In the context of long-tail classification on graphs, the vast majority of existing work primarily revolves around the development of model debiasing strategies, intending to mitigate class imbalances and enhance the overall performance. Despite the notable success, there is very limited literature that provides a theoretical tool for characterizing the behaviors of long-tail classes in graphs and gaining insight into generalization performance in real-world scenarios. To bridge this gap, we propose a generalization bound for long-tail classification on graphs by formulating the problem in the fashion of multi-task learning, i.e., each task corresponds to the prediction of one particular class. Our theoretical results show that the generalization performance of long-tail classification is dominated by the overall loss range and the task complexity. Building upon the theoretical findings, we propose a novel generic framework HierTail for long-tail classification on graphs. In particular, we start with a hierarchical task grouping module that allows us to assign related tasks into hypertasks and thus control the complexity of the task space; then, we further design a balanced contrastive learning module to adaptively balance the gradients of both head and tail classes to control the loss range across all tasks in a unified fashion. Extensive experiments demonstrate the effectiveness of HierTail in characterizing long-tail classes on real graphs, which achieves up to 12.9% improvement over the leading baseline method in balanced accuracy.
1 October 2025 in IEEE Journal of Biomedical and Health Informatics
While type 2 diabetes is predominantly found in the elderly population, recent publications indicate an increasing prevalence in the young adult population. Failing to diagnose it in the minority younger age group could have significant adverse effects on their health. Several previous works acknowledge the bias of machine learning models towards different gender and race groups and propose various approaches to mitigate it. However, those works failed to propose any effective methodologies to diagnose diabetes in the young population, which is the minority group in the diabetic population. This is the first paper where we mention digital ageism towards the young adult population diagnosing diabetes. In this paper, we identify this deficiency in traditional machine learning models and propose an algorithm to mitigate the bias towards the young population when predicting diabetes. Deviating from the traditional concept of one-model-fits-all, we train customized machine-learning models for each age group. Our pipeline trains a separate machine learning model for every 5-year age band (i.e., age groups 30-34, 35-39, and 40-44). The proposed solution consistently improves recall of diabetes class by 26% to 40% in the young age group (30-44). Moreover, our technique outperforms 7 commonly used whole-group resampling techniques (i.e., random oversampling, random undersampling, SMOTE, ADASYN, Tomek-links, ENN, and Near Miss) by at least 36% in terms of diabetes recall in the young age group. Feature important analysis shows that the age attribute has a significant contribution to the decision of the original model, which was marginalized in the age-personalized model. Our method shows improved performance (e.g., balanced accuracy improved 7-12%) over multiple machine learning models and multiple sampling algorithms.
Learning on graphs (LOG) has a profound impact on various high-impact domains, such as information retrieval, social network analysis, computational chemistry and transportation. Despite decades of theoretical development, algorithmic advancements, and open-source systems that answers what the optimal learning results are, concerns about the trustworthiness of state-of-the-art LOG techniques have emerged in practical applications. Consequently, crucial research questions arise: why are LOG techniques untrustworthy with respect to critical social aspects like fairness, transparency, privacy, and security? How can we ensure the trustworthiness of learning algorithms on graphs? To address the increasingly important safety and ethical challenges in learning on graphs, it is essential to achieve a paradigm shift from solely addressing what questions to understanding how and why questions. Building upon the success of the first TrustLOG workshop in 2022, the second TrustLOG workshop aims to bring together researchers and practitioners to present, discuss, and advance cutting-edge research in the realm of trustworthy learning on graphs. The workshop serves as a platform to stimulate the TrustLOG community, fostering the identification of new research challenges, and shedding light on potential future directions.