The proliferation of social media exacerbates information fragmentation, posing challenges to understanding public events. We address the problem of event reconstruction with a novel Multi-view Contrast Event Reconstruction (MCER) model. MCER maximizes feature dissimilarity between different views of the same event using contrastive learning, while minimizing mutual information between distinct events. This aggregates fragmented views to reconstruct comprehensive event representations. MCER employs momentum and weight-sharing encoders in a three-tower architecture with supervised contrastive loss for multi-view representation learning. Due to the scarcity of multi-view public datasets, we construct a new Mul-view-data benchmark.Experiments demonstrate MCER’s superior performance on public data and our Mul-view-data, significantly outperforming selfsupervised methods by incorporating supervised contrastive techniques. MCER advances multi-view representation learning to counter information fragmentation and enable robust event understanding.

Anomaly detection of time series has been widely used in many practical domains, such as network security, industrial inspection, temperature monitoring. However, because the observed values of time series are disturbed by a large amount of noise to be nonlinear and non-stationary, traditional anomaly detection methods are unable to achieve superior effect. To tackle this problem, considering the influence on the reconstruction of different type time series, we propose an empirical mode decomposition (EMD) plus Attention Variational Auto-Encoder (E-AVAE) model including three parts to realize time series anomaly detection based on self-masked reconstruction error. In the first part, EMD is used to decompose the original time series to obtain Intrinsic Mode Functions (IMFs) and residual function. The second part is to obtain the set of reconstruction error using AVAE model which combines self-attention mechanism, VAE and Long Short-Term Memory (LSTM). Based on density peak clustering, a self-masked reconstruction error iterative clustering algorithm is proposed to detect outliers of abnormal time series in the last part. Experiments on four real time series datasets show that the E-AVAE model has outstanding performance in accuracy and model interpretation.

In recent years, large usage of wireless networks puts forward challenge to the utilization of spectrum resources, and it is significant to improve the spectrum utilization and the system sum data rates in the premise of fairness. However, the existing algorithms have drawbacks in efficiency to maximize the sum data rates of orthogonal frequency division multiple access (OFDMA) systems in the premise of fairness threshold. To address the issue, a novel artificial bee colony algorithm with update quantities of nectar sources is proposed for OFDMA resource allocation in this paper. Firstly, the population of nectar sources is divided into several groups, and a different update quantity of nectar sources is set for each group. Secondly, based on the update quantities of nectar sources set for these groups, nectar sources are initialized by a greedy subcarrier allocation method. Thirdly, neighborhood searches and updates are performed on dimensions of nectar sources corresponding to the preset update quantities. The proposed algorithm can not only make the initialized nectar sources maintain high levels of fairness through the greedy subcarrier allocation but also use the preset update quantities to reduce dimensions of the nectar sources to be optimized by the artificial bee colony algorithm, thereby making full use of both the local optimization of the greedy method and the global optimization of the artificial bee colony algorithm. The simulation results show that, just in the equal‐power subcarrier allocation stage, the proposed algorithm can achieve the required fairness threshold and effectively improve the system sum data rates.

In the field of NLP, most of the existing domain adaptation studies belong to the feature-based adaptation, while the research of instance-based adaptation is very scarce. In this work, we propose a new instance-based adaptation model, called in-target-domain logistic approximation (ILA). In ILA, we adapt the source-domain data to the target domain by a logistic approximation. The normalized in-target-domain probability is assigned as an instance weight to each of the source-domain training data. An instance-weighted classification model is trained finally for the cross-domain classification problem. Compared to the previous techniques, ILA conducts instance adaptation in a dimensionality-reduced linear feature space to ensure efficiency in high-dimensional NLP tasks. The instance weights in ILA are learnt by leveraging the criteria of both maximum likelihood and minimum statistical distance. The empirical results on two NLP tasks including text categorization and sentiment classification show that our ILA model beats the state-of-the-art instance adaptation methods significantly, in cross-domain classification accuracy, parameter stability and computational efficiency.