O-pFGL achieves one-shot personalized federated graph learning by aggregating class-wise feature statistics into a surrogate graph and combining global distillation with local fine-tuning, outperforming baselines on 14 graph datasets.
Decoupled Subgraph Federated Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We address the challenge of federated learning on graph-structured data distributed across multiple clients. Specifically, we focus on the prevalent scenario of interconnected subgraphs, where interconnections between different clients play a critical role. We present a novel framework for this scenario, named FedStruct, that harnesses deep structural dependencies. To uphold privacy, unlike existing methods, FedStruct eliminates the necessity of sharing or generating sensitive node features or embeddings among clients. Instead, it leverages explicit global graph structure information to capture inter-node dependencies. We validate the effectiveness of FedStruct through experimental results conducted on six datasets for semi-supervised node classification, showcasing performance close to the centralized approach across various scenarios, including different data partitioning methods, varying levels of label availability, and number of clients.
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Personalized One-shot Federated Graph Learning for Heterogeneous Clients
O-pFGL achieves one-shot personalized federated graph learning by aggregating class-wise feature statistics into a surrogate graph and combining global distillation with local fine-tuning, outperforming baselines on 14 graph datasets.