neighboring nodes. Forward messages consist of label representations such as representations of words and other attributes associated with the nodes. Backward messages consist of gradients that result from aggregating the label representations and applying a reconstruction loss. Node representations are finally computed from the representation of their labels. With significantly fewer parameters and hyperparameters an instance of EP is competitive with and often outperforms state of the art unsupervised and semi-supervised learning methods on a range of benchmark data sets.

cs.LG↗

arXiv2017

Net2Vec: Deep Learning for the Network

We present Net2Vec, a flexible high-performance platform that allows the execution of deep learning algorithms in the communication network. Net2Vec is able to capture data from the network at more than 60Gbps, transform it into meaningful tuples and apply predictions over the tuples in real time. This platform can be used for different purposes ranging from traffic classification to network performance analysis. Finally, we showcase the use of Net2Vec by implementing and testing a solution able to profile network users at line rate using traces coming from a real network. We show that the use of deep learning for this case outperforms the baseline method both in terms of accuracy and performance.

cs.NI↗

arXiv2016

Discriminative Gaifman Models

We present discriminative Gaifman models, a novel family of relational machine learning models. Gaifman models learn feature representations bottom up from representations of locally connected and bounded-size regions of knowledge bases (KBs). Considering local and bounded-size neighborhoods of knowledge bases renders logical inference and learning tractable, mitigates the problem of overfitting, and facilitates weight sharing. Gaifman models sample neighborhoods of knowledge bases so as to make the learned relational models more robust to missing objects and relations which is a common situation in open-world KBs. We present the core ideas of Gaifman models and apply them to large-scale relational learning problems. We also discuss the ways in which Gaifman models relate to some existing relational machine learning approaches.

cs.LG↗

arXiv2016

Learning Convolutional Neural Networks for Graphs

Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient.

cs.LG↗

arXiv2014

Lifted Probabilistic Inference for Asymmetric Graphical Models

Lifted probabilistic inference algorithms have been successfully applied to a large number of symmetric graphical models. Unfortunately, the majority of real-world graphical models is asymmetric. This is even the case for relational representations when evidence is given. Therefore, more recent work in the community moved to making the models symmetric and then applying existing lifted inference algorithms. However, this approach has two shortcomings. First, all existing over-symmetric approximations require a relational representation such as Markov logic networks. Second, the induced symmetries often change the distribution significantly, making the computed probabilities highly biased. We present a framework for probabilistic sampling-based inference that only uses the induced approximate symmetries to propose steps in a Metropolis-Hastings style Markov chain. The framework, therefore, leads to improved probability estimates while remaining unbiased. Experiments demonstrate that the approach outperforms existing MCMC algorithms.

cs.AI↗

arXiv2014

On the Conditional Independence Implication Problem: A Lattice-Theoretic Approach

A lattice-theoretic framework is introduced that permits the study of the conditional independence (CI) implication problem relative to the class of discrete probability measures. Semi-lattices are associated with CI statements and a finite, sound and complete inference system relative to semi-lattice inclusions is presented. This system is shown to be (1) sound and complete for saturated CI statements, (2) complete for general CI statements, and (3) sound and complete for stable CI statements. These results yield a criterion that can be used to falsify instances of the implication problem and several heuristics are derived that approximate this "lattice-exclusion" criterion in polynomial time. Finally, we provide experimental results that relate our work to results obtained from other existing inference algorithms.

cs.AI↗

arXiv2014

Markov Chains on Orbits of Permutation Groups

We present a novel approach to detecting and utilizing symmetries in probabilistic graphical models with two main contributions. First, we present a scalable approach to computing generating sets of permutation groups representing the symmetries of graphical models. Second, we introduce orbital Markov chains, a novel family of Markov chains leveraging model symmetries to reduce mixing times. We establish an insightful connection between model symmetries and rapid mixing of orbital Markov chains. Thus, we present the first lifted MCMC algorithm for probabilistic graphical models. Both analytical and empirical results demonstrate the effectiveness and efficiency of the approach.

cs.AI↗

arXiv2014

LODE: Linking Digital Humanities Content to the Web of Data

Numerous digital humanities projects maintain their data collections in the form of text, images, and metadata. While data may be stored in many formats, from plain text to XML to relational databases, the use of the resource description framework (RDF) as a standardized representation has gained considerable traction during the last five years. Almost every digital humanities meeting has at least one session concerned with the topic of digital humanities, RDF, and linked data. While most existing work in linked data has focused on improving algorithms for entity matching, the aim of the LinkedHumanities project is to build digital humanities tools that work "out of the box," enabling their use by humanities scholars, computer scientists, librarians, and information scientists alike. With this paper, we report on the Linked Open Data Enhancer (LODE) framework developed as part of the LinkedHumanities project. With LODE we support non-technical users to enrich a local RDF repository with high-quality data from the Linked Open Data cloud. LODE links and enhances the local RDF repository without compromising the quality of the data. In particular, LODE supports the user in the enhancement and linking process by providing intuitive user-interfaces and by suggesting high-quality linking candidates using tailored matching algorithms. We hope that the LODE framework will be useful to digital humanities scholars complementing other digital humanities tools.

cs.DL↗

arXiv2014

Exchangeable Variable Models

A sequence of random variables is exchangeable if its joint distribution is invariant under variable permutations. We introduce exchangeable variable models (EVMs) as a novel class of probabilistic models whose basic building blocks are partially exchangeable sequences, a generalization of exchangeable sequences. We prove that a family of tractable EVMs is optimal under zero-one loss for a large class of functions, including parity and threshold functions, and strictly subsumes existing tractable independence-based model families. Extensive experiments show that EVMs outperform state of the art classifiers such as SVMs and probabilistic models which are solely based on independence assumptions.

cs.LG↗

arXiv2014

Tractability through Exchangeability: A New Perspective on Efficient Probabilistic Inference

Exchangeability is a central notion in statistics and probability theory. The assumption that an infinite sequence of data points is exchangeable is at the core of Bayesian statistics. However, finite exchangeability as a statistical property that renders probabilistic inference tractable is less well-understood. We develop a theory of finite exchangeability and its relation to tractable probabilistic inference. The theory is complementary to that of independence and conditional independence. We show that tractable inference in probabilistic models with high treewidth and millions of variables can be understood using the notion of finite (partial) exchangeability. We also show that existing lifted inference algorithms implicitly utilize a combination of conditional independence and partial exchangeability.

cs.AI↗

arXiv2013

RockIt: Exploiting Parallelism and Symmetry for MAP Inference in Statistical Relational Models

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.

cs.AI↗

arXiv2013

Symmetry-Aware Marginal Density Estimation

The Rao-Blackwell theorem is utilized to analyze and improve the scalability of inference in large probabilistic models that exhibit symmetries. A novel marginal density estimator is introduced and shown both analytically and empirically to outperform standard estimators by several orders of magnitude. The developed theory and algorithms apply to a broad class of probabilistic models including statistical relational models considered not susceptible to lifted probabilistic inference.

cs.AI↗