Conference item
GNNRank: Learning global rankings from pairwise comparisons via directed graph neural networks
- Abstract:
-
Recovering global rankings from pairwise comparisons has wide applications from time synchronization to sports team ranking. Pairwise comparisons corresponding to matches in a competition can be construed as edges in a directed graph (digraph), whose nodes represent e.g. competitors with an unknown rank. In this paper, we introduce neural networks into the ranking recovery problem by proposing the so-called GNNRank, a trainable GNN-based framework with digraph embedding. Moreover, new objecti...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Accepted manuscript, pdf, 654.9KB)
-
- Publication website:
- https://proceedings.mlr.press/v162/he22b.html
Authors
Bibliographic Details
- Publisher:
- Proceedings of Machine Learning Research Publisher's website
- Journal:
- Proceedings of the 39th International Conference on Machine Learning (PMLR22) Journal website
- Volume:
- 162
- Pages:
- 8581-8612
- Publication date:
- 2022-10-02
- Acceptance date:
- 2022-07-20
- Event title:
- 39th International Conference on Machine Learning (ICML 2022)
- Event location:
- Baltimore, MD, USA
- Event start date:
- 2022-07-17
- Event end date:
- 2022-07-21
- ISSN:
-
2640-3498
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1281690
- Local pid:
- pubs:1281690
- Deposit date:
- 2022-10-07
Terms of use
- Copyright holder:
- He et al.
- Copyright date:
- 2022
- Rights statement:
- Copyright 2022 by the author(s).
- Notes:
-
This conference paper was presented at the 39th International Conference on Machine Learning (PMLR22). This is the accepted manuscript version of the article.
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record