• Publications
  • Influence
Set Functions for Time Series
TLDR
This paper proposes a novel approach for classifying irregularly-sampled time series with unaligned measurements, focusing on high scalability and data efficiency, and is based on recent advances in differentiable set function learning, extremely parallelizable with a beneficial memory footprint. Expand
Wasserstein Weisfeiler-Lehman Graph Kernels
TLDR
A novel method that relies on the Wasserstein distance between the node feature vector distributions of two graphs, which allows to find subtler differences in data sets by considering graphs as high-dimensional objects, rather than simple means is proposed. Expand
Topological Autoencoders
TLDR
It is shown that the proposed approach to preserving topological structures of the input space in latent representations of autoencoders exhibits favourable latent representations on a synthetic manifold as well as on real-world image data sets, while preserving low reconstruction errors. Expand
Persistent Homology for the Evaluation of Dimensionality Reduction Schemes
TLDR
This work presents a novel technique to quantify and compare the quality of DR algorithms that is based on persistent homology, and provides knowledge about the local quality of an embedding, thereby helping users understand the shortcomings of the selected DR method. Expand
Graph Filtration Learning
TLDR
An approach to learning with graph-structured data in the problem domain of graph classification is proposed, and a novel type of readout operation to aggregate node features into a graph-level representation is presented. Expand
Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
TLDR
This work proposes neural persistence, a complexity measure for neural network architectures based on topological data analysis on weighted stratified graphs and derives a neural persistence-based stopping criterion that shortens the training process while achieving comparable accuracies as early stopping based on validation loss. Expand
A Persistent Weisfeiler-Lehman Procedure for Graph Classification
TLDR
This work leverages propagated node label information and transform unweighted graphs into metric ones to augment the subtree features with topological information obtained using persistent homology, a concept from topological data analysis. Expand
Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping
TLDR
This empirical study proposes two novel approaches for the early detection of sepsis: a deep learning model and a lazy learner based on time series distances based on a temporal convolutional network that is embedded in a Multi-task Gaussian Process Adapter framework. Expand
Graph Kernels: State-of-the-Art and Future Challenges
TLDR
This manuscript provides a review of existing graph kernels, their applications, software plus data resources, and an empirical comparison of state-of-the-art graph kernels. Expand
Agreement Analysis of Quality Measures for Dimensionality Reduction
TLDR
This work proposes an algorithm based on persistent homology that permits the comparative analysis of different quality measures on a given embedding, regardless of their ranges, and provides local feedback about which aspects of a data set are preserved by an embedding in certain areas. Expand
...
1
2
3
4
5
...