pyg-team/pytorch_geometric
Voir sur GitHubWeighted aggregations `torch_geometric.nn.aggr.Aggregation`
Open
#6 867 ouverte le 7 mars 2023
1 - Priority P1featurehelp wantednn
Métriques du dépôt
- Stars
- (19 985 stars)
- Métriques de merge PR
- (Merge moyen 35j 1h) (14 PRs mergées en 30 j)
Description
🚀 The feature, motivation and pitch
The current API of torch_geometric.nn.aggr.Aggregation seems to be unnecessarily limited with respect to edge weights. At least some architectures introduce edge weights, with GCN being the most prominent one. For mean aggregation, it is simple to work around this with a custom message passing / convolution that multiplies features with edge weights. However, for most other weighted aggregations (e.g. median, quantiles, standard deviation, ...) it is not.
Alternatives
Add edge weights to aggregations API
Additional context
No response