ABSTRACT Recently, Multi‐label learning has emerged as a crucial technique across various fields. However, it typically requires a large amount of labelled data for effective model training. To address this limitation, many researchers have introduced the label propagation (LP) algorithm from semi‐supervised learning into multi‐label learning. Unfortunately, conventional LP approaches only transform multi‐label problem into single‐label formulations, thereby ignoring label correlations. This paper proposes a new LP algorithm integrating fuzzy C‐means (FCM) and sorting empowerment for multi‐label learning, termed C lustering‐based S orting Empowerment L abel P ropagation (CSLP). Firstly, FCM is employed to strengthen the relationship among labels, ensuring that the probability results of the LP algorithm in multi‐label scenarios are more consistent with actual data distributions. Afterward, sorting empowerment, inspired by group decision theory, is adopted as an ensemble strategy to enhance the robustness of the LP algorithm. Finally, extensive experiments on seven multi‐label datasets demonstrate that CSLP outperforms competing algorithms across four evaluation metrics (Hamming loss, Average precision, Recall score, and MicroF1).

With the development of intelligent technology, data exhibits characteristics of multi-label and imbalanced distribution, which lead to the degradation of classification model performance. Therefore, addressing multi-label class imbalance has become a hot research topic. Nowadays, over-sampling approaches aim to generate a superset of the original dataset to deal with imbalanced data. However, traditional over-sampling methods only employ the central data point and its nearest neighbor samples to synthesize samples without considering the impact of data distribution. To address these issues, in this paper, we propose an ensemble multi-label over-sampling algorithm (MLCIO) based on Chebyshev inequality and a group optimization strategy. Firstly, to generate more representative and diverse samples, with the seed sample serving as the sphere’s center, Chebyshev inequality is utilized to ensure that synthetic samples fall within its m times the standard deviation. Secondly, a group optimization ranking weighting approach is employed to obtain more reliable and stable label information. Finally, comparative experiments are conducted on 11 imbalanced datasets from various domains using different evaluation metrics. The results demonstrate that our proposal achieves better performance than other approaches.

Few-shot learning (FSL) is a challenging task in classifying new classes from few labelled examples. Many existing models embed class structural knowledge as prior knowledge to enhance FSL against data scarcity. However, they fall short of connecting the class structural knowledge with the limited visual information which plays a decisive role in FSL model performance. In this paper, we propose a unified FSL framework with multi-granularity knowledge fusion and decision-making (MGKFD) to overcome the limitation. We aim to simultaneously explore the visual information and structural knowledge, working in a mutual way to enhance FSL. On the one hand, we strongly connect global and local visual information with multigranularity class knowledge to explore intra-image and inter-class relationships, generating specific multi-granularity class representations with limited images. On the other hand, a weight fusion strategy is introduced to integrate multi-granularity knowledge and visual information to make the classification decision of FSL. It enables models to learn more effectively from limited labelled examples and allows generalization to new classes. Moreover, considering varying erroneous predictions, a hierarchical loss is established by structural knowledge to minimize the classification loss, where greater degree of misclassification is penalized more. Experimental results on three benchmark datasets show the advantages of MGKFD over several advanced models.

Mobile edge computing (MEC) is viewed as a promising technology to address the challenges of intensive computing demands in hotspots (HSs). In this paper, we consider a unmanned aerial vehicle (UAV)-assisted backscattering MEC system. The UAVs can fly from parking aprons to HSs, providing energy to HSs via RF beamforming and collecting data from wireless users in HSs through backscattering. We aim to maximize the long-term utility of all HSs, subject to the stability of the HSs' energy queues. This problem is a joint optimization of the data offloading decision and contract design that should be adaptive to the users' random task demands and the time-varying wireless channel conditions. A deep reinforcement learning based contract incentive (DRLCI) strategy is proposed to solve this problem in two steps. Firstly, we use deep Q-network (DQN) algorithm to update the HSs' offloading decisions according to the changing network environment. Secondly, to motivate the UAVs to participate in resource sharing, a contract specific to each type of UAVs has been designed, utilizing Lagrangian multiplier method to approach the optimal contract. Simulation results show the feasibility and efficiency of the proposed strategy, demonstrating a better performance than the natural DQN and Double-DQN algorithms.

In this paper, we consider a mobile edge computing (MEC) system with multiple unmanned aerial vehicles (UAVs) and stochastic energy harvesting. The UAVs' mobility can help data offloading over a larger geographical area containing multi- hotspots (HSs). If HSs have offloading requests, the dispatch agent (DA) can recruit different types of UAVs to fly close to HSs and help computation. We aim to maximize the long-term utility of all HSs, subject to the stability of energy queue. The proposed problem is a joint optimization problem of offloading strategy and contract design in a dynamic setting over time. We design a deep reinforcement learning based contract incentive (DRLCI) strategy that solves the joint optimization problem in two steps. Firstly, we use an improved deep Q-network (DQN) algorithm to obtain the offloading decision. Secondly, to motivate UAVs to participate in resources sharing, a contract has been designed for asymmetric information scenarios, and Lagrangian multiplier method has been utilized to approach the optimal contract. Simulation results show the feasibility and efficiency of the proposed strategy. It can achieve a very close-to the performance obtained by complete information scenario.

Existing machine learning methods for classification and recognition of EEG motor imagery usually suffer from reduced accuracy for limited training data. To address this problem, this paper proposes a multi-rhythm capsule network (FBCapsNet) that uses as little EEG information as possible with key features to classify motor imagery and further improves the classification efficiency. The network conforms to a small recognition model with only 3 acquisition channels but it can effectively use the limited data for feature learning. Based on the BCI Competition IV 2b data set, experimental results show that the proposed network can achieve 2.41% better performance than existing cutting-edge methods.

Here, the authors study the novel problem of optimising access point (AP) association by maximising the network throughput, subject to the degree bound of AP. The formulated problem is a combinatorial optimisation. They resort to the Markov Chain approximation technique to design a distributed algorithm. They first approximate their optimal objective via Log‐Sum‐Exp function. Thereafter, they construct a special class of Markov Chain with steady‐state distribution specify to their problem to yield a distributed solution. Furthermore, they extend the static problem setting to a dynamic environment where the users can randomly leave or join the system. Their proposed algorithm has provable performance, achieving an approximation gap of . It is simple and can be implemented in a distributed manner. Their extensive simulation results show that the proposed algorithm can converge very fast, and achieve a close‐to‐optimal performance with a guaranteed loss bound.

Classification is one of the most important problems in data mining and machine learning. The quality and quantity of classification rules are two factors to influence the accuracy of classification. In this paper, we propose a new algorithm to enhance the final classification accuracy, called CMCM (Classification based on Multiple Classifier Models), which consists of two classification models. Model1 centers on the improvement of quality. The optimal attribute values are obtained as the first item of a classification rule from both the items and their complements. While in Model2, quantity is taken into consideration, so it constructs two candidate sets and uses the one-versus-many strategy to generate several rules at one time. The experiment results demonstrate that CMCM can achieve higher classification accuracy than the proposed classification approaches. CMCM can extract sufficient high-quality rules for imbalanced data. Meanwhile, it can also obtain sufficient latent information for classification.