Prototype-based sample-weighted distillation unified framework adapted to missing modality sentiment analysis.

Missing modality sentiment analysis is a prevalent and challenging issue in real life. Furthermore, the heterogeneity of multimodality often leads to an imbalance in optimization when attempting to optimize the same objective across all modalities in multimodal networks. Previous works have consistently overlooked the optimization imbalance of the network in cases when modalities are absent. This paper presents a Prototype-Based Sample-Weighted Distillation Unified Framework Adapted to Missing Modality Sentiment Analysis (PSWD). Specifically, it fuses features with a more efficient transformer-based cross-modal hierarchical cyclic fusion module. Subsequently, we propose two strategies, namely sample-weighted distillation and prototype regularization network, to address the issues of missing modality and optimization imbalance. The sample-weighted distillation strategy assigns higher weights to samples that are located closer to class boundaries. This facilitates the obtaining of complete knowledge by the student network from the teacher's network. The prototype regularization network calculates a balanced metric for each modality, which adaptively adjusts the gradient based on the prototype cross-entropy loss. Unlike conventional approaches, PSWD not only connects the sentiment analysis study in the missing modality to the full modality, but the proposed prototype regularization network is not reliant on the network structure and can be expanded to more multimodal studies. Massive experiments conducted on IEMOCAP and MSP-IMPROV show that our method achieves the best results compared to the latest baseline methods, which demonstrates its value for application in sentiment analysis.

Effective social spider optimization algorithms for distributed assembly permutation flowshop scheduling problem in automobile manufacturing supply chain.

This paper presents a novel distributed assembly permutation flowshop scheduling problem (DAPFSP) based on practical problems in automobile production. Different from the existing research on DAPFSP, this study considers that each component of the final product is composed of more than one part. Components are processed in a set of identical components manufacturing factories and are assembled into products in the assembly factory. The integration of manufacturing processes is an important objective of Industry 4.0. For solving this problem with the minimum makespan criterion, we introduce a three-level representation and a novel initialization method. To enhance the search ability of the proposed algorithms, we design three local search methods and two restart procedures according to characteristics of the problem. Then, by incorporating the problem specific knowledge with the social spider optimization algorithm (SSO), we propose three SSO variants: the SSO with hybrid local search strategies (HSSO), the HSSO with restart procedures (HSSOR), and the HSSOR with self-adaptive selection probability (HSSORP). Finally, 810 extended instances based on the famous instances are used to test the proposed algorithms. In most cases, HSSOR performs the best, with an average comparison metric value of 0.158% across three termination conditions, while the average comparison metric value for the best comparison method is 2.446%, which is 15.481 times that of HSSOR. Numerical results demonstrate that the proposed algorithms can solve the problem efficiently.

Improving long-term multivariate time series forecasting with a seasonal-trend decomposition-based 2-dimensional temporal convolution dense network.

Improving the accuracy of long-term multivariate time series forecasting is important for practical applications. Various Transformer-based solutions emerging for time series forecasting. Recently, some studies have verified that the most Transformer-based methods are outperformed by simple linear models in long-term multivariate time series forecasting. However, these methods have some limitations in exploring complex interdependencies among various subseries in multivariate time series. They also fall short in leveraging the temporal features of the data sequences effectively, such as seasonality and trends. In this study, we propose a novel seasonal-trend decomposition-based 2-dimensional temporal convolution dense network (STL-2DTCDN) to deal with these issues. We incorporate the seasonal-trend decomposition based on loess (STL) to explore the trend and seasonal features of the original data. Particularly, a 2-dimensional temporal convolution dense network (2DTCDN) is designed to capture complex interdependencies among various time series in multivariate time series. To evaluate our approach, we conduct experiments on six datasets. The results demonstrate that STL-2DTCDN outperforms existing methods in long-term multivariate time series forecasting.

Modality attention fusion model with hybrid multi-head self-attention for video understanding.

Video question answering (Video-QA) is a subject undergoing intense study in Artificial Intelligence, which is one of the tasks which can evaluate such AI abilities. In this paper, we propose a Modality Attention Fusion framework with Hybrid Multi-head Self-attention (MAF-HMS). MAF-HMS focuses on the task of answering multiple-choice questions regarding a video-subtitle-QA representation by fusion of attention and self-attention between each modality. We use BERT to extract text features, and use Faster R-CNN to ex-tract visual features to provide a useful input representation for our model to answer questions. In addition, we have constructed a Modality Attention Fusion (MAF) framework for the attention fusion matrix from different modalities (video, subtitles, QA), and use a Hybrid Multi-headed Self-attention (HMS) to further determine the correct answer. Experiments on three separate scene datasets show our overall model outperforms the baseline methods by a large margin. Finally, we conducted extensive ablation studies to verify the various components of the network and demonstrate the effectiveness and advantages of our method over existing methods through question type and required modality experimental results.

A CTR prediction model based on session interest.

Click-through rate prediction has become a hot research direction in the field of advertising. It is important to build an effective CTR prediction model. However, most existing models ignore the factor that the sequence is composed of sessions, and the user behaviors are highly correlated in each session and are not relevant across sessions. In this paper, we focus on user multiple session interest and propose a hierarchical model based on session interest (SIHM) for CTR prediction. First, we divide the user sequential behavior into session layer. Then, we employ a self-attention network obtain an accurate expression of interest for each session. Since different session interest may be related to each other or follow a sequential pattern, next, we utilize bidirectional long short-term memory network (BLSTM) to capture the interaction of different session interests. Finally, the attention mechanism based LSTM (A-LSTM) is used to aggregate their target ad to find the influences of different session interests. Experimental results show that the model performs better than other models.

Session interest model for CTR prediction based on self-attention mechanism.

Click-through rate prediction, which aims to predict the probability of the user clicking on an item, is critical to online advertising. How to capture the user evolving interests from the user behavior sequence is an important issue in CTR prediction. However, most existing models ignore the factor that the sequence is composed of sessions, and user behavior can be divided into different sessions according to the occurring time. The user behaviors are highly correlated in each session and are not relevant across sessions. We propose an effective model for CTR prediction, named Session Interest Model via Self-Attention (SISA). First, we divide the user sequential behavior into session layer. A self-attention mechanism with bias coding is used to model each session. Since different session interest may be related to each other or follow a sequential pattern, next, we utilize gated recurrent unit (GRU) to capture the interaction and evolution of user different historical session interests in session interest extractor module. Then, we use the local activation and GRU to aggregate their target ad to form the final representation of the behavior sequence in session interest interacting module. Experimental results show that the SISA model performs better than other models.

Prediction of SO2 Concentration Based on AR-LSTM Neural Network.

Sulphur dioxide is one of the most common air pollutants, forming acid rain and other harmful substances in the atmosphere, which can further damage our ecosystem and cause respiratory diseases in humans. Therefore, it is essential to monitor the concentration of sulphur dioxide produced in industrial processes in real-time to predict the concentration of sulphur dioxide emissions in the next few hours or days and to control them in advance. To address this problem, we propose an AR-LSTM analytical forecasting model based on ARIMA and LSTM. Based on the sensor's time series data set, we preprocess the data set and then carry out the modeling and analysis work. We analyze and predict the proposed analysis and prediction model in two data sets and conduct comparative experiments with other comparison models based on the three evaluation indicators of R2, RMSE and MAE. The results demonstrated the effectiveness of the AR-LSTM analytical prediction model; Finally, a forecasting exercise was carried out for emissions in the coming weeks using our proposed AR-LSTM analytical forecasting model.

Recommendation system in social networks with topical attention and probabilistic matrix factorization.

Collaborative filtering (CF) is a common recommendation mechanism that relies on user-item ratings. However, the intrinsic sparsity of user-item rating data can be problematic in many domains and settings, limiting the ability to generate accurate predictions and effective recommendations. At present, most algorithms use two-valued trust relationship of social network to improve recommendation quality but fail to take into account the difference of trust intensity of each friend and user's comment information. To this end, the recommendation system within a social network adopts topical attention and probabilistic matrix factorization (STAPMF) is proposed. We combine the trust information in social networks and the topical information from review documents by proposing a novel algorithm combining probabilistic matrix factorization and attention-based recurrent neural networks to extract item underlying feature vectors, user's personal potential feature vectors, and user's social hidden feature vectors, which represent the features extracted from the user's trusted network. Using real-world datasets, we show a significant improvement in recommendation performance comparing with the prevailing state-of-the-art algorithms for social network-based recommendation.

TSSCM: A synergism-based three-step cascade model for influence maximization on large-scale social networks.

Identification of the most influential spreaders that maximize information propagation in social networks is a classic optimization problem, called the influence maximization (IM) problem. A reasonable diffusion model that can accurately simulate information propagation in social networks is the key step to efficiently solving the IM problem. Synergism of neighbor nodes plays an important role in information propagation dynamics. Some known diffusion models have considered the reinforcement mechanism in defining the activation threshold. Most of these models focus on the synergetic effects of nodes on their common neighbors, but the accumulation of synergism has been neglected in previous studies. Inspired by these facts, we first discuss the catalytic role of synergism in the spreading dynamics of social networks and then propose a novel diffusion model called the synergism-based three-step cascade model (TSSCM) based on the above analysis and the three-degree influence theory. Finally, we devise an algorithm for solving the IM problem based on the TSSCM. Experiments on five real large-scale social networks demonstrate the efficacy of our method, which achieves competitive results in terms of influence spreading compared to the four other algorithms tested.

A New Approach for Advertising CTR Prediction Based on Deep Neural Network via Attention Mechanism.

Click-through rate prediction is critical in Internet advertising and affects web publisher's profits and advertiser's payment. The traditional method of obtaining features using feature extraction did not consider the sparseness of advertising data and the highly nonlinear association between features. To reduce the sparseness of data and to mine the hidden features in advertising data, a method that learns the sparse features is proposed. Our method exploits dimension reduction based on decomposition, takes advantage of the attention mechanism in neural network modelling, and improves FM to make feature interactions contribute differently to the prediction. We utilize stack autoencoder to explore high-order feature interactions and use improved FM for low-order feature interactions to portray the nonlinear associated relationship of features. The experiment shows that our method improves the effect of CTR prediction and produces economic benefits in Internet advertising.