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.
This paper discusses the sociocultural theory (SCT). In particular, three significant concepts of Vyogtsky’s theory: self-regulation, the Zone of Proximal Development (ZPD), and scaffolding all of which have been discussed in numerous second language acquisition (SLA) and second language learning (SLL) research papers. These concepts lay the psychological foundation for collaborative learning, the subject of this paper. This publication aims to examine SCT by assessing collaborative learning within the Chinese context. This paper focuses on teacher-student collaboration and it concludes that the perceived way of learning and teaching and teacher-student relationship should be changed in order to implement collaborative learning.
3 February 2025 in IEEE Journal of Biomedical and Health Informatics
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.
Senqi Yang, Dongyu Zhang, Jing Ren, Ziqi Xu, Xiuzhen Zhang, Yiliao Song, Hongfei Lin, Feng Xia. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Interpreting the personality and the disposition of people is important for social interaction. Both emotional expression and facial width are known to affect personality perception. Moreover, both the apparent emotional expression and the apparent width-to-height ratio of the face change with head tilt. We investigated how head tilt affects judgements of trustworthiness and dominance and whether such trait judgements reflect apparent emotion or facial width. Sixty-seven participants rated the dominance, emotion, and trustworthiness of 24 faces posing with different head tilts while maintaining eye gaze at the camera. Both the 30° up and 20° down head postures were perceived as less trustworthy and more dominant (less submissive) than the head-level posture. Change in perceived trustworthiness and submissiveness with head tilt correlated with change in apparent emotional positivity but not change in facial width. Hence, our analysis suggests that apparent emotional expression provides a better explanation of perceived trustworthiness and dominance compared with cues to facial structure.
1 January 2021 in Computer Science and Information Systems
Metaphor is widely used in human communication. The cohort of scholars studying metaphor in various fields is continuously growing, but very few work has been done in bibliographical analysis of metaphor research. This paper examines the advancements in metaphor research from 2000 to 2017. Using data retrieved from Microsoft Academic Graph and Web of Science, this paper makes a macro analysis of metaphor re search, and expounds the underlying patterns of its development. Taking into consideration sub-fields of metaphor research, the internal analysis of metaphor research is carried out from a micro perspective to reveal the evolution of research topics and the inherent relationships among them. This paper provides novel insights into the current state of the art of metaphor research as well as future trends in this field, which may spark new research interests in metaphor from both linguistic and interdisciplinary perspectives.