Numerous recent works have analyzed the expressive power of message-pass...
Recently, transformer architectures for graphs emerged as an alternative...
Recently, many works studied the expressive power of graph neural networ...
Knowledge graphs, modeling multi-relational data, improve numerous
appli...
Numerous subgraph-enhanced graph neural networks (GNNs) have emerged
rec...
Mixed-integer programming (MIP) technology offers a generic way of
formu...
While (message-passing) graph neural networks have clear limitations in
...
Combinatorial optimization is a well-established area in operations rese...
In recent years, algorithms and neural architectures based on the
Weisfe...
Graph neural networks (GNNs) have limited expressive power, failing to
r...
In recent years, algorithms and neural architectures based on the
Weisfe...
Combinatorial optimization is a well-established area in operations rese...
Recently, there has been an increasing interest in (supervised) learning...
This work presents a two-stage neural architecture for learning and refi...
The k-dimensional Weisfeiler-Leman algorithm is a well-known heuristic f...
Graph kernels have become an established and widely-used technique for
s...
In recent years, graph neural networks (GNNs) have emerged as a powerful...
Recently, graph neural networks (GNNs) have revolutionized the field of ...
Recently, graph neural networks (GNNs) have revolutionized the field of ...
Most state-of-the-art graph kernels only take local graph properties int...
Non-linear kernel methods can be approximated by fast linear ones using
...
While state-of-the-art kernels for graphs with discrete labels scale wel...