pyg-team/pytorch_geometric

Support `AttentionalAggregation` for `HeteroConv`

Open

#7.414 geöffnet am 23. Mai 2023

Auf GitHub ansehen
 (1 Kommentar) (0 Reaktionen) (0 zugewiesene Personen)Python (3.514 Forks)batch import
1 - Priority P1featurehelp wanted

Repository-Metriken

Stars
 (19.985 Stars)
PR-Merge-Metriken
 (Durchschn. Merge 35T 1h) (14 gemergte PRs in 30 T)

Beschreibung

🚀 The feature, motivation and pitch

use pyg == 2.3.0
conv = HeteroConv({
    edge_type: GraphConv(-1, second_channels) for edge_type in metadata[1]
}, aggr='attentional')

In pyg 2.3.0, can not use aggr.AttentionalAggregation to aggregation node feature from different edge type in above code, right ? (may i thought is wrong...), so can you give me some advice on how to integrate node features from different edges in pyg ?

Alternatives

No response

Additional context

No response

Contributor Guide