In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled with advancements in Deep Learning (DL), this opens up countless possibilities for meaningful applications, e.g., for medical purposes and in vehicular networks. Traditional cloud-based Machine Learning (ML) approaches require the data to be centralized in a cloud server or data center. However, this results in critical issues related to unacceptable latency and communication inefficiency. To this end, Mobile Edge Computing (MEC) has been proposed to bring intelligence closer to the edge, where data is produced. However, conventional enabling technologies for ML at mobile edge networks still require personal data to be shared with external parties, e.g., edge servers. Recently, in light of increasingly stringent data privacy legislations and growing privacy concerns, the concept of Federated Learning (FL) has been introduced. In FL, end devices use their local data to train an ML model required by the server. The end devices then send the model updates rather than raw data to the server for aggregation. FL can serve as an enabling technology in mobile edge networks since it enables the collaborative training of an ML model and also enables DL for mobile edge network optimization. However, in a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved. This raises challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale. In this survey, we begin with an introduction to the background and fundamentals of FL. Then, we highlight the aforementioned challenges of FL implementation and review existing solutions. Furthermore, we present the applications of FL for mobile edge network optimization. Finally, we discuss the important challenges and future research directions in FL.

Electroencephalography (EEG) measures the neuronal activities in different brain regions via electrodes. Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels. In this paper, we propose a regularized graph neural network (RGNN) for EEG-based emotion recognition. RGNN considers the biological topology among different brain regions to capture both local and global relations among different EEG channels. Specifically, we model the inter-channel relations in EEG signals via an adjacency matrix in a graph neural network where the connection and sparseness of the adjacency matrix are inspired by neuroscience theories of human brain organization. In addition, we propose two regularizers, namely node-wise domain adversarial training (NodeDAT) and emotion-aware distribution learning (EmotionDL), to better handle cross-subject EEG variations and noisy labels, respectively. Extensive experiments on two public datasets, SEED and SEED-IV, demonstrate the superior performance of our model than state-of-the-art models in most experimental settings. Moreover, ablation studies show that the proposed adjacency matrix and two regularizers contribute consistent and significant gain to the performance of our RGNN model. Finally, investigations on the neuronal activities reveal important brain regions and inter-channel relations for EEG-based emotion recognition.

With the increasing demand for intelligent services, the sixth-generation (6G) wireless networks will shift from a traditional architecture that focuses solely on a high transmission rate to a new architecture that is based on the intelligent connection of everything. Semantic communication (SemCom), a revolutionary architecture that integrates user as well as application requirements and the meaning of information into data processing and transmission, is predicted to become a new core paradigm in 6G. While SemCom is expected to progress beyond the classical Shannon paradigm, several obstacles need to be overcome on the way to a SemCom-enabled smart Internet. In this paper, we first highlight the motivations and compelling reasons for SemCom in 6G. Then, we provide an overview of SemCom-related theory development. After that, we introduce three types of SemCom, i.e., semantic-oriented communication, goal-oriented communication, and semantic-aware communication. Following that, we organize the design of the communication system into three dimensions, i.e., semantic information (SI) extraction, SI transmission, and SI metrics. For each dimension, we review existing techniques and discuss their benefits and limitations, as well as the remaining challenges. Then, we introduce the potential applications of SemCom in 6G and portray the vision of future SemCom-empowered network architecture. Finally, we outline future research opportunities. In a nutshell, this paper provides a holistic review of the fundamentals of SemCom, its applications in 6G networks, and the existing challenges and open issues with insights for further in-depth investigations.

Dubbed “the successor to the mobile Internet”, the concept of the Metaverse has grown in popularity. While there exist lite versions of the Metaverse today, they are still far from realizing the full vision of an immersive, embodied, and interoperable Metaverse. Without addressing the issues of implementation from the communication and networking, as well as computation perspectives, the Metaverse is difficult to succeed the Internet, especially in terms of its accessibility to billions of users today. In this survey, we focus on the edge-enabled Metaverse to realize its ultimate vision. We first provide readers with a succinct tutorial of the Metaverse, an introduction to the architecture, as well as current developments. To enable ubiquitous, seamless, and embodied access to the Metaverse, we discuss the communication and networking challenges and survey cutting-edge solutions and concepts that leverage next-generation communication systems for users to immerse as and interact with embodied avatars in the Metaverse. Moreover, given the high computation costs required, e.g., to render 3D virtual worlds and run data-hungry artificial intelligence-driven avatars, we discuss the computation challenges and cloud-edge-end computation framework-driven solutions to realize the Metaverse on resource-constrained edge devices. Next, we explore how blockchain technologies can aid in the interoperable development of the Metaverse, not just in terms of empowering the economic circulation of virtual user generated content but also to manage physical edge resources in a decentralized, transparent, and immutable manner. Finally, we discuss the future research directions towards realizing the true vision of the edge-enabled Metaverse.

Most machine-learning methods focus on classifying instances whose classes have already been seen in training. In practice, many applications require classifying instances whose classes have not been seen previously. Zero-shot learning is a powerful and promising learning paradigm, in which the classes covered by training instances and the classes we aim to classify are disjoint. In this paper, we provide a comprehensive survey of zero-shot learning. First of all, we provide an overview of zero-shot learning. According to the data utilized in model optimization, we classify zero-shot learning into three learning settings. Second, we describe different semantic spaces adopted in existing zero-shot learning works. Third, we categorize existing zero-shot learning methods and introduce representative methods under each category. Fourth, we discuss different applications of zero-shot learning. Finally, we highlight promising future research directions of zero-shot learning.

In pharmaceutical sciences, a crucial step of the drug discovery process is the identification of drug-target interactions. However, only a small portion of the drug-target interactions have been experimentally validated, as the experimental validation is laborious and costly. To improve the drug discovery efficiency, there is a great need for the development of accurate computational approaches that can predict potential drug-target interactions to direct the experimental verification. In this paper, we propose a novel drug-target interaction prediction algorithm, namely neighborhood regularized logistic matrix factorization (NRLMF). Specifically, the proposed NRLMF method focuses on modeling the probability that a drug would interact with a target by logistic matrix factorization, where the properties of drugs and targets are represented by drug-specific and target-specific latent vectors, respectively. Moreover, NRLMF assigns higher importance levels to positive observations (i.e., the observed interacting drug-target pairs) than negative observations (i.e., the unknown pairs). Because the positive observations are already experimentally verified, they are usually more trustworthy. Furthermore, the local structure of the drug-target interaction data has also been exploited via neighborhood regularization to achieve better prediction accuracy. We conducted extensive experiments over four benchmark datasets, and NRLMF demonstrated its effectiveness compared with five state-of-the-art approaches. This work introduces a computational approach, namely neighborhood regularized logistic matrix factorization (NRLMF), to predicting potential interactions between drugs and targets. The novelty of NRLMF lies in integrating logistic matrix factorization with neighborhood regularization for drug-target interaction prediction. In NRLMF, we model the interaction probability for each drug-target pair using logistic matrix factorization. As the observed interacting drug-target pairs are experimentally verified, they are more trustworthy than the unknown pairs. We propose to assign higher importance levels to interaction pairs and lower importance levels to unknown pairs. In addition, we further improve the prediction accuracy by neighborhood regularization, which considers the neighborhood influences from most similar drugs and most similar targets. To evaluate the performance of NRLMF, we conducted extensive experiments on four benchmark datasets. The experimental results demonstrated that NRLMF usually outperformed five state-of-the-art methods under three different cross-validation settings, in terms of the area under the ROC curve (AUC) and the area under the precision-recall curve (AUPR). In addition, we confirmed the practical prediction ability of NRLMF by mapping with the latest version of four online biological databases, including ChEMBL, DrugBank, KEGG, and Matador.