Sixth-Generation (6G) networks necessitate intelligent and energy-efficient operations. However, the direct deployment of Large Language Models (LLMs) for real-time 6G control is hindered by significant latency and energy constraints, conflicting with green 6G imperatives. This paper pioneers a collaborative architecture of large-small AI models to address these challenges. In this architecture, resource-intensive LLMs, i.e., large models, are strategically employed offline for comprehensive Wireless Data Knowledge Graph (WDKG) construction, effectively distilling domain knowledge. This WDKG, in turn, enables the development and deployment of lightweight, efficient small models for real-time network tasks by facilitating the generation of optimized feature datasets. To operationalize this, we first introduce a novel multi-agent collaborative LLM framework, bolstered by an enhanced semantic representation method incorporating domain-adaptive embedding fine-tuning and mutual information (MI)-based feature encoding, for automated high-fidelity WDKG construction. Subsequently, we propose the Semantic-Data and Spatio-Temporal (SD-ST) model, which uniquely fuses LLM-extracted semantic information with the spatio-temporal characteristics of wireless network data and WDKG structure. Insights from the SD-ST model guide a WDKG-driven method for generating optimized feature datasets by evaluating node influence and redundancy. Experimental validation demonstrates that these distilled feature datasets lead to substantial reductions in training and inference overhead for the lightweight downstream AI models, offering a tangible pathway towards greener, more efficient, and intelligent 6G networks.

High-dimensional time series data are becoming more widespread in many domains, including large-scale wireless networks for communication. However, because of its high dimensionality, label scarcity, and complicated temporal connections, anomaly detection in such data is difficult. This work proposes a Bayesian network conditional normalizing flow model for multivariate time series anomaly detection, called Graphormer-based Bayesian Network Conditional Normalizing Flow (GBNCNF), based on a graph Transformer (Graphormer) to convert the spatial and temporal dependencies of high-dimensional time series into simple evaluable conditional densities. It models the causal links between numerous time series using a Bayesian network, and it obtains representations of the interdependencies between different time series by combining LSTM modules with Graphormer modules. These representations are introduced as conditional information into the normalizing flow for density estimation, and data corresponding to low density are judged as anomalies. Experiments are conducted on two real datasets and show that our method detects anomalies more accurately than baseline methods, accurately captures the correlations between sensors, and allows users to infer the root causes of detected anomalies.

Native artificial intelligence (AI) has played a pivotal role in shaping the evolution of 6G networks. It must meet stringent real-time requirements and therefore deploying lightweight AI models is necessary. However, as wireless networks generate a multitude of data fields and only a fraction of them imposes significant impact on the AI models, it is essential to accurately identify a small amount of critical data that significantly impacts communication performance. In this paper, we propose the pervasive multi-level (PML) native AI architecture, which incorporates knowledge graph (KG) into mobile network operations to establish a wireless data KG. Leveraging the wireless data KG, we analyze the relationships among various data fields and provide the on-demand generation of minimal and effective datasets, referred to as feature datasets. Consequently, it not only enhances AI training, inference, and validation processes but also significantly reduces resource wastage and overhead for communication networks. The proposed solution includes a spatio-temporal heterogeneous graph attention neural network model (STREAM) and a feature dataset generation algorithm. Experimental results validate the exceptional capability of STREAM in handling spatio-temporal data and demonstrate that the proposed architecture effectively reduces data scale and computational costs of AI training by almost an order of magnitude.

With the application of the fifth-generation wireless communication technologies, more smart terminals are being used and generating huge amounts of data, which has prompted extensive research on how to handle and utilize these wireless data. Researchers currently focus on the research on the upper-layer application data or studying the intelligent transmission methods concerning a specific problem based on a large amount of data generated by the Monte Carlo simulations. This article aims to understand the endogenous relationship of wireless data by constructing a knowledge graph according to the wireless communication protocols, and domain expert knowledge and further investigating the wireless endogenous intelligence. We firstly construct a knowledge graph of the endogenous factors of wireless core network data collected via a 5G/B5G testing network. Then, a novel model based on graph convolutional neural networks is designed to learn the representation of the graph, which is used to classify graph nodes and simulate the relation prediction. The proposed model realizes the automatic nodes classification and network anomaly cause tracing. It is also applied to the public datasets in an unsupervised manner. Finally, the results show that the classification accuracy of the proposed model is better than the existing unsupervised graph neural network models, such as VGAE and ARVGE.

This paper is mainly devoted to investigating the migrativity equations involving nullnorms and 2-uninorms. Depending on whether the absorbing elements of 2-uninorms and unllnorms are same or not, all solutions of the migrativity equations for all possible combinations of the three defined subclasses of 2-uninorms and nullnorms are analyzed and characterized respectively. And for such equations, there are new solutions which extend the known ones about the migrativity for uninorms and nullnorms.