AWhat changed
Introduced graph attention networks and tested transductive and inductive tasks.
Scientific scope
The record is the exact six-author ICLR 2018 paper. It does not absorb graph convolutional networks, later GAT variants, every graph-attention mechanism or claims beyond the four reported benchmarks.
Evidence
The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact six-author ICLR 2018 paper. It does not absorb graph convolutional networks, later GAT variants, every graph-attention mechanism or claims beyond the four reported benchmarks.
Contributors
- Petar Veličković · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Guillem Cucurull · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Arantxa Casanova · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Adriana Romero · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Pietro Liò · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Yoshua Bengio · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
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