Learning representations on graphs is foundational for many downstream tasks, and its synergy with diffusion models has emerged as a promising direction. However, diffusion-based methods for heterogeneous graphs remain underexplored, confronting two principal challenges: (1) The presence of noise and structural heterogeneity in graphs makes it challenging to accurately capture semantic transitions among diverse relation types. (2) The isotropic Gaussian noise used in forward diffusion fails to reflect graphs' inherent semantics and structural anisotropy. To address these, we propose ARDiff, a novel framework that integrates residual diffusion with anisotropic noise for heterogeneous graph learning. Specifically, we propose a semantic residual diffusion mechanism that progressively refines node embeddings by orchestrating transitions from low-semantic (high-noise) to high-semantic (low-noise) relational contexts, thus enabling step-wise distillation of task-relevant information. In addition, to address the limitations of conventional diffusion, we introduce an anisotropic diffusion strategy: in the forward process, noise injection is oriented by structural and semantic priors; in the denoising step, a conditional diffusion mechanism is guided by a random walk encoding, enhancing both topological consistency and semantic alignment. Extensive evaluation on heterogeneous graph datasets demonstrates that ARDiff significantly surpasses current leading methods in link prediction and node classification, setting a new paradigm and benchmark in heterogeneous graph representation learning.

Data imbalance poses a significant challenge in deep learning for regression tasks, where continuous labels display intrinsic ordering and vary in density across the label space. Traditional methods, mainly developed for classification problems, do not adequately address the continuous characteristics of regression. To overcome this, we introduce Dynamic Similarity Weighted Regression (DSWR), an innovative approach designed to effectively bridge the gap between label space and feature space in regression scenarios. DSWR leverages information from the label space to inform and constrain feature space representation, ensuring that samples with similar labels also exhibit similarity in their feature representations. This strategy enhances the model’s ability to learn from imbalanced data by emphasizing the continuity and structured order of the label space. It also extends the model’s applicability to complex, high-dimensional label spaces, such as those found in depth map regression tasks. Unlike traditional methods that may focus solely on local distributions or employ smoothing techniques, DSWR considers both proximate and distant label relationships. This promotes a feature space arrangement that accurately reflects the nuanced structure of the label space. Validated on three distinct datasets, DSWR has demonstrated superior performance, offering a new perspective on tackling data imbalance in regression models.

Summary Imbalanced samples are widespread, which impairs the generalization and fairness of models. Semi‐supervised learning can overcome the deficiency of rare labeled samples, but it is challenging to select high‐quality pseudo‐label data. Unlike discrete labels that can be matched one‐to‐one with points on a numerical axis, labels in regression tasks are consecutive and cannot be directly chosen. Besides, the distribution of unlabeled data is imbalanced, which easily leads to an imbalanced distribution of pseudo‐label data, exacerbating the imbalance in the semi‐supervised dataset. To solve this problem, this article proposes a semi‐supervised imbalanced regression network (SIRN), which consists of two components: A, designed to learn the relationship between features and labels (targets), and B, dedicated to learning the relationship between features and target deviations. To measure target deviations under imbalanced distribution, the target deviation function is introduced. To select continuous pseudo‐labels, the deviation matching strategy is designed. Furthermore, an adaptive selection function is developed to mitigate the risk of skewed distributions due to imbalanced pseudo‐label data. Finally, the effectiveness of the proposed method is validated through evaluations of two regression tasks. The results show a great reduction in predicted value error, particularly in few‐shot regions. This empirical evidence confirms the efficacy of our method in addressing the issue of imbalanced samples in regression tasks.

An alternative learning approach for destructive testing of structural specimens in civil engineering is explored by using a remote laboratory experimentation method.The remote laboratory approach focuses on overcoming the constraints in the hands-on experimentation without compromising the understanding of the students on the concepts and mechanics of reinforced concrete structures.The goal of this study is to evaluate whether or not the remote laboratory experimentation approach can become a standard in civil engineering teaching.The teaching activity using remote-laboratory experimentation is presented here and the outcomes of this activity are outlined.The experience and feedback gathered from this study are used to improve the remote-laboratory experimentation approach in future years to other aspects of civil engineering where destructive testing is essential.