GraphGuard: An adaptive approach for restoring accuracy in backdoor-compromised GNNs.

MolContraCLIP: Structurally similar molecule retrieval algorithm based on graph neural network and CLIP model.

GIMS: Image matching system based on adaptive graph construction and graph neural network.

Tailoring educational support with graph neural networks and explainable AI: Insights into online learners' metacognitive abilities

Multi-scale Spatio-temporal graph neural network for enhanced water demand forecasting.

A risk assessment framework for online transactions via Graph Neural Networks and efficient probabilistic prediction

Tangency portfolios using graph neural networks.

Environmental impacts prediction using graph neural networks on molecular graphs

Impact of converting graphs into spanning trees on node and graph classification in Graph Neural Network

Bike-sharing ridership prediction for network expansion using graph neural networks

GraSTI-ACL: Graph spatial-temporal infomax with adversarial contrastive learning for brain disorders diagnosis based on resting-state fMRI.

Novel graph neural network and GNN-C-Transformer model construction for direction of arrival estimation

SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical features.

Predicting the equivalent alkane carbon number of oils using graph neural networks and quantum mechanical descriptors

Learning time-dependent PDE via graph neural networks and deep operator network for robust accuracy on irregular grids

Two-stage automated generation of frame structure topology using graph neural networks

Multi-task learning (MTL) is a standard learning paradigm in machine learning. The central idea of MTL is to capture the shared knowledge among multiple tasks for mitigating the problem of data sparsity where the annotated samples for each task are quite limited. Recent studies indicate that graph multi-task learning (GMTL) yields the promising improvement over previous MTL methods. GMTL represents tasks on a task relation graph, and further leverages graph neural networks (GNNs) to learn complex task relationships. Although GMTL achieves the better performance, the construction of task relation graph heavily depends on simple heuristic tricks, which results in the existence of spurious task correlations and the absence of true edges between tasks with strong connections. This problem largely limits the effectiveness of GMTL. To this end, we propose the Generative Causality-driven Network (GCNet), a novel framework that progressively learns the causal structure between tasks to discover which tasks are beneficial to be jointly trained for improving generalization ability and model robustness. To be specific, in the feature space, GCNet first introduces a feature-level generator to generate the structure prior for reducing learning difficulty. Afterwards, GCNet develops a output-level generator which is parameterized as a new causal energy-based model (EBM) to refine the learned structure prior in the output space driven by causality. Benefiting from our proposed causal framework, we theoretically derive an intervention contrastive estimation for training this causal EBM efficiently. Experiments are conducted on multiple synthetic and real-world datasets. Extensive empirical results and model analyses demonstrate the superior performance of GCNet over several competitive MTL baselines.

The delivery of digital information in Indonesian-language news presents challenges in efficiently capturing the core information. This study proposes a combination of the TextRank algorithm and a simple Graph Neural Network (GNN) to improve the quality of automatic text summarization. TextRank is used to construct a sentence graph based on TF-IDF similarity and cosine similarity, followed by training a SimpleGNN model to optimize sentence scores. Evaluations were conducted on 1,000 articles from the Liputan6 dataset using the ROUGE metric (ROUGE-1, ROUGE-2, and ROUGE-L). The results show that this combined method improves performance compared to pure TextRank, especially in capturing semantic relationships between sentences. This study demonstrates that the integration of a simple GNN can enrich representations in graphs and provide more informative and contextual summaries.

Recent applications of liquid chromatography-based QSRR models for pharmaceutically relevant small molecules: A review.

Current network security technologies face new threats from determined attackers employing advanced evasion techniques such as IP spoofing, tiny fragment attacks, tunneling, and HTML smuggling. Conventional intrusion detection and prevention systems (IDS/IPS) have significant limitations in detecting zero-day attacks and sophisticated threats that can continuously alter their attack vectors. This paper presents a novel deep learning-driven, multilayer intrusion detection and prevention framework that integrates network-based IDS/IPS, host-based intrusion detection systems (HIDS), and honeypot technologies with advanced machine learning models, including graph neural networks (GNNs), autoencoders, and transformers. The framework employs adaptive learning mechanisms to enhance resilience against evasion techniques while maintaining low false positive rates. Experimental evaluation using diverse attack datasets demonstrates superior performance, achieving 97.3% detection accuracy for zero-day attacks and 94.8% resilience against advanced evasion techniques, significantly outperforming existing state-of-the-art solutions. The proposed framework contributes to cybersecurity research by introducing innovative multilayer correlation mechanisms, adaptive threat modeling, and evasion-resilient detection algorithms.