Our great sponsors
-
pna
Implementation of Principal Neighbourhood Aggregation for Graph Neural Networks in PyTorch, DGL and PyTorch Geometric
-
gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
In this regard, I came across the Principal Neighborhood Aggregation paper which aggregates information from neighbors based on different aggregators (1st, 2nd, and higher-order moments like mean, std, kurtosis, etc.). Additionally, the authors also introduce a scaler based on the degree of the node. It basically amplifies or attenuates the incoming information from the neighboring nodes. The code implementation is available here. Reach out to me if you want to discuss more!