AI Paper Atlas

Research map / Graph learning / GNN architectures

Beyond GNNs: An Efficient Architecture for Graph Problems

Pranjal Awasthi, Abhimanyu Das, Sreenivas Gollapudi

AAAI 2022 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 5 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use GNN+ instead of message-passing GNNmpGraph problem predictors · Shortest Pathstest MSE: 0.975 ± 0.031 -> 0.849 ± 0.022Improved
Use GNN+ instead of message-passing GNNmpGraph problem predictors · Effective Resistancetest MSE: 0.397 ± 0.025 -> 0.187 ± 0.008Improved
Use GNN+ instead of message-passing GNNmpGraph problem predictors · Affinitytest MSE: 0.0025 ± 0.00017 -> 0.0018 ± 1.8e−05Improved
Use GNN+ instead of message-passing GNNmpGraph problem predictors · MSTtest MSE: 1011.39 ± 106.94 -> 733.901 ± 30.97Improved
Use GNN+ instead of message-passing GNNmpGraph problem predictors · MINCUTtest MSE: 0.963 ± 0.110 -> 0.694 ± 0.07Improved
Use GNN+ instead of message-passing GNNmpGraph classification · IMDB-BINARYtest accuracy: 0.742 ± 0.09 -> 0.769 ± 0.02Improved
Use GNN+ instead of message-passing GNNmpGraph classification · IMDB-MULTItest accuracy: 0.523 ± 0.06 -> 0.527 ± 0.04No clear effect
Use GNN+ instead of message-passing GNNmpGraph classification · COLLABtest accuracy: 0.802 ± 0.02 -> 0.816 ± 0.004Improved
Use GNN+ instead of message-passing GNNmpGraph classification · PROTEINStest accuracy: 0.760 ± 0.008 -> 0.765 ± 0.015No clear effect
Use GNN+ instead of message-passing GNNmpGraph classification · NCI1test accuracy: 0.849 ± 0.004 -> 0.851 ± 0.003No clear effect
Use GNN+ instead of message-passing GNNmpGraph classification · PTCtest accuracy: 0.686 ± 0.02 -> 0.708 ± 0.018Improved
Use GNN+ instead of message-passing GNNmpGraph classification · MUTAGtest accuracy: 0.876 ± 0.016 -> 0.898 ± 0.012Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy