• Publications
  • Influence
Hierarchical Graph Representation Learning with Differentiable Pooling
TLDR
We propose a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. Expand
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
TLDR
In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. Expand
Deep Graph Matching Consensus
TLDR
This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs, on which we improve upon the current state-of-the-art. Expand
A survey on graph kernels
TLDR
Graph kernels have become an established and widely-used technique for solving classification tasks on graphs. Expand
TUDataset: A collection of benchmark datasets for learning with graphs
Recently, there has been an increasing interest in (supervised) learning with graph data, especially using graph neural networks. However, the development of meaningful benchmark datasets andExpand
Faster Kernels for Graphs with Continuous Attributes via Hashing
TLDR
We present hash graph kernels, a general framework to derive kernels for graphs with continuous attributes from discrete ones. Expand
Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs
TLDR
We proposed a graph kernel based on a local variant of the (global) k-dimensional Weisfeiler-Lehman algorithm, which explores the space between local and global graph properties. Expand
A Property Testing Framework for the Theoretical Expressivity of Graph Kernels
TLDR
We introduce a theoretical framework for investigating the expressive power of graph kernels, which is inspired by concepts from the area of property testing. Expand
Output-sensitive Complexity of Multiobjective Combinatorial Optimization
TLDR
We study output-sensitive algorithms and complexity for multiobjective combinatorial optimization problems. Expand
A Unifying View of Explicit and Implicit Feature Maps for Structured Data: Systematic Studies of Graph Kernels
TLDR
We investigate how general convolution kernels are composed from base kernels and apply them to real-world graphs with discrete labels. Expand
...
1
2
...