Graph Neural Networks (GNNs) often suffer from degraded performance when encountering out-of-distribution (OOD) samples, particularly in multi-domain graph scenarios. Existing graph OOD detection methods typically require extensive modifications to data or model architectures, resulting in high computational costs and limited generalization. Moreover, prior approaches largely overlook local structural semantics and community-level patterns, leading to biased representations and suboptimal detection performance. To overcome these limitations, we propose community enhanced graph out-of-distribution detection (CEGOOD), a novel framework that incorporates community structure into GNN-based OOD detection. Specifically, we propose two community-aware view generation strategies: intra-community attribute aggregation (ICAA) to distill fine-grained feature coherence and inter-community edge dropping (ICED) to fortify structural robustness by pruning non-critical cross-community edges. Furthermore, We also design three community-level loss functions (compactness, separability, and balance) to optimize community hierarchical structures and improve community representation. Experimental results on various datasets show that CEGOOD outperforms state-of-the-art baselines by an average of 1.8% AUC, with notable gains of 2.4% on AIDS+DHFR and 2.8% on BBBP+BACE, demonstrating superior adaptability and effectiveness in graph OOD detection tasks.

Generalized federated learning seeks to develop robust models across distributed source domains that generalize well to the unseen target domain. Mainstream methods make strict assumptions about the availability of target domain data, limiting the flexibility and adaptability of real-world applications. In this work, we tackle a real-world challenge that has never been addressed before: federated multi-source domain adaptation for an unseen target domain. We propose federated cross-domain semantic alignment with adversarial feature augmentation, a method that enhances model generalization across domains. Our method operates in the feature space to capture both diversity and invariance between source and target domains through a two-stage local training strategy. In the adversarial training phase, a domain identifier and feature discriminator constrain the generated features to extract target-relevant information. During the contrastive learning stage, a semantic representation alignment loss (SRA) is incorporated to align class prototype distributions between source and target domains, ensuring uniform classification standards. Federated aggregation consolidates model knowledge across clients, facilitating collaborative evolution and rapid adaptation to the unseen target domain. Extensive experimental results on four prevalent datasets demonstrate that our approach outperforms existing benchmarks across different backbones, showcasing its effectiveness in scenarios with data silos.

Graph matching aims to establish node correspondences between graphs, which is a classic combinatorial optimization problem. In recent years, (deep) learning-based methods have emerged as a superior alternative to traditional graph matching solvers. However, these methods typically rely on node-level correspondence labels, which can be prohibitively expensive or unrealistic. Inspired by contrastive learning that is a prevalent paradigm for self-supervised representation learning, we develop a Contrastive Learning Network for Unsupervised Graph Matching (CUGM), which is an end-to-end differentiable pipeline to learn node permutations. Specifically, we propose three-level augmentation including raw image augmentation, graph augmentation and model augmentation for generating diverse enough contrastive views to enrich training instances. Then a contrastive learning network is constructed to capture the higher-order structural information in graphs and learn the final node representations for yielding the affinity matrix to directly solve a linear assignment problem. More importantly, we propose a node-level contrastive loss with false negative cancellation for optimizing the whole network to extract the tailored node feature representations to improve graph matching accuracy. Experimental results on standard graph matching benchmarks demonstrate that our end-to-end unsupervised method achieves the competitive performance compared with state-of-the-art supervised and unsupervised graph matching methods.

Federated unsupervised representation learning aims at leveraging unlabeled data from multiple parties to learn visual representations without compromising the data privacy and tackle the non-IID challenge by aligning diverse representation spaces. However, model heterogeneity and communication overhead will directly impact the convergence rate and model accuracy of federated unsupervised learning. And it is challenging to learn visual features for downstream tasks under the premise of compatibility with heterogeneous models and reducing communication overhead. To address these issues, we propose a novel communication-efficient federated unsupervised representation learning framework based on prototype similarity distillation (FLPD). In this framework, the global model builds the feature representation space based on the global dataset and steers the optimization of the prototype relations of the client models. In addition to employing discriminative self-supervised learning for model training, each client fine-tunes the local representation space with global prototype similarity via knowledge distillation, which facilitates local models to fit both the local data distribution and the global representation space. In order to maintain the compactness of prototypes within the same category and enhance the separability between prototypes of different categories, a prototype-based consistency constraint is introduced to alleviate the conflict between local and global representation space. Experimental results demonstrate that our framework outperforms other alternative approaches in terms of communication efficiency and accuracy in the federated settings with statistical heterogeneity and model heterogeneity.

Graph matching endeavors to find corresponding nodes across two or more graphs, which plays a fundamental role in many vision and pattern matching tasks. However, existing graph matching algorithms often meet abnormal graphs with missing node features and suffer from numerous cluttered outliers in practical applications. To address these, we propose a novel deep graph matching method called Random Deep Graph Matching (RDGM). Different from the deterministic affinity inference in existing deep graph matching methods, RDGM performs message passing in a random manner during model training through randomly masking some available node features in the source or target graph, so that the affinity inference between nodes is insensitive to specific neighborhoods. In addition, a hierarchical attention graph neural network framework is devised in the node embedding process of RDGM, which can obtain more sufficient high-order structural information to reduce the impact of latent noise on affinity learning. Extensive experiments suggest that the proposed RDGM outperforms state-of-the-art graph matching methods, and demonstrates strong robustness and generalization performance.

Federated learning (FL) unites multiple participants to collaboratively learn a global consensus model on the centralized server by aggregating their individual models trained locally on clients. To meet the goal of obtaining an optimal model, sufficient labeled data and myriad communications are required during training. However, the major problems are the limited budget for manually annotating unlabeled instances and the restricted bandwidth of server and clients. This article presents a communication-efficient federated active semi-supervised learning (CEFedASSL) framework that unites active learning (AL) clients and a semi-supervised learning (SSL) client to train models on unlabeled data while achieving communication efficiency. In each AL client, different query strategies are, respectively, applied for the local model to obtain a more robust model and query only the optimal samples which significantly reduces the cost of annotation. Subsequently, these optimal samples are encrypted as input to fine-tune the pretrained model of the SSL client by performing self-training, thereby enhancing the model performance while preserving the privacy of data. Furthermore, we propose an efficient selective aggregation strategy to reduce the communication cost between clients and the server. Empirical experiments on four different learning tasks demonstrate that the proposed CEFedASSL distinctively outperforms the common FL algorithms in terms of both model performance and communication costs.

Recent research has shown that lumbar disease has become common in China. Since the structure of the lumbar spine is extremely complex, a finite element analysis method was used to perform biomechanical simulation and analysis of stress and strain on the L3–L4 lumbar segment to provide both a scientific and theoretical basis for clinical diagnosis and medical research. The MC volume-rendering 3D reconstruction method was the first step to accurately constructing the finite element model of the L3–L4 lumbar sacral segment, which was simulated prior to the addition of the ligaments, fibrous ring, and other major spinal tissue. The finite element model network was classified and the material properties of the corresponding parts were described. According to the normal model, careful simulation and deformation were performed, in addition to intervertebral disc degeneration in various cases. We have provided a detailed and professional analysis of the biomechanical properties, providing a powerful biomechanical basis for the diagnosis of intervertebral disc bulge and degeneration.

In this paper, combined with physiological anatomy knowledge, the complete finite element model of L3–L4 lumbosacral segment of human lumbar was established by using the 3D graphic of human spine L3–L4 segment, which is obtained by image diagnosis technique (CT scan). This model includes the sections of the bones, the intervertebral disc and the anterior ligament, the posterior ligament, the ligamentum flavum, the fibrous ring and other major spine attached soft tissue. Then the finite element model meshing and the material properties of the corresponding part setting were done on the constructed model, and different loads and boundary conditions were imposed to simulate the displacement and stress and strain nephogram of the normal model and intervertebral disc herniation, senile degeneration and other models in different movement states. And the effectiveness of model data is verified by analyzing its biomechanical properties. The biomechanical properties of the spine obtained by the finite element method can be used to provide biomechanical basis for the diagnosis and treatment of intervertebral disc herniation and degeneration.