Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data. The synergy between transformers and graph learning demonstrates strong performance and versatility across various graph-related tasks. This survey provides an in-depth review of recent progress and challenges in graph transformer research. We begin with foundational concepts of graphs and transformers. We then explore design perspectives of graph transformers, focusing on how they integrate graph inductive biases and graph attention mechanisms into the transformer architecture. Furthermore, we propose a taxonomy classifying graph transformers based on depth, scalability, and pretraining strategies, summarizing key principles for effective development of graph transformer models. Beyond technical analysis, we discuss the applications of graph transformer models for node-level, edge-level, and graph-level tasks, exploring their potential in other application scenarios as well. Finally, we identify remaining challenges in the field, such as scalability and efficiency, generalization and robustness, interpretability and explainability, dynamic and complex graphs, as well as data quality and diversity, charting future directions for graph transformer research.

Early detection of Alzheimer's disease (AD) through spontaneous speech analysis represents a promising, non-invasive diagnostic approach. Existing methods predominantly rely on fusion-based multimodal deep learning, effectively integrating linguistic and acoustic features. However, these methods inadequately model higher-order interactions between modalities, reducing diagnostic accuracy. To address this, we introduce SpeechHGT, a multimodal hypergraph transformer designed to capture and learn higher-order interactions in spontaneous speech features. SpeechHGT encodes multimodal features as hypergraphs, where nodes represent individual features and hyperedges represent grouped interactions. A novel hypergraph attention mechanism enables robust modeling of both pairwise and higher-order interactions. Experimental evaluations on the DementiaBank datasets reveal that SpeechHGT achieves state-of-the-art performance, surpassing baseline models in accuracy and F1 score. These results highlight the potential of hypergraph-based models to improve AI-driven diagnostic tools for early AD detection.

Dynamic brain networks play a pivotal role in diagnosing brain disorders by capturing temporal changes in brain activity and connectivity. Previous methods often rely on sliding-window approaches for constructing these networks using fMRI data. However, these methods face two key limitations: a fixed temporal length that inadequately captures brain activity dynamics and a global spatial scope that introduces noise and reduces sensitivity to localized dysfunctions. These challenges can lead to inaccurate brain network representations and potential misdiagnoses.To address these challenges, we propose BrainDGT, a dynamic Graph Transformer model designed to enhance the construction and analysis of dynamic brain networks for more accurate diagnosis of brain disorders. BrainDGT leverages adaptive brain states by deconvolving the Hemodynamic Response Function (HRF) within individual functional brain modules to generate dynamic graphs, addressing the limitations of fixed temporal length and global spatial scope. The model learns spatio-temporal local features through attention mechanisms within these graphs and captures global interactions across modules using adaptive fusion. This dual-level integration enhances the model's ability to analyze complex brain connectivity patterns. We validate BrainDGT's effectiveness through classification experiments on three fMRI datasets (ADNI, PPMI, and ABIDE), where it outperforms state-of-the-art methods. By enabling adaptive, localized analysis of dynamic brain networks, BrainDGT advances neuroimaging and supports the development of more precise diagnostic and treatment strategies in biomedical research.

Abstract The transition from secondary education to higher education could be challenging for most freshmen. For students who fail to adjust to university life smoothly, their status may worsen if the university cannot offer timely and proper guidance. Helping students adapt to university life is a long‐term goal for any academic institution. Therefore, understanding the nature of the maladaptation phenomenon and the early prediction of “at‐risk” students are crucial tasks that urgently need to be tackled effectively. This article aims to analyze the relevant factors that affect the maladaptation phenomenon and predict this phenomenon in advance. We develop a prediction framework (MAladaptive STudEnt pRediction, MASTER) for the early prediction of students with maladaptation. First, our framework uses the SMOTE (Synthetic Minority Oversampling Technique) algorithm to solve the data label imbalance issue. Moreover, a novel ensemble algorithm, priority forest, is proposed for outputting ranks instead of binary results, which enables us to perform proactive interventions in a prioritized manner where limited education resources are available. Experimental results on real‐world education datasets demonstrate that the MASTER framework outperforms other state‐of‐art methods.