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.

Multiparty learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multiparty learning approaches are confronted with obstacles, such as system heterogeneity, statistical heterogeneity, and incentive design. Determining how to deal with these challenges and further improve the efficiency and performance of multiparty learning has become an urgent problem to be solved. In this article, we propose a novel contrastive multiparty learning framework for knowledge refinement and sharing with an accountable incentive mechanism. Since the existing parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication and analogize multiparty learning as a many-to-one knowledge-sharing problem. The approach is capable of integrating the acquired explicit knowledge of each client in a transparent manner without privacy disclosure, and it reduces the dependence on data distribution and communication environments. The proposed scheme achieves significant improvement in model performance in a variety of scenarios, as we demonstrated through experiments on several real-world datasets.

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.

The performance of machine learning algorithms heavily relies on the availability of a large amount of training data. However, in reality, data usually reside in distributed parties such as different institutions and may not be directly gathered and integrated due to various data policy constraints. As a result, some parties may suffer from insufficient data available for training machine learning models. In this article, we propose a multiparty dual learning (MPDL) framework to alleviate the problem of limited data with poor quality in an isolated party. Since the knowledge-sharing processes for multiple parties always emerge in dual forms, we show that dual learning is naturally suitable to handle the challenge of missing data, and explicitly exploits the probabilistic correlation and structural relationship between dual tasks to regularize the training process. We introduce a feature-oriented differential privacy with mathematical proof, in order to avoid possible privacy leakage of raw features in the dual inference process. The approach requires minimal modifications to the existing multiparty learning structure, and each party can build flexible and powerful models separately, whose accuracy is no less than nondistributed self-learning approaches. The MPDL framework achieves significant improvement compared with state-of-the-art multiparty learning methods, as we demonstrated through simulations on real-world datasets.

Graph classification aims to predict the label associated with a graph and is an important graph analytic task with widespread applications. Recently, graph neural networks (GNNs) have achieved state-of-the-art results on purely supervised graph classification by virtue of the powerful representation ability of neural networks. However, almost all of them ignore the fact that graph classification usually lacks reasonably sufficient labeled data in practical scenarios due to the inherent labeling difficulty caused by the high complexity of graph data. The existing semisupervised GNNs typically focus on the task of node classification and are incapable to deal with graph classification. To tackle the challenging but practically useful scenario, we propose a novel and general semisupervised GNN framework for graph classification, which takes full advantage of a slight amount of labeled graphs and abundant unlabeled graph data. In our framework, we train two GNNs as complementary views for collaboratively learning high-quality classifiers using both labeled and unlabeled graphs. To further exploit the view itself, we constantly select pseudo-labeled graph examples with high confidence from its own view for enlarging the labeled graph dataset and enhancing predictions on graphs. Furthermore, the proposed framework is investigated on two specific implementation regimes with a few labeled graphs and the extremely few labeled graphs, respectively. Extensive experimental results demonstrate the effectiveness of our proposed semisupervised GNN framework for graph classification on several benchmark datasets.

Graph Neural Network (GNN) is capable of applying deep neural networks to graph domains. Recently, Message Passing Neural Networks (MPNNs) have been proposed to generalize several existing graph neural networks into a unified framework. For graph representation learning, MPNNs first generate discriminative node representations using the message passing function and then read from the node representation space to generate a graph representation using the readout function. In this paper, we analyze the representation capacity of the MPNNs for aggregating graph information and observe that the existing approaches ignore the self-loop for graph representation learning, leading to limited representation capacity. To alleviate this issue, we introduce a simple yet effective propagation enhanced extension, Self-Connected Neural Message Passing (SC-NMP), which aggregates the node representations of the current step and the graph representation of the previous step. To further improve the information flow, we also propose a Densely Self-Connected Neural Message Passing (DSC-NMP) that connects each layer to every other layer in a feed-forward fashion. Both proposed architectures are applied at each layer and the graph representation can then be used as input into all subsequent layers. Remarkably, combining these two architectures with existing GNN variants can improve these models’ performance for graph representation learning. Extensive experiments on various benchmark datasets strongly demonstrate the effectiveness, leading to superior performance for graph classification and regression tasks.

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.

Graph classification aims to predict the class labels of graphs and has a wide range of applications in many real-world domains. However, most of existing graph neural networks for graph classification tasks use 90$\%$of labeled graphs for training and the remaining 10$\%$for testing, which obviously struggle in solving the problem of the scarcity of labeled graphs in real-world graph classification scenarios. And it is arduous to label a large number of graph examples for training because of the difficulty and resource consumption in the tagging process. Motivated by this, we propose a novel active and semi-supervised graph neural network (ASGNN) framework, which endeavors to complete graph classification tasks with a small number of labeled graph examples and available unlabeled graph examples. In our framework, active learning selects high-uncertain and representative graph examples from the test set and add them to the training set after annotation. Semi-supervised learning is utilized to select the high-confidence unlabeled graph examples containing structural information from the test set, and add them to the training set after pseudo labeling. To improve the generalization performance of the graph classification model, multiple GNNs are trained collaboratively for promoting the expressiveness of each other and increasing the reliability of graph classification results. Overall, the ASGNN framework takes fully use of unlabeled graph examples to reinforce graph classification effectively, and can be applied to any existing supervised graph neural networks for graph classification. Experimental results on benchmark graph datasets demonstrate that the proposed framework yields competitive performance on graph classification tasks with only a small number of labeled graph examples.

Detecting anomalies in videos is a fundamental issue in public security. The majority of existing deep learning methods often perform anomaly detection based on the behavior or the trajectory of a single target. However, due to the overlaps of the crowd and the low-resolution of monitoring images, the segmentation of population is hard to implement and the features cannot be learned thoroughly, which make the methods be easily disturbed by visual elements and thus may lead to false detection sometimes. To tackle these problems, we propose the influence-aware attention to learn the representative attributes of the whole crowd. Walking pedestrians can be divided into numbers of flows, and in this paper, we aim to measure the consistency of movement patterns in the same stream and the interactions between different streams. Meanwhile, great importance is given to the relation between pedestrians and the circumstance for certain anomalies occur as a result of environmental issues. Specifically, the influence-aware attention module is composed of the motion attention and the location attention, which is designed to quantify the relations in the scene from spatial and temporal aspects. For the lack of abnormal samples, we utilize a dual generator-based framework to learn interactions among normal scenes. Experimental results on six benchmarks verify the effectiveness and robustness of our proposed method.

Representing nodes in a network as low-dimensional dense vectors can facilitate the analysis of complex networks, which is a challenging task and has attracted increasing attention. However, in the real world, networks are changing over time, such as cooperation in citation networks and communication in email networks. Most of the recent embedding methods only focus on static networks. Thus they ignore the critical temporal information, which serves as a supplement to structure information and has been proved to improve the quality of node embedding. In this work, we propose an unsupervised deep learning model called DTINE, which explores temporal information for further enhancing the robustness of node representations in dynamic networks. To preserve network topology, we pertinently design a temporal weight and sampling strategy to extract features from the neighborhoods. An attention mechanism will be applied on the recurrent neural network to measure the contributions of historical information and capture the evolution of the networks. Experimental results on four real-world networks demonstrate that the proposed method achieves better performance than state-of-the-art methods.

Network embedding has been widely used to solve the network analytics problem. Existing methods mainly focus on networks with single-layered homogeneous or heterogeneous networks. However, many real-world complex systems can be naturally represented by multilayer networks, which is another term of heterogeneous networks with multiple edge/relation types. The problem of how to capture and utilize rich interaction information of multi-type relations causes a major challenge of multilayer network embedding. To address this problem, we propose a fast and scalable multilayer network embedding model, called HMNE, to efficiently preserve and learn information of multi-type relations into a unified embedding space. We develop a heuristic 3D interactive walk technique dedicated for multilayer networks, which can leverage rich interactions among distinct layers and effectively capture important information contained in the layered structure. We evaluate our proposed model HMNE on two downstream analytic applications: node classification and link prediction. Experimental results on seven social and biological multilayer network datasets demonstrate that the proposed model outperforms existing competitive baselines with reduced time and memory occupations.

Face is one of the most attractive sensitive information in visual shared data. It is an urgent task to design an effective face deidentification method to achieve a balance between facial privacy protection and data utilities when sharing data. Most of the previous methods for face deidentification rely on attribute supervision to preserve a certain kind of identity-independent utility but lose the other identity-independent data utilities. In this article, we mainly propose a novel disentangled representation learning architecture for multiple attributes preserving face deidentification called replacing and restoring variational autoencoders (R2VAEs). The R2VAEs disentangle the identity-related factors and the identity-independent factors so that the identity-related information can be obfuscated, while they do not change the identity-independent attribute information. Moreover, to improve the details of the facial region and make the deidentified face blends into the image scene seamlessly, the image inpainting network is employed to fill in the original facial region by using the deidentified face asa priori. Experimental results demonstrate that the proposed method effectively deidentifies face while maximizing the preservation of the identity-independent information, which ensures the semantic integrity and visual quality of shared images.

This article proposes a novel and computationally efficient explicit intertask information transfer strategy between optimization tasks by aligning the subspaces. In evolutionary multitasking, the tasks might have biases embedded in function landscapes and decision spaces, which often causes the threat of predominantly negative transfer. However, the complementary information among different tasks can give an enhanced performance of solving complicated problems when properly harnessed. In this article, we distill this insight by introducing an intertask knowledge transfer strategy implemented in the low-dimension subspaces via a learnable alignment matrix. Specifically, to unveil the significant features of the function landscapes, the task-specific low-dimension subspaces is established based on the distribution information of subpopulations possessed by tasks, respectively. Next, the alignment matrix between pairwise subspaces is learned by minimizing the discrepancies of the subspaces. Given the aligned subspaces by applying the alignment matrix to subspaces' base vectors, the individuals from different tasks are then projected into aligned subspaces and reproduce therein. Moreover, since this method only considers the leading eigenvectors, it turns out to be intrinsically regularized and noise-insensitive. Comprehensive experiments are conducted on the synthetic and practical benchmark problems so as to assess the efficacy of the proposed method. According to the experimental results, the proposed method exhibits a superior performance compared with existing evolutionary multitask optimization algorithms.

With the prevalence of the Internet, online reviews have become a valuable information resource for people. However, the authenticity of online reviews remains a concern, and deceptive reviews have become one of the most urgent network security problems to be solved. Review spams will mislead users into making suboptimal choices and inflict their trust in online reviews. Most existing research manually extracted features and labeled training samples, which are usually complicated and time-consuming. This paper focuses primarily on a neglected emerging domain - movie review, and develops a novel unsupervised spam detection model with an attention mechanism. By extracting the statistical features of reviews, it is revealed that users will express their sentiments on different aspects of movies in reviews. An attention mechanism is introduced in the review embedding, and the conditional generative adversarial network is exploited to learn users’ review style for different genres of movies. The proposed model is evaluated on movie reviews crawled from Douban, a Chinese online community where people could express their feelings about movies. The experimental results demonstrate the superior performance of the proposed approach.

Domain adaptation aims at learning from the la-beled source domain to build an accurate classifier for a related but different target domain. Existing methods attempt to reduce domain discrepancy explicitly by means of statistical properties yet ignore the inherent differences among samples. In this paper, we present a novel solution for domain adaptation based on collaborative representation, named Discrepancy-Aware Collaborative Representation (DACR). Inspired by the success of nearest regularization, DACR develops a novel indicator to measure the discrepancy among every source sample and target domain. Then the indicator is employed in sparse regularization thus ensure that samples with small discrepancy have larger weights in the learned representation. Extensive experiments verify that DACR is able to achieve comparable performance with existing methods while significantly reducing computing complexity.