Graph Federated Learning (GFL) has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information. However, existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization, particularly in non-independent and identically distributed (NON-IID) scenarios where balancing global structural understanding and local node-level detail remains a challenge. To this end, this paper proposes a novel framework called GFL-SAR (Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement), which enhances the representation learning capability of graph data through a dual-branch collaborative design. Specifically, we propose the Structural Insight Amplifier (SIA), which utilizes an improved Graph Convolutional Network (GCN) to strengthen structural awareness and improve modeling of topological patterns. In parallel, we propose the Attentive Relational Refiner (ARR), which employs an enhanced Graph Attention Network (GAT) to perform fine-grained modeling of node relationships and neighborhood features, thereby improving the expressiveness of local interactions and preserving critical contextual information. GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization, thereby addressing existing GFL limitations in structural modeling and feature representation. Experiments on standard benchmark datasets including Cora, Citeseer, Polblogs, and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy, convergence speed, and robustness compared to existing methods, confirming its effectiveness and generalizability in GFL tasks.

Federated learning (FL) enables collaborative model training without sharing raw data. However, in real-world applications, clients often exhibit statistical heterogeneity, missing classes, and long-tailed distributions, which can substantially degrade the generalization performance of conventional parameter aggregation and some personalization approaches. Moreover, distillation or alignment-based methods may suffer from unstable supervision and difficult optimization under highly heterogeneous settings. To this end, this paper proposes a novel method called FKD-RTM (Heterogeneous Federated Knowledge Distillation Based on Residual-Enhanced Tree-to-MLP Knowledge Transfer). The key idea is to decouple local teaching from globally aggregatable student learning: we introduce a Gradient Boosting Decision Tree (GBDT) as a local teacher at each client, providing more reliable soft supervision based on shared feature representations for a Multi-Layer Perceptron (MLP) student that supports efficient global aggregation and adaptation. To further correct the prediction bias left after first-stage distillation, we introduce a residual enhancement mechanism. It learns complementary knowledge in the pre-normalization score domain and enables second-stage corrective learning. In addition, FKD-RTM performs partial parameter fine-tuning of the feature extractor and student model for personalized local adaptation. Personalized updates are excluded from global aggregation to avoid contaminating the global model. Experiments on multiple datasets, including CIFAR-100, demonstrate that the proposed FKD-RTM method consistently improves accuracy and generalization under diverse complex data settings and achieves a better trade-off between global and personalized performance.

Federated Graph Learning (FGL) enables model training without requiring each client to share local graph data, effectively breaking data silos by aggregating the training parameters from each terminal while safeguarding data privacy. Traditional FGL relies on a centralized server for model aggregation; however, this central server presents challenges such as a single point of failure and high communication overhead. Additionally, efficiently training a robust personalized local model for each client remains a significant objective in federated graph learning. To address these issues, we propose a decentralized Federated Graph Learning framework with efficient communication, termed Decentralized Federated Graph Learning via Surrogate Model (SD_FGL). In SD_FGL, each client is required to maintain two models: a private model and a surrogate model. The surrogate model is publicly shared and can exchange and update information directly with any client, eliminating the need for a central server and reducing communication overhead. The private model is independently trained by each client, allowing it to calculate similarity with other clients based on local data as well as information shared through the surrogate model. This enables the private model to better adjust its training strategy and selectively update its parameters. Additionally, local differential privacy is incorporated into the surrogate model training process to enhance privacy protection. Testing on three real-world graph datasets demonstrates that the proposed framework improves accuracy while achieving decentralized Federated Graph Learning with lower communication overhead and stronger privacy safeguards.

An optimization algorithm for federated learning, equipped with an incentive mechanism, is introduced to tackle the challenges of excessive iterations, prolonged training durations, and suboptimal efficiency encountered during model training within the federated learning framework. Initially, the algorithm establishes reputation values that are tied to both time and model loss metrics. This foundation enables the creation of incentive mechanisms aimed at rewarding honest nodes while penalizing malicious ones. Subsequently, a bidirectional selection mechanism anchored in blockchain technology is developed, allowing smart contracts to enroll nodes with high reputations in training sessions, thus filtering out malicious clients and enhancing local training efficiency. Furthermore, the integration of the Earth Mover's Distance (EMD) mechanism serves to lessen the impact of non-IID (non-Independent and Identically Distributed) data on the global model, leading to a reduction in the frequency of model training cycles and an improvement in model accuracy. Experimental results confirm that this approach maintains high model accuracy in non-IID data settings, outperforming traditional federated learning algorithms.