Kipf and Welling: graph convolutional networks for semi-supervised classification

What changed

Derived a scalable first-order graph convolutional propagation rule and evaluated node classification on citation and knowledge-graph data.

Scientific scope

The record is the exact two-author ICLR 2017 paper, posted in 2016. Its reported benchmark gains do not establish universal superiority, and earlier graph neural networks, spectral convolutions and later message-passing variants remain separate.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact two-author ICLR 2017 paper, posted in 2016. Its reported benchmark gains do not establish universal superiority, and earlier graph neural networks, spectral convolutions and later message-passing variants remain separate.

Contributors

• Thomas N. Kipf · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Max Welling · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Graph convolutional networks author manuscript

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction