pyg-team/pytorch_geometric

Weighted aggregations `torch_geometric.nn.aggr.Aggregation`

Open

#6867 aperta il 7 mar 2023

Vedi su GitHub
 (10 commenti) (0 reazioni) (0 assegnatari)Python (3514 fork)batch import
1 - Priority P1featurehelp wantednn

Metriche repository

Star
 (19.985 star)
Metriche merge PR
 (Merge medio 35g 1h) (14 PR mergiate in 30 g)

Descrizione

🚀 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

Guida contributor