Search Results (5)

With the rapid growth of Chinese social media data, many language-driven analytical tasks, such as sentiment analysis and malicious account detection, are increasingly formulated as computationally expensive optimization problems, particularly in the context of hyperparameter tuning for deep learning models. Due to the intrinsic characteristics of Chinese text, including implicit word boundaries, strong context dependency, and high linguistic variability, the resulting feature representations are often high-dimensional, sparse, and heterogeneously distributed. From an optimization perspective, these properties induce highly irregular, non-smooth, and multimodal objective landscapes, posing significant challenges to conventional surrogate-assisted data-driven evolutionary algorithms (DDEAs). To address this problem, this paper proposes a Normal Selection-based data-driven evolutionary algorithm (NSEA) for improving surrogate-assisted optimization under complex conditions. Specifically, a Normal distribution-based selection strategy (NSS) is developed to enable probabilistic selection of surrogate models, balancing exploitation of high-performing models and exploration of alternative candidates, thereby alleviating premature convergence in multimodal search spaces. In addition, an exponential weighting ensemble (EWE) method is introduced to aggregate surrogate models based on their relative ranking performance, which enhances the stability and generalization capability of fitness approximation across different regions of the search space. Extensive experiments on benchmark functions demonstrate that the proposed NSEA consistently outperforms several state-of-the-art DDEAs in terms of optimization accuracy and robustness. Furthermore, a real-world application of cheating official account (COA) detection on Chinese social media is conducted, in which the hyperparameter optimization of a heterogeneous graph transformer (HGT) model is formulated as an EOP. The results further prove the effectiveness and practical applicability of the NSEA in complex data-driven scenarios. Overall, this study provides an effective optimization framework for handling EOPs with complex and multimodal characteristics and offers a feasible computational approach for tasks associated with large-scale Chinese textual data. Full article

Continuous Integration pipelines rely on large-scale automated testing to support rapid releases. However, flaky tests exhibit non-deterministic outcomes under an identical code and configuration, substantially increasing rerun costs and hindering fault localization. Existing approaches struggle to uniformly model heterogeneous runtime evidence and its multi-relational structure in CI environments, which limits cross-project generalization and interpretability. To address this gap, this paper presents HgtFlaky, a runtime-evidence-centered multi-view heterogeneous graph learning framework. A Unified Event Model is introduced to normalize heterogeneous CI artifacts into semantically consistent event quadruples, and a heterogeneous execution graph is then constructed to capture testing entities and multiple relation types. Based on the HEG, three complementary views are derived to characterize run-level, test-level, and thread-level flaky behaviors. A heterogeneous graph Transformer is further adopted to jointly encode the multi-view graph instances and learn transferable test-level representations for flaky/non-flaky prediction. Experiments on two benchmark datasets, FlakeFlagger and IDoFT, show that HgtFlaky achieves strong and stable performance. Under 10-fold cross-validation, it obtains an F1-score of 83% on FlakeFlagger and 98% on IDoFT. Under per-project validation on FlakeFlagger, HgtFlaky achieves 78% Precision, 89% Recall, and 81% F1-score, outperforming Flakify by 8 percentage points and FlakeFlagger by 74 percentage points in F1-score. Full article

Accurately identifying drug off-targets is essential for reducing toxicity and improving the success rate of pharmaceutical discovery pipelines. However, current deep learning approaches often struggle to fuse chemical structure, protein biology, and multi-target context. Here, we introduce HDPC-LGT (Hybrid Dual-Prompt Cross-Attention Ligand–Protein Graph Transformer), a framework designed to predict ligand binding across sixteen human translation-related proteins clinically associated with antibiotic toxicity. HDPC-LGT combines graph-based chemical reasoning with protein language model embeddings and structural priors to capture biologically meaningful ligand–protein interactions. The model was trained on 216,482 experimentally validated ligand–protein pairs from the Chemical Database of Bioactive Molecules (ChEMBL) and the Protein–Ligand Binding Database (BindingDB) and evaluated using scaffold-level, protein-level, and combined holdout strategies. HDPC-LGT achieves a macro receiver operating characteristic–area under the curve (macro ROC–AUC) of 0.996 and a micro F1-score (micro F1) of 0.989, outperforming Deep Drug–Target Affinity Model (DeepDTA), Graph-based Drug–Target Affinity Model (GraphDTA), Molecule–Protein Interaction Transformer (MolTrans), Cross-Attention Transformer for Drug–Target Interaction (CAT–DTI), and Heterogeneous Graph Transformer for Drug–Target Affinity (HGT–DTA) by 3–7%. External validation using the Papyrus universal bioactivity resource (Papyrus), the Protein Data Bank binding subset (PDBbind), and the benchmark Yamanishi dataset confirms strong generalisation to unseen chemotypes and proteins. HDPC-LGT also provides biologically interpretable outputs: cross-attention maps, Integrated Gradients (IG), and Gradient-weighted Class Activation Mapping (Grad-CAM) highlight catalytic residues in aminoacyl-tRNA synthetases (aaRSs), ribosomal tunnel regions, and pharmacophoric interaction patterns, aligning with known biochemical mechanisms. By integrating multimodal biochemical information with deep learning, HDPC-LGT offers a practical tool for off-target toxicity prediction, structure-based lead optimisation, and polypharmacology research, with potential applications in antibiotic development, safety profiling, and rational compound redesign. Full article

This article addresses the task of building personalized educational recommendations based on a heterogeneous knowledge graph that integrates data from university curricula, job vacancies, and online courses. To solve the problem of course recommendations by their relevance to a user’s competencies, a graph neural network (GNN)-based approach is proposed, specifically utilizing and comparing the Heterogeneous Graph Transformer (HGT) architecture, Graph Sample and Aggregate network (GraphSAGE), and Heterogeneous Graph Attention Network (HAN). Experiments were conducted on a heterogeneous graph comprising various node and relation types. The models were evaluated using regression and ranking metrics. The results demonstrated the superiority of the HGT-based recommendation model as a link regression task, especially in terms of ranking metrics, confirming its suitability for generating accurate and interpretable recommendations in educational systems. The proposed approach can be useful for developing adaptive learning recommendations aligned with users’ career goals. Full article

The microbiome plays a crucial role in maintaining physiological homeostasis and is intricately linked to various diseases. Traditional culture-based microbiological experiments are expensive and time-consuming. Therefore, it is essential to prioritize the development of computational methods that enable further experimental validation of disease-associated microorganisms. Existing computational methods often struggle to effectively capture nonlinear interactions and heterogeneous network structures when predicting microbiome–disease associations. To address this issue, we propose HG-LGBM, an innovative joint prediction framework that combines heterogeneous graph neural networks with a gradient boosting mechanism. We employ a hierarchical heterogeneous graph transformer (HGT) encoder, which utilizes a multi-head attention mechanism to learn higher-order node representations, while LightGBM optimizes the classification task using gradient-boosted decision trees. Evaluated through five-fold cross-validation on the HMDAD and Disbiome datasets, HG-LGBM demonstrated a state-of-the-art performance. The experimental results showed that combining heterogeneous network learning with gradient boosting strategies effectively revealed potential microbiome–disease interactions, providing a powerful tool for biomedical research and precision medicine. Finally, case studies on colorectal cancer and inflammatory bowel disease (IBD) further validated the effectiveness of HG-LGBM. Full article