pyg-team/pytorch_geometric
GitHub ã§èŠãSupport `AttentionalAggregation` for `HeteroConv`
Open
#7,414 opened on 2023幎5æ23æ¥
1 - Priority P1featurehelp wanted
Repository metrics
- Stars
- Â (19,985 stars)
- PR merge metrics
-  (å¹³åããŒãž 35d 1h) (30d ã§ 14 merged PRs)
説æ
ð 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