What is recorded here?
Introduced graph attention networks using masked self-attention over graph neighborhoods and evaluated the architecture on transductive citation-network and inductive protein-interaction benchmarks.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
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.
Read the original work
- ICLR proceedings paper for Graph Attention Networks
- Cambridge repository deposit for Graph Attention Networks
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Petar Veličković; Guillem Cucurull; Arantxa Casanova; Adriana Romero; Pietro Liò; Yoshua Bengio
The named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.
Research locations and affiliations
Documented mapping · Included in country comparison
Documented countries / regions: Canada, United Kingdom
Documented research locations or paper affiliations for this contribution. Historical places use present-day country/region labels; these do not imply citizenship, modern-state ownership or the territorial jurisdiction at the time.
English catalogue narrative
Veličković and colleagues: graph attention networks
Introduced graph attention networks using masked self-attention over graph neighborhoods and evaluated the architecture on transductive citation-network and inductive protein-interaction benchmarks.
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.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Petar Veličković; Guillem Cucurull; Arantxa Casanova; Adriana Romero; Pietro Liò; Yoshua Bengio
The named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.