Picture for Dominik Alfke

Dominik Alfke

A Study of Graph-Based Approaches for Semi-Supervised Time Series Classification

Add code
Apr 16, 2021
Figure 1 for A Study of Graph-Based Approaches for Semi-Supervised Time Series Classification
Figure 2 for A Study of Graph-Based Approaches for Semi-Supervised Time Series Classification
Figure 3 for A Study of Graph-Based Approaches for Semi-Supervised Time Series Classification
Figure 4 for A Study of Graph-Based Approaches for Semi-Supervised Time Series Classification
Viaarxiv icon

Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs

Add code
Aug 03, 2020
Figure 1 for Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs
Figure 2 for Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs
Figure 3 for Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs
Figure 4 for Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs
Viaarxiv icon

Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks

Add code
May 24, 2019
Figure 1 for Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks
Figure 2 for Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks
Figure 3 for Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks
Figure 4 for Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks
Viaarxiv icon

The Oracle of DLphi

Add code
Jan 27, 2019
Viaarxiv icon

NFFT meets Krylov methods: Fast matrix-vector products for the graph Laplacian of fully connected networks

Add code
Aug 14, 2018
Figure 1 for NFFT meets Krylov methods: Fast matrix-vector products for the graph Laplacian of fully connected networks
Figure 2 for NFFT meets Krylov methods: Fast matrix-vector products for the graph Laplacian of fully connected networks
Figure 3 for NFFT meets Krylov methods: Fast matrix-vector products for the graph Laplacian of fully connected networks
Figure 4 for NFFT meets Krylov methods: Fast matrix-vector products for the graph Laplacian of fully connected networks
Viaarxiv icon