Graph neural networks (GNNs) have recently garnered significant attention for use in network intrusion detection systems (NIDS), owing to their ability to model network traffic as graphs and capture complex dependencies between flows. However, existing GNN-based methods face critical limitations: their reliance on labeled data, often scarce or noisy in practice, and their inability to address multi-scale threats, such as localized node anomalies (e.g., port scanning), coordinated subnet-work attacks (e.g., botnets), and global network-wide campaigns (e.g., DDoS attacks). To bridge this gap, we propose Multi-Scale Graph Contrastive Representation Learning (MGCRL), a semi-supervised framework that hierarchically integrates three perspectives to model network intrusions. At the node level, MGCRL constructs semantic subnetworks around individual traffic flows to capture fine-grained behavioral deviations. For subnetwork-level threats, it employs substructure-aware pooling to identify coordinated anomalies, such as clusters of devices exhibiting synchronized malicious activity. Finally, at the global level, MGCRL derives representations that reflect the holistic state of the network, enabling detection of large-scale threats, such as distributed malware propagation. MGCRL couples a shared GNN encoder with a multi-level contrastive loss to align multi-scale representations while largely eliminating label dependence. It learns discriminative features from unlabeled traffic, sharpens decision boundaries with minimal supervision, and exposes anomalies that surface in a hierarchical network context by contrasting related and unrelated nodes at each scale. Extensive experiments on three benchmark datasets for multi-class classification show that MGCRL consistently outperforms SOTA methods, particularly under severe label scarcity and class imbalance.

This paper presents FFS-ORAN-IDS, a federated few-shot intrusion-detection framework that secures streaming traffic in Open Radio Access Networks (O-RAN) while respecting their stringent latency and resource constraints. The framework addresses the twin challenges of scarce attack labels and heterogeneous data, where naïve pseudo-label injection without sufficient confidence propagates errors, large-scale labeling of streaming traffic is impractical, and inherent uncertainty often requires costly human intervention. FFS-ORAN-IDS combines three coordinated x-functional blocks: a confidence-adaptive curriculum that releases pseudo-labels only when local TabTransformers are reliable, a diversity filter that retains the most informative uncertain packets, and a token-budgeted large-language-model (LLM) oracle that verifies the remaining hard samples. A mixed-integer optimization jointly governs curriculum pacing, sampling size, and Oracle LLM calls so that each federated round minimizes detection loss, propagation error, and LLM token cost under per-round resource caps. We train FFS-ORAN-IDS in two stages: an initial few-shot phase that fits the TabTransformer on the scarce ground-truth packets, followed by iterative rounds that refine the model with oracle-verified pseudo-labels. Experimental evaluation on the CIC-IDS 2018 benchmark shows that the proposed framework improves detection accuracy by 6%, reduces label-error propagation by 20%, and lowers energy consumption by 40% in the most label-constrained scenarios.

Spatiotemporal graph neural networks (STGNNs) have proven especially effective in traffic prediction tasks by modeling sensors or regions as nodes, with distances and correlations as edges. Their ability to capture complex spatiotemporal dependencies in road networks drives key applications in public safety, urban planning, and intelligent transportation. However, existing STGNNs often rely on manually designed architectures and typically process multiview graphs separately, requiring specialized expertise, thus limiting flexibility and overlooking intricate spatiotemporal interdependencies. To address these challenges, we propose an Attention-based Dynamic Multiview Spatiotemporal Graph Neural Architecture Search (ADMGNAS) framework, comprising three interconnected components. First, we introduce a unified Attention-based Dynamic Multiview Spatiotemporal Graph (ADMSTG) architecture that integrates spatiotemporal and view-aware attention mechanisms, enabling the effective capture of complex cross-view relationships. Building upon this architecture, we then develop a dedicated Multiview Attention Spatiotemporal (MVAS) search space, which systematically automates the selection of optimal attention operations. Then, a specialized differentiable search algorithm efficiently explores the MVAS space to dynamically identify architecture variations specifically tailored to dynamic multiview spatiotemporal graphs. Extensive experiments on benchmark datasets show that ADMGNAS consistently outperforms SOTA methods, proving its effectiveness and adaptability.

BACKGROUND: Drug response prediction is critical in precision medicine to determine the most effective and safe treatments for individual patients. Traditional prediction methods relying on demographic and genetic data often fall short in accuracy and robustness. Recent graph-based models, while promising, frequently neglect the critical role of atomic interactions and fail to integrate drug fingerprints with SMILES for comprehensive molecular graph construction. RESULTS: We introduce multimodal multi-channel graph attention network with adaptive fusion (MGATAF), a framework designed to enhance drug response predictions by capturing both local and global interactions among graph nodes. MGATAF improves drug representation by integrating SMILES and fingerprints, resulting in more precise predictions of drug effects. The methodology involves constructing multimodal molecular graphs, employing multi-channel graph attention networks to capture diverse interactions, and using adaptive fusion to integrate these interactions at multiple abstraction levels. Empirical results demonstrate MGATAF's superior performance compared to traditional and other graph-based techniques. For example, on the GDSC dataset, MGATAF achieved a 5.12% improvement in the Pearson correlation coefficient (PCC), reaching 0.9312 with an RMSE of 0.0225. Similarly, in new cell-line tests, MGATAF outperformed baselines with a PCC of 0.8536 and an RMSE of 0.0321 on the GDSC dataset, and a PCC of 0.7364 with an RMSE of 0.0531 on the CCLE dataset. CONCLUSIONS: MGATAF significantly advances drug response prediction by effectively integrating multiple molecular data types and capturing complex interactions. This framework enhances prediction accuracy and offers a robust tool for personalized medicine, potentially leading to more effective and safer treatments for patients. Future research can expand on this work by exploring additional data modalities and refining the adaptive fusion mechanisms.

Multi-modal multi-view graph learning models have achieved significant success in medical outcome prediction, combining various modalities to enhance the performance of various medical tasks. However, current architectures for multi-modal multi-view graph learning (M3GL) models heavily depend on manual design, demanding significant effort and expert experience. Meanwhile, significant advancements have been achieved in the field of graph neural architecture search (GNAS), contributing to the automated design of learning architectures based on graphs. However, GNAS faces challenges in automating multimodal multi-view graph learning (M3GL) models, as existing frameworks cannot handle M3GL architecture topology, and current search spaces do not consider M3GL models. To address the above challenges, we propose, for the first time, a multi-modal multi-view graph neural architecture search (M3GNAS) framework that automates the construction of the optimal M3GL models, enabling the integration of multi-modal features from different views. We also design an effective multi-modal multi-view learning (M3L) search space to develop inner-view and outer-view graph representation learning in the context of graph learning, obtaining a latent graph representation tailored to the specific requirements of downstream tasks. To examine the effectiveness of M3GNAS, it is evaluated on medical outcome prediction tasks. The experimental findings demonstrate our proposed framework’s superior performance compared to state-of-the-art models.

Drug-drug interaction (DDI) has attracted widespread attention because when incompatible drugs are taken together, DDI will lead to adverse effects on the body, such as drug poisoning or reduced drug efficacy. The adverse effects of DDI are closely determined by the molecular structures of the drugs involved. To represent drug data effectively, researchers usually treat the molecular structure of drugs as a molecule graph. Then, previous studies can use the handcrafted graph neural network (GNN) model to learn the molecular graph representations of drugs for DDI prediction. However, in the field of bioinformatics, manually designing GNN architectures for specific molecular structure datasets is time-consuming and depends on expert experience. To address this problem, we propose an automatic drug-drug interaction prediction method named AutoDDI that can efficiently and automatically design the GNN architecture for drug-drug interaction prediction without manual intervention. To this end, we first design an effective search space for drug-drug interaction prediction by revisiting various handcrafted GNN architectures. Then, to efficiently and automatically design the optimal GNN architecture for each drug dataset from the search space, a reinforcement learning search algorithm is adopted. The experiment results show that AutoDDI can achieve the best performance on two real-world datasets. Moreover, the visual interpretation results of the case study show that AutoDDI can effectively capture drug substructure for drug-drug interaction prediction.

MOTIVATION: Understanding drug-response differences in cancer treatments is one of the most challenging aspects of personalized medicine. Recently, graph neural networks (GNNs) have become state-of-the-art methods in many graph representation learning scenarios in bioinformatics. However, building an optimal handcrafted GNN model for a particular drug sensitivity dataset requires manual design and fine-tuning of the hyperparameters for the GNN model, which is time-consuming and requires expert knowledge. RESULTS: In this work, we propose AutoCDRP, a novel framework for automated cancer drug-response predictor using GNNs. Our approach leverages surrogate modeling to efficiently search for the most effective GNN architecture. AutoCDRP uses a surrogate model to predict the performance of GNN architectures sampled from a search space, allowing it to select the optimal architecture based on evaluation performance. Hence, AutoCDRP can efficiently identify the optimal GNN architecture by exploring the performance of all GNN architectures in the search space. Through comprehensive experiments on two benchmark datasets, we demonstrate that the GNN architecture generated by AutoCDRP surpasses state-of-the-art designs. Notably, the optimal GNN architecture identified by AutoCDRP consistently outperforms the best baseline architecture from the first epoch, providing further evidence of its effectiveness. AVAILABILITY AND IMPLEMENTATION: https://github.com/BeObm/AutoCDRP.

Recently, graph neural architecture search (GNAS) frameworks have been successfully used to automatically design the optimal neural architectures for many problems such as node classification and graph classification. In the existing GNAS frameworks, the designed graph neural network (GNN) architectures learn the representation of homogenous graphs with one type of relationship connecting two nodes. However, multi-view graphs, where each view represents a type of relationship among nodes, are ubiquitous in the real world. The traditional GNAS frameworks learn the graph representation without considering the interactions between nodes and multiple relationships, so they fail to solve multi-view graph-based problems, such as multi-view graphs modelling the biomedical entity and relation extraction tasks. In this paper, we propose MVGNAS, a multi-view graph neural network automatic modelling framework for biomedical entity and relation extraction, to resolve this challenge. In MVGNAS, we propose an automatic multi-view representation learning to learn low-dimensional representations of nodes that capture multiple relationships in a multi-view graph, representing the first research work in literature to solve the problem of multi-view graph representation learning architecture search for biomedical entity and relation extraction tasks. The experimental results demonstrate that MVGNAS can achieve the best performance in biomedical entity and relation extraction tasks against the state-of-the-art baseline methods.

In this article, first a comprehensive study of the impact of term weighting schemes on the topic modeling performance (i.e., LDA and DMM) on Arabic long and short texts is presented. We investigate six term weighting methods including Word count method (standard topic models), TFIDF, PMI, BDC, CLPB, and CEW. Moreover, we propose a novel combination term weighting scheme, namely, CmTLB. We utilize the mTFIDF that takes into account the missing terms and the number of the documents in which the term appears when calculating the term weight. For further robust term weight, we combine mTFIDF with two weighting methods. We evaluate CmTLB against the studied weighting schemes by the quality of the learned topics (topic visualization and topic coherence), classification, and clustering tasks. We applied weighting schemes to Latent Dirichlet allocation (LDA) and Dirichlet multinomial mixture (DMM) on eight Arabic long and short document datasets, respectively. The experiment results outline that appropriate weighting schemes can effectively improve topic modeling performance on Arabic texts. More importantly, our proposed CmTLB significantly outperforms the other weighting schemes. Secondly, we investigate whether the Arabic stemming process can improve topic modeling performance. We study the three approaches of Arabic stemming including root-based, stem-based, and statistical approaches. We also train topic models with weighting schemes on documents after applying four stemmers related to different stemming approaches. The results outline that applying the stemming process not only reduces the dimensionality of term-document matrix leading to fast estimation process, but also show enhancement of topic modeling performance both on short and long Arabic documents. Moreover, Farasa stemmer achieves the highest performance in most cases, since it prevents the ambiguity that may happen because of the blind removal of the affixes such as in root-based or stem-based stemmers.