Predicting diseases solely from patient-side information, such as demographics and self-reported symptoms, has attracted significant research attention due to its potential to enhance patient awareness, facilitate early healthcare engagement, and improve healthcare system efficiency. However, existing approaches encounter critical challenges, including imbalanced disease distributions and a lack of interpretability, resulting in biased or unreliable predictions. To address these issues, we propose the Knowledge graph-enhanced, Prototype-aware, and Interpretable (KPI) framework. KPI systematically integrates structured and trusted medical knowledge into a unified disease knowledge graph, constructs clinically meaningful disease prototypes, and employs contrastive learning to enhance predictive accuracy, which is particularly important for long-tailed diseases. Additionally, KPI utilizes large language models (LLMs) to generate patient-specific, medically relevant explanations, thereby improving interpretability and reliability. Extensive experiments on real-world datasets demonstrate that KPI outperforms state-of-the-art methods in predictive accuracy and provides clinically valid explanations that closely align with patient narratives, highlighting its practical value for patient-centered healthcare delivery.

Temporal Graph Neural Networks (TGNNs) are increasingly applied in dynamic scenarios, however, their limited explainability hinders their adoption in high-stakes domains. Existing methods tend to conflate causality with temporal proximity, leading to ambiguous explanations that mix impactful and irrelevant events. Moreover, they lack counterfactual reasoning to assess whether altering specific temporal events would change TGNN predictions. To overcome these challenges, we propose CTM-Explainer, which identifies critical temporal dependencies through iterative “what-if” perturbation analysis. To the best of our knowledge, this is the first post-hoc counterfactual explanation framework for TGNN. It enables precise attribution of how specific timestamped events influence TGNN predictions. By embedding causal analysis into a reinforcement learning framework, CTM-Explainer constructs Counterfactual Temporal Motifs (CTMs) that are causally grounded in model outcome shifts via interventional probability estimation. This design eliminates temporally correlated but non-essential events, while preserving those with verified causal influence. Extensive experiments on real-world and synthetic datasets confirm that CTM-Explainer generates more faithful and concise explanations than existing methods, at significantly lower computational cost.

Traffic prediction plays a crucial role in smart cities. As concerns over data privacy grow, direct data sharing is increasingly restricted, prompting substantial interest in Federated Graph Learning for traffic prediction. Nonetheless, most existing methods follow batch learning paradigms, which are unsuitable for dynamic, streaming traffic data. In practical applications, traffic data arrives continuously, calling for online learning techniques. Moreover, current methods often rely on split learning to capture spatio-temporal dependencies, which increases communication overhead and latency, limiting their real-time applicability. To this end, we propose aswiftonlinefederated Graph Learning Framework for Traffic Streaming Data Prediction (Sofedfor short). We introduce an early training strategy to equip clients with the up-to-date local temporal models and dynamic spatial features, enabling rapid adaptation to traffic fluctuations while minimizing client response time. Additionally, we pre-train a masked data generation module to synthesize multi-step data, effectively decoupling the server from real-time ground-truth dependency and enhancing model generalization. Lastly, the client model is optimized for lightweight deployment by offloading specific components to the server. Extensive experiments on real-world datasets demonstrate thatSofedachieves state-of-the-art performance with significantly reduced client response time and communication cost.

User prediction aims to identify the user who show potential value in e-commerce platforms. Existing user prediction algorithms primarily focus on distinguishing between potential user, those likely to purchase a specific product in the future, and non-potential user, those unlikely to do so. However, these algorithms often overlook a valuable group named conditional potential user in non-potential group. Conditional potential user, initially categorized as non-potential, can convert into potential user under specific converted condition (e.g., product trial, coupon receipt, or certification attainment). Additionally, conventional user prediction models do not offer insights into the associated converted condition and provide classification results only. Furthermore, the lack of explainability in user prediction methods limits their practical utility. To tackle these challenges, this paper proposes a definitive concept for conditional potential users and introduces an innovative user prediction framework, the Conditional Potential User Mining (CPUM). Addressing the challenge of predicting conditional potential users, CPUM employs a Gold Standard Classifier to ascertain users’ intentions, thereby identifying their interest in target products under converted conditions and enabling the prediction of conditional potential users. Moreover, CPUM adopts an explainable surrogate model with an attention mechanism to boost explainability. This model is designed to mirror the decision-making capacity of the Gold Standard Classifier and provides importance explanations for different user interactions. This enables precise identification of converted conditions in conditional potential users, thus enhancing explainability. The effectiveness of this method is substantiated by experimental results derived from extensive e-commerce datasets from Alibaba and Amazon, demonstrating its cutting-edge performance and applicability. • Introduces the concept of conditional potential users in e-commerce. • Launches CPUM framework for accurate prediction of conditional potential users. • Enhances model explainability with a surrogate model and attention mechanism. • Validates CPUM’s effectiveness with Amazon and Alibaba datasets. • Offers a scalable user prediction model adaptable to various e-commerce platforms.

Graph Neural Networks (GNNs) hold promise in various application domains, but their limited explainability hinders widespread adoption, impacting customer satisfaction and loyalty. This issue intensifies when addressing diverse explanation needs of different user groups. Current GNN explanation models focus on a single objective, neglecting varied and potential conflicting user requirements, resulting in suboptimal outcomes. Moreover, existing models prioritize explanation objectives during multi-objective explanations, disrupting the intrinsic hierarchical structures and distant relationships within the graphs, further diminishing their effectiveness. To tackle these challenges, this paper introduces a novel multi-objective explanatory framework with hierarchical structure attribution for GNNs, termed HM-Explainer. This framework constructs a multi-objective explanation generation module based on Pareto theory to balance different and potentially conflicting explanatory objectives. Additionally, to embed hierarchical information into explanations, HM-Explainer designs node-level and cluster-level attribution modules to analyze the impact of input data on GNN decisions hierarchically. Furthermore, a self-attention mechanism is integrated into the node-level attribution module to account for the influence of distant neighbors. Ultimately, the efficacy of HM-Explainer is validated across multiple datasets for different GNN models through experimentation.

Graph Neural Networks (GNNs) have significantly advanced recommendation systems by capturing complex interplays between user-item relationships and dependencies. However, inherent noise in user behaviors, manifesting as random clicks and diverse browsing patterns, disrupts the structural integrity of graphs, thereby degrading the accuracy and reliability of GNN-based recommendation systems. Traditional graph pruning methods, which remove or reweight connections, often fail to adequately address this noise because they neglect the deeper causal factors influencing user choices, resulting in biased outcomes. To confront these challenges, this paper presents the GNN-based Causal Denoising Framework (GCDF). GCDF employs causal relationships to filter out noisy connections, thus enhancing the performance of GNNs. By utilizing a denoised graph that more accurately reflects the causal interactions among items, GCDF significantly improves the accuracy and reliability of recommendations, as evidenced by comprehensive empirical evaluations.