Cui Huang

Heterogeneous graph neural networks have become popular in various domains. However, their generalizability and interpretability are limited due to the discrepancy between their inherent inference flows and human reasoning logic or underlying causal relationships for the learning problem. This study introduces a novel solution, HG-SCM (Heterogeneous Graph as Structural Causal Model). It can mimic the human perception and decision process through two key steps: constructing intelligible variables based on semantics derived from the graph schema and automatically learning task-level causal relationships among these variables by incorporating advanced causal discovery techniques. We compared HG-SCM to seven state-of-the-art baseline models on three real-world datasets, under three distinct and ubiquitous out-of-distribution settings. HG-SCM achieved the highest average performance rank with minimal standard deviation, substantiating its effectiveness and superiority in terms of both predictive power and generalizability. Additionally, the visualization and analysis of the auto-learned causal diagrams for the three tasks aligned well with domain knowledge and human cognition, demonstrating prominent interpretability. HG-SCM's human-like nature and its enhanced generalizability and interpretability make it a promising solution for special scenarios where transparency and trustworthiness are paramount.

Information technology (IT) policies have played an indispensable role in China’s IT research and development (R&D) and industrial development. However, there has been a lack of quantitative and clear understanding of the consistency and diversity of China’s IT policy mixes. In this article, we constructed policy target network to simulate the real policy mixes. Based on the distribution and evolution of networks, we identify and analyse the ‘diversity’ and ‘consistency & continuity’ of China’s IT policy. Our results show that China’s IT policies cover 12 different demands, and each demand corresponds to 5–10 core policy goals. At the same time, we divide the history of IT policy into seven periods and compare the characteristics of each period. Despite the scale of the policy mixes continuing to expand, the synergy between different policy targets has become clearer, forming unique communities. Among them, there are 25 core policy targets that reflect varying degrees of consistency and continuity. This study not only deepens the understanding of China’s policy characteristics and patterns, but also provides a quantitative framework for the assessment of policy consistency and diversity.

This study aimed to determine whether learning engagement plays a mediating effect on the relationship between family capital and students’ higher education gains in mainland China. We used family capital, learning engagement, and higher education gains as measures and analyzed data using a structural equation model. Data were collected from 1334 students at a Chinese university. The results show that family cultural capital had the most significant effect on students’ learning engagement, while economic capital also played a positive role, and social capital had no significant impact. Learning engagement played a mediating role in the relationship between cultural capital and higher education gains, as did the relationship between economic capital and higher education gains. However, learning engagement did not have a mediating effect on the relationship between social capital and higher education gains. Our results show that we should focus on the importance of students’ learning engagement, improve the cultural capital of disadvantaged groups, and provide financial support for students from low-income families.

Purpose: The paper aims to explore whether topic analysis (identification of the core contents, trends and topic distribution in the target field) can be performed using a more low-cost and easily applicable method that relies on a small dataset, and how we can obtain this small dataset based on the features of the publications. Design/methodology/approach: The paper proposes a topic analysis method based on prolific and authoritative researchers (PARs). First, the authors identify PARs in a specific discipline by considering the number of publications and citations of authors. Based on the research publications of PARs (small dataset), the authors then construct a keyword co-occurrence network and perform a topic analysis. Finally, the authors compare the method with the traditional method. Findings: The authors found that using a small dataset (only 6.47% of the complete dataset in our experiment) for topic analysis yields relatively high-quality and reliable results. The comparison analysis reveals that the proposed method is quite similar to the results of traditional large dataset analysis in terms of publication time distribution, research areas, core keywords and keyword network density. Research limitations/implications: Expert opinions are needed in determining the parameters of PARs identification algorithm. The proposed method may neglect the publications of junior researchers and its biases should be discussed. Practical implications: This paper gives a practical way on how to implement disciplinary analysis based on a small dataset, and how to identify this dataset by proposing a PARs-based topic analysis method. The proposed method presents a useful view of the data based on PARs that can produce results comparable to traditional method, and thus will improve the effectiveness and cost of interdisciplinary topic analysis. Originality/value: This paper proposes a PARs-based topic analysis method and verifies that topic analysis can be performed using a small dataset.