Hamilton, Ying and Leskovec: inductive representation learning on large graphs

What changed

Introduced feature-based neighborhood sampling and aggregation for inductive node embeddings.

Scientific scope

The record is the exact three-author 2017 NeurIPS paper. It does not absorb transductive graph convolution, later sampling variants, graph transformers or claims beyond the reported datasets and tasks.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact three-author 2017 NeurIPS paper. It does not absorb transductive graph convolution, later sampling variants, graph transformers or claims beyond the reported datasets and tasks.

Contributors

• William L. Hamilton · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Rex Ying · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Jure Leskovec · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Hamilton, Ying and Leskovec: inductive representation learning on large graphs

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