SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.11010 · ICLR · 2022

Agent-based Graph Neural Networks

Roger Wattenhofer, Karolis Martinkus, Pál Papp, Benedikt Schesch

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
karolismart/agentnet canonical 4 of 5
nokpil/AgentNet reimplementation 0 of 2
FunctionStatusWhere it lives
create_batch_info Ran karolismart/agentnet/smp_models/utils/misc.py
code served (permissive licence) · get_code("29a568f05ffbc54c")
eval Ran karolismart/agentnet/ogb_mol.py
code served (permissive licence) · get_code("037633469c40345a")
kaiming_init_with_gain Ran karolismart/agentnet/smp_models/utils/layers.py
code served (permissive licence) · get_code("57be240b8826b674")
pooling Ran karolismart/agentnet/smp_models/utils/layers.py
code served (permissive licence) · get_code("7a693a902861da98")
map_x_to_u Not yet run karolismart/agentnet/smp_models/utils/misc.py
code served (permissive licence) · get_code("28ea7c6cdbeb3875")
test Not yet run nokpil/AgentNet/train/AOUP_train.py
code served (permissive licence) · get_code("8a97cf5a15c22a81")
train Not yet run nokpil/AgentNet/train/AOUP_train.py
code served (permissive licence) · get_code("82d777283362729c")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present a novel graph neural network we call AgentNet, which is designed specifically for graph-level tasks. AgentNet is inspired by sublinear algorithms, featuring a computational complexity that is independent of the graph size. The architecture of AgentNet differs fundamentally from the architectures of traditional graph neural networks. In AgentNet, some trained neural agents intelligently walk the graph, and then collectively decide on the output. We provide an extensive theoretical analysis of AgentNet: We show that the agents can learn to systematically explore their neighborhood and that AgentNet can distinguish some structures that are even indistinguishable by 2-WL. Moreover, AgentNet is able to separate any two graphs which are sufficiently different in terms of subgraphs. We confirm these theoretical results with synthetic experiments on hard-to-distinguish graphs and real-world graph classification tasks. In both cases, we compare favorably not only to standard GNNs but also to computationally more expensive GNN extensions.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2206.11010")
get_code_for_paper("2206.11010")
have("2206.11010")

Connect an agent — have() is free.