2025
FedIGL: Federated Invariant Graph Learning for Non-IID Graphs
This work proposes a FedIGL framework based on invariant learning, which effectively disrupts spurious correlations and further mines the invariant factors across different distributions, and proposes a novel Bi-Gradient Regularization strategy that introduces gradient constraints to guide the model in identifying clie...
Lingren Wang, Wenxuan Tu, Jiaxin Wang et al.
· Neural Information Processin... · 2 citations