Principal Neighbourhood Aggregation (PNA) is a general and flexible architecture for graphs combining multiple aggregators with degree-scalers (which generalize the sum aggregator).
Source: Principal Neighbourhood Aggregation for Graph NetsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Computational Efficiency | 1 | 25.00% |
Graph Classification | 1 | 25.00% |
Graph Regression | 1 | 25.00% |
Node Classification | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |