Research breakthrough · curated entry
Graph convolutional networks go mainstream
Semi-Supervised Classification with Graph Convolutional Networks
- Date
- September 9, 2016
- Category
- Research breakthrough
- Organization / Model
- University of Amsterdam
- Evidence
- 1 source · 1 evidence family
Kipf and Welling made a first-order approximation of spectral graph convolution, yielding a simple layer-wise propagation that did semi-supervised node classification on citation networks. GCNs let neural networks train directly on graph-structured data and became a standard component in drug discovery, recommendation, risk control and knowledge graphs.
Curator's note: Cross-checked against the arXiv preprint; the paper was published at ICLR in 2017.
Curated sources · 1
-
Original paper · arXiv2016-09-09
Semi-Supervised Classification with Graph Convolutional Networks
arxiv.org
Cite this page
This page is a curated static snapshot and can be cited directly. Preferred format GB/T 7714—2025 (electronic resource [EB/OL]); the other 5 styles open below, together with the machine-readable files.
GB/T 7714—2025 (electronic resource [EB/OL])
AI 纪年. 图卷积网络 GCN 提出，图神经网络进入主流[EB/OL]. (2016-09-09)[2026-11-03]. https://aihist.net/e/gcn-2016.html.
APA 7 · American Psychological Association
AI 纪年. (2016, September 9). 图卷积网络 GCN 提出，图神经网络进入主流 [Web page]. https://aihist.net/e/gcn-2016.html
MLA 9 · Modern Language Association
"图卷积网络 GCN 提出，图神经网络进入主流." AI 纪年, 9 Sept. 2016, aihist.net/e/gcn-2016.html. Accessed 3 Nov. 2026.
Chicago 17 · notes-bibliography
AI 纪年. "图卷积网络 GCN 提出，图神经网络进入主流." Published Sept. 9, 2016. Accessed Nov. 3, 2026. https://aihist.net/e/gcn-2016.html.
IEEE · citation-reference list
"图卷积网络 GCN 提出，图神经网络进入主流," AI 纪年, 9 Sept. 2016. [Online]. Available: https://aihist.net/e/gcn-2016.html. [Accessed: 3 Nov. 2026].
ACM · author-date variant
AI 纪年. September 9, 2016. 图卷积网络 GCN 提出，图神经网络进入主流. Retrieved November 3, 2026 from https://aihist.net/e/gcn-2016.html.
All six styles come from one template and can be compared word for word. [引用日期], Accessed, urldate and Y2 all carry this page's build date, 2026-11-03 — a static page is an immutable snapshot, so substitute the date you actually consulted it. The address in every style is the archive's canonical page: this English page translates the same snapshot, and the work keeps its name, so one record cites both. For one-click copying use the same entry in the timeline, which takes the day you opened it. Expand the other styles before printing.