We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We introduce Automorphism-based graph neural networks (Autobahn), a new family of graph neural networks. In an Autobahn, we decompose the graph into a collection of subgraphs and apply local convolutions that are equivariant to each subgraph's automorphism group. Specific choices of local neighborhoods and subgraphs recover existing architectures such as message passing neural networks. Our formalism also encompasses novel architectures: as an example, we introduce a graph neural network that decomposes the graph into paths and cycles. The resulting convolutions reflect the natural way that parts of the graph can transform, preserving the intuitive meaning of convolution without sacrificing global permutation equivariance. We validate our approach by applying Autobahn to molecular graphs, where it achieves results competitive with state-of-the-art message passing algorithms.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.01710")
get_code_for_paper("2103.01710")
have("2103.01710")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.01710.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.01710)
Connect an agent — have() is free.