Volker Tresp - Academia.edu (original) (raw)

Papers by Volker Tresp

2021 IEEE 9th International Conference on Healthcare Informatics (ICHI)

Deep neural networks are increasingly being used for the analysis of medical images. However, mos... more Deep neural networks are increasingly being used for the analysis of medical images. However, most works neglect the uncertainty in the model's prediction. We propose an uncertainty-aware deep kernel learning model which permits the estimation of the uncertainty in the prediction by a pipeline of a Convolutional Neural Network and a sparse Gaussian Process. Furthermore, we adapt different pre-training methods to investigate their impacts on the proposed model. We apply our approach to Bone Age Prediction and Lesion Localization. In most cases, the proposed model shows better performance compared to common architectures. More importantly, our model expresses systematically higher confidence in more accurate predictions and less confidence in less accurate ones. Our model can also be used to detect challenging and controversial test samples. Compared to related methods such as Monte-Carlo Dropout, our approach derives the uncertainty information in a purely analytical fashion and is thus computationally more efficient.

In label-ranking, the goal is to learn a mapping from instances to rankings (total orders) over a... more In label-ranking, the goal is to learn a mapping from instances to rankings (total orders) over a fixed set of labels. Hitherto existing approaches to label-ranking implicitly operate on an underlying (utility) scale which is not calibrated, that is, which lacks a natural zero point. Since this severely restricts the expressive power of these approaches, we propose a suitable extension of the constraint classification framework to labelranking. Beyond the general case, we focus on a particular category of ranking problems which admit a representation as a special instance of calibrated label-ranking: In top label-ranking, an extension of multilabel classification an ordering is required for the subset of labels relevant for the given instance.

2000 10th European Signal Processing Conference, 2000

In classification problems, it is preferred to attack the discrimination problem directly rather ... more In classification problems, it is preferred to attack the discrimination problem directly rather than indirectly by first estimating the class densities and by then estimating the discrimination function from the generative models through Bayes's rule. Sometimes, however, it is convenient to express the models as probabilistic models, since they are generative in nature and can handle the representation of high-dimensional data like time-series. In this paper, we derive a discriminative training procedure based on Learning Vector Quantization (LVQ) where the codebook is expressed in terms of probabilistic models. The likelihood-based distance measure is justified using the Kullback-Leibler distance. In updating the winner unit, a gradient learning step is taken with regard to the parameters of the probabilistic model. The method essentially departs from a prototypical representation and incorporates learning in the parameter space of generative models. As an illustration, we pre...

ArXiv, 2020

Recently, knowledge graph embeddings (KGEs) received significant attention, and several software ... more Recently, knowledge graph embeddings (KGEs) received significant attention, and several software libraries have been developed for training and evaluating KGEs. While each of them addresses specific needs, we re-designed and re-implemented PyKEEN, one of the first KGE libraries, in a community effort. PyKEEN 1.0 enables users to compose knowledge graph embedding models (KGEMs) based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. Besides, an automatic memory optimization has been realized in order to exploit the provided hardware optimally, and through the integration of Optuna extensive hyper-parameter optimization (HPO) functionalities are provided.

In this paper we define Clinical Data Intelligence as the analysis of data generated in the clini... more In this paper we define Clinical Data Intelligence as the analysis of data generated in the clinical routine with the goal of improving patient care. We define a science of a Clinical Data Intelligence as a data analysis that permits the derivation of scientific, i.e., generalizable and reliable results. We argue that a science of a Clinical Data Intelligence is sensible in the context of a Big Data analysis, i.e., with data from many patients and with complete patient information. We discuss that Clinical Data Intelligence requires the joint efforts of knowledge engineering, information extraction (from textual and other unstructured data), and statistics and statistical machine learning. We describe some of our main results as conjectures and relate them to a recently funded research project involving two major German university hospitals.

Lecture Notes in Computer Science

In this work, we focus on the problem of entity alignment in Knowledge Graphs (KG) and we report ... more 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.

Proceedings of the IEEE, 2016

Relational machine learning studies methods for the statistical analysis of relational, or graph-... more Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be "trained" on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph). In particular, we discuss two fundamentally different kinds of statistical relational models, both of which can scale to massive datasets. The first is based on latent feature models such as tensor factorization and multiway neural networks. The second is based on mining observable patterns in the graph. We also show how to combine these latent and observable models to get improved modeling power at decreased computational cost. Finally, we discuss how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web. To this end, we also discuss Google's Knowledge Vault project as an example of such combination.

Lecture Notes in Computer Science, 2001

Empirical evidence indicates that the training time for the support vector machine (SVM) scales t... more Empirical evidence indicates that the training time for the support vector machine (SVM) scales to the square of the number of training data points. In this paper, we introduce the Bayesian committee support vector machine (BC-SVM) and achieve an algorithm for training the SVM which scales linearly in the number of training data points. We verify the good performance of the BC-SVM using several data sets.

Electrical Engineering & Applied Signal Processing Series, 2001