Graph domain adaptation has gained significant attention in label-scarce scenarios across different graph domains. Traditional approaches to graph domain adaptation primarily focus on transforming node attributes over raw graph structures and aligning the distributions of the transformed node features across networks. However, these methods often struggle with the underlying structural heterogeneity between distinct graph domains, which leads to suboptimal distribution alignment. To address this limitation, we propose Structure-Attribute Transformation with Markov Chain (SATMC), a novel framework that sequentially aligns distributions across networks via both graph structure and attribute transformations. To mitigate the negative influence of domain-private information and further enhance the model's generalization, SATMC introduces a private domain information reduction mechanism and an empirical Wasserstein distance. Theoretical proofs suggest that SATMC can achieve a tighter error bound for cross-network node classification compared to existing graph domain adaptation methods. Extensive experiments on nine pairs of publicly available cross-domain datasets show that SATMC outperforms state-of-the-art methods in the cross-network node classification task. The code is available at https://github.com/GiantZhangYT/SATMC.

Graph adversarial attacks refer to a class of adversarial attack methods targeting graph-structured data, such as social networks, knowledge graphs, and molecular structures. The objective of these attacks is to introduce subtle yet carefully designed perturbations to graph data (e.g., nodes, edges, or features) to cause graph-based machine learning models, such as graph neural networks (GNNs), to produce incorrect predictions or classification results. The core idea behind graph adversarial attacks is to exploit the vulnerabilities of the model, maximizing the degradation of its performance with minimal perturbations. However, due to the incompleteness of attack strategies, graph adversarial attacks often exhibit redundancy, meaning that some perturbations are ineffective. These ineffective perturbations consume the attack budget and increase the likelihood of detection. To address this issue, this paper proposes Budget-Reduced Attack Filtering (BRAF in short) frameworks capable of eliminating ineffective perturbations produced by existing graph adversarial attack methods, thereby optimizing the attack budget. Extensive experiments validate the effectiveness and scalability of the proposed filtering frameworks. The code is available at https://github.com/Xiangchao-Wen/Filter-Graph-Attack.

Anomalous links such as noisy links or adversarial edges widely exist in real-world networks, which may undermine the credibility of the network study, e.g., community detection in social networks. Therefore, anomalous links need to be removed from the polluted network by a detector. Due to the co-existence of normal links and anomalous links, how to identify anomalous links in a polluted network is a challenging issue. By designing a robust graph structure embedding framework, also called RGSE, the link-level feature representations that are generated from both global embedding view and local stable view can be used for anomalous link detection on contaminated graphs. Comparison experiments on a variety of datasets demonstrate that the new model and its variants achieve up to an average 5.2% improvement with respect to the accuracy of anomalous link detection against the traditional graph representation models. Further analyses also provide interpretable evidence to support the model's superiority.

Removing noisy links from an observed network is a task commonly required for preprocessing real-world network data. However, containing both noisy and clean links, the observed network cannot be treated as a trustworthy information source for supervised learning. Therefore, it is necessary but also technically challenging to detect noisy links in the context of data contamination. To address this issue, in the present article, a two-phased computational model is proposed, called link-information augmented twin autoencoders, which is able to deal with: 1) link information augmentation; 2) link-level contrastive denoising; 3) link information correction. Extensive experiments on six real-world networks verify that the proposed model outperforms other comparable methods in removing noisy links from the observed network so as to recover the real network from the corrupted one very accurately. Extended analyses also provide interpretable evidence to support the superiority of the proposed model for the task of network denoising.

Network embedding, also known as network repre-sentation, has attracted a surge of attention in data mining and machine learning community as a fundamental tool to treat net-work data. Most existing deep learning-based network embedding approaches focus on reconstructing the pairwise connections of micro-structure, which are easily disturbed by network anomaly or attack. Thus, to address the aforementioned challenge, we pro-pose a novel robust framework for attributed network embedding by preserving Community Information (AnECI). Rather than using pairwise connection-based micro-structure, we try to guide the node embedding by the underlying community structure learned from data itself as an unsupervised learning, as to own stronger anti-interference ability. Specially, we put forward a new modularity function for high-order proximity and overlapped community to guide the network embedding of an attributed graph encoder. We conducted extensive experiments on node classification, anomaly detection and community detection tasks on real benchmark data sets, and the results show that AnECI is superior to the state-of-art attributed network embedding methods.

Anomaly detection in hyperspectral image (HSI) is affected by redundant bands and the limited utilization capacity of spectral–spatial information. In this article, we propose a novel improved Isolation Forest (IIF) algorithm based on the assumption that anomaly pixels are more susceptible to isolation than background pixels. The proposed IIF is a modified version of the Isolation Forest (iForest) algorithm, which addresses the poor performance of iForest in detecting local anomalies and anomaly detection in high-dimensional data. Furthermore, we propose a spectral–spatial anomaly detector based on IIF (SSIIFD) to make full use of global and local information, as well as spectral and spatial information. To be specific, first, we apply the Gabor filter to extract spatial features, which are then employed as input to the relative mass isolation forest (ReMass-iForest) detector to obtain the spatial anomaly score. Next, original images are divided into several homogeneous regions via the entropy rate segmentation (ERS) algorithm, and the preprocessed images are then employed as input to the proposed IIF detector to obtain the spectral anomaly score. Finally, we fuse the spatial and spectral anomaly scores by combining them linearly to predict anomaly pixels. The experimental results on four real hyperspectral datasets demonstrate that the proposed detector outperforms other state-of-the-art methods.

The amount of music information available on the Web is rapidly increasing. There is a pressing need for music information extraction. To extract useful information from natural language text, we must recognize music named entities first. This paper introduces a hybrid method to identify the Chinese named entities in music domain. Recently, machine learning approaches are frequently used to solve name entity recognition (NER). So our method uses a hidden Markov model (HMM) as the underlying method. Since HMM has innate weaknesses, we incorporate it with rule-based method for pre-processing and post-processing. The combination of machine learning method and rule-based method results in a high precision recognition. And we improve both training and recognizing process of HMM for music named entity recognition (MNER). In this paper, a novel and convenient musical name entity (MNE) tagging method to generate training data is proposed, which makes HMM method practically usable. In addition, we present an effective method of unknown words tagging in recognition. The experimental results show that our framework brings significant improvements for solving MNER.