A knowledge graph (KG), also known as a knowledge base, is a particular kind of network structure in which the node indicates entity and the edge represent relation. However, with the explosion of network volume, the problem of data sparsity that causes large-scale KG systems to calculate and manage difficultly has become more significant. For alleviating the issue, knowledge graph embedding is proposed to embed entities and relations in a KG to a low-, dense and continuous feature space, and endow the yield model with abilities of knowledge inference and fusion. In recent years, many researchers have poured much attention in this approach, and we will systematically introduce the existing state-of-the-art approaches and a variety of applications that benefit from these methods in this paper. In addition, we discuss future prospects for the development of techniques and application trends. Specifically, we first introduce the embedding models that only leverage the information of observed triplets in the KG. We illustrate the overall framework and specific idea and compare the advantages and disadvantages of such approaches. Next, we introduce the advanced models that utilize additional semantic information to improve the performance of the original methods. We divide the additional information into two categories, including textual descriptions and relation paths. The extension approaches in each category are described, following the same classification criteria as those defined for the triplet fact-based models. We then describe two experiments for comparing the performance of listed methods and mention some broader domain tasks such as question answering, recommender systems, and so forth. Finally, we collect several hurdles that need to be overcome and provide a few future research directions for knowledge graph embedding.

The goal of relation classification is to recognize the relationship between two marked entities in a sentence. It is a crucial constituent in natural language processing. Up till the present moment, most previous neural network models for this task either focus on using the handcrafted syntactic features or learning semantic representations of raw word sequences, they have no capacity for encoding whole sentence representation including syntax and semantic information. In general, information of syntax and semantics can both have significant effect on classifying relation. Based on this idea, we propose a novel two-channels neural network architecture with attention mechanism in the paper to handle this task. Firstly, we employ bidirectional sequence LSTM channel to capture the semantic information and acquire syntactic knowledge by utilizing tree structure LSTM channel. Secondly, sentence level attention mechanism for word sequences is used to determine which parts of the sentence are most influential component. Eventually, we conduct experiments on two real world datasets: the Wikipedia and the SemEval-2010 Task8 dataset. The experimental results on datasets demonstrate that our method can make better use of the information contained in sentences, and achieve impressive improvements on relation classification as compared with the existing methods.

Pretrained language models, represented by bidirectional encoder representation from Transformer (BERT), show great potential for deep learning (DL)-based intrusion detection systems (IDSs) due to their strong semantic modeling capability. However, the high cost of training and fine-tuning limits their applicability in large-scale and resource-constrained environments. To address this challenge, we propose a split-federated BERT framework with adversarial training for edge intrusion detection. The framework partitions BERT into an embedding layer deployed at the edge and Transformer and head layers hosted in the cloud, enabling collaborative training between edge devices and the cloud. At the edge, a conditional generative adversarial network (CGAN) integrated with BERT enhances traffic feature extraction. Guided by BERT, the generator adapts to local traffic distributions, improving sample coverage and feature representation. Edge devices perform local updates to the embedding layer, while the cloud conducts high-dimensional semantic learning using BERT’s Transformer and head layers. During federated aggregation, a multihead attention mechanism is employed in the cloud to differentially weight model updates, ensuring distributional alignment and stable convergence. This design decouples edge-side adversarial enhancement from federated aggregation, reducing both computational and communication overhead. The experimental results on multiple authoritative datasets demonstrate that the proposed method consistently outperforms local DL, BERT, federated learning (FL), and split learning (SL) baselines in precision, recall, and ${F}1$ -score, while improving edge computational efficiency and communication cost.

Many studies in recent years have focused on social image understanding due to the increasing number of shared images from social networks and online communities. However, previous work in social image understanding fails to learn an effective feature representation because of a large amount of missing and irrelevant tags, though matrix completion techniques are frequently utilized for this purpose. Autoencoder models have been validated to be effective in learning latent low-dimensional representations in unsupervised learning. In this paper, we propose a new social image understanding model based on deep autoencoders, which can learn the shared latent codes of social images and tags as supervision information in the deep autoencoders. First, social images are extracted with multi-modal features, which provides a comprehensive characterization to image semantic understanding. And, the social image understanding problems are transformed into the problem of minimizing an optimization objective. Second, multi-layered autoencoders with weak supervision integration are employed to learn an efficient low-dimensional representation from the multi-view feature sources that can make up the semantic gap between image features and tags through minimizing the problem formulation. Finally, we design a new balanced loss function based on binary cross entropy, in which we address highly sparse inputs for a better optimization performance. Extensive experiments on several real-world social image datasets confirm the effectiveness and robustness of the proposed model compared with the state-of-the-art methods.