Graph-level clustering (GLC), which aims to group entire graphs according to their structural and attribute-based similarities, represents a fundamental yet challenging task in various practical applications. Existing GLC methods primarily fall into two main paradigms: 1) deep graph clustering approaches based on Graph Neural Networks (GNNs), and 2) kernel-based methods that utilize predefined kernels to perform fine-grained structural comparison for clustering. However, GNN-based methods typically learn graph-level representations by aggregating node embeddings through pooling operations, which inevitably leads to substantial information loss and suboptimal clustering performance. In contrast, kernel methods, despite their theoretical expressiveness, suffer from prohibitive computational costs that hinder their scalability to large-scale settings. To solve these issues, we propose a novel graph learning framework named Anchor-driven Nyström for Deep Graph-Level Clustering (ANGC), which computes graph similarity via kernel methods while retaining the scalability of GNNs. Specifically, we first employ GNNs to encode individual graphs into sets of node embeddings. Rather than relying on pooling operations, we compute graph similarities in a kernel space constructed from these embeddings. To enhance both scalability and representational power, we introduce learnable graph Nyström anchors, which support end-to-end optimization and significantly accelerate kernel computations. To further improve the discriminative capability of these anchors, we propose the concept of anchor response discrepancy, that is, the variation in a given anchor’s responses across different samples. By maximizing this discrepancy, the anchors are encouraged to strengthen inter-graph distinctions for better clustering. Extensive experiments demonstrate the effectiveness and superiority of ANGC over existing state-of-the-art methods.

Medical imaging is foundational to modern diagnostics, with computed tomography (CT) and magnetic resonance imaging (MRI) as standard modalities. However, single-modality imaging lacks the capability to comprehensively represent complex anatomical structures and pathological variations. Recently, multi-source medical image fusion has shown transformative potential in computer-aided diagnosis but faces challenges in integrating heterogeneous multimodal data and fully exploiting its informational richness. To address these challenges, we propose a Federated Dynamic Window Selection Aggregation Method (DWS-FedSeg) to optimize task-specific information while reducing inter-site communication overhead. A frequency-adaptive selection mechanism dynamically prioritizes task-relevant frequency components, improving global model aggregation fidelity. Specifically, a learnable Discrete Cosine Transform (LDCT) transforms spatial features into frequency domain representations, while frequency-adaptive windows isolate high-salience features. This approach enhances data utilization and minimizes communication costs. Extensive experiments on six datasets validate the superior performance and efficiency of the proposed method.

Federated Learning (FL) has become an effective method for improving medical image segmentation performance under privacy protection. However, the heterogeneity between medical image modalities, including background differences, variations in detail presentation, and resolution discrepancies, presents challenges for enhancing the accuracy of multi-modal joint segmentation. These differences between modalities may hinder the effective fusion of information from each modality, thus affecting the accuracy and consistency of segmentation results. To address this issue, this study proposes a novel federated medical image segmentation method, DCT-GMM-FedSeg. This method combines Discrete Cosine Transform (DCT) and Gaussian Mixture Model (GMM) to improve segmentation accuracy while preserving privacy. Specifically, DCT is used to extract background frequency information, which is globally unified and integrated with the original background to alleviate modality-related background differences. GMM is used to model image detail features, and by sharing the distribution information of these detailed regions, it reduces the differences between modalities. In this way, federated learning can extract complementary information from different modalities, enhancing global generalization ability and fully leveraging the advantages of multi-modal segmentation. Throughout the process, key image information is retained locally to prevent privacy leakage. Experimental results demonstrate that DCT-GMM-FedSeg significantly improves performance in four heterogeneous medical image segmentation tasks, particularly exhibiting excellent robustness and generalization ability in Non-IID data environments.

Graph-level clustering remains a pivotal yet formidable challenge in graph learning. Recently, the integration of deep learning with representation learning has demonstrated notable advancements, yielding performance enhancements to a certain degree. However, existing methods suffer from at least one of the following issues: 1) the original graph structure has noise, and 2) during feature propagation and pooling processes, noise is gradually aggregated into the graph-level embeddings through information propagation. Consequently, these two limitations mask clustering-friendly information, leading to suboptimal graph-level clustering performance. To this end, we propose a novel Dual Boost-Driven Graph-Level Clustering Network (DBGCN) to alternately promote graph-level clustering and filtering out interference information in a unified framework. Specifically, in the pooling step, we evaluate the contribution of features at the global and optimize them using a learnable transformation matrix to obtain high-quality graph-level representation, such that the model’s reasoning capability can be improved. Moreover, to enable reliable graph-level clustering, we first identify and suppress information detrimental to clustering by evaluating similarities between graph-level representations, providing more accurate guidance for multi-view fusion. Extensive experiments demonstrated that DBGCN outperforms the state-of-the-art graph-level clustering methods on six benchmark datasets.

Federated Graph Learning (FGL) effectively facilitates cross-domain graph model training by enabling decentralized learning across multiple domains, while ensuring data privacy through local data storage and communication of model updates instead of raw data. Existing approaches usually assume shared generic knowledge (e.g., prototypes, spectral features) via aggregating local structures statistically to alleviate structural heterogeneity. However, imposing overly strict assumptions about the presumed correlation between structural features and the global objective often fails in generalizing to local tasks, leading to suboptimal performance. To tackle this issue, we propose a **Fed**erated **I**nvariant **G**raph **L**earning (**FedIGL**) framework based on invariant learning, which effectively disrupts spurious correlations and further mines the invariant factors across different distributions. Specifically, a server-side global model is trained to capture client-agnostic subgraph patterns shared across clients, whereas client-side models specialize in client-specific subgraph patterns. Subsequently, without compromising privacy, we propose a novel Bi-Gradient Regularization strategy that introduces gradient constraints to guide the model in identifying client-agnostic and client-specific subgraph patterns for better graph representations. Extensive experiments on graph-level clustering and classification tasks demonstrate the superiority of FedIGL against its competitors.