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.

Breast cancer is a serious health threat to women. The early detection of breast cancer is crucial to improving survival rates and reducing the difficulty of treatment. In recent years, denoising diffusion probability models (DDPM) have performed well in image generation, but their application to breast cancer classification remains unknown. Additionally, conditional priors are often the most important source of information for diffusion models to solve problems, and fuzzy lesions or high-noise images pose a significant challenge for the model to extract accurate prior information. To address these issues, we propose a new classification model based on DDPM and combine it with the holographic guided diffusion framework (HGDF) to remove noise from images through specific guidance and make full use of HPC resources to improve the classification performance of breast cancer images. Results from the experiment indicate that the model has excellent accuracy in ultrasound images (BUS dataset) and mammography images (MAMMO dataset), with accuracy of 86.17 % ± 1.74% and 94.32% ± 2.31%, respectively.