Search

Multimodal sentiment analysis aims to extract sentiment cues from various modalities, such as textual, acoustic, and visual data, and manipulate them to determine the inherent sentiment polarity in the data. Despite significant achievements in multimodal sentiment analysis, challenges persist in addressing noise features in modal representations, eliminating substantial gaps in sentiment information among modal representations, and exploring contextual information that expresses different sentiments between modalities. To tackle these challenges, our paper proposes a new Multimodal Sentiment Analysis (MSA) framework. Firstly, we introduce the Hierarchical Denoising Representation Disentanglement module (HDRD), which employs hierarchical disentanglement techniques. This ensures the extraction of both common and private sentiment information while eliminating interference noise from modal representations. Furthermore, to address the uneven distribution of sentiment information among modalities, our Inter-Modal Representation Enhancement module (IMRE) enhances non-textual representations by extracting sentiment information related to non-textual representations from textual representations. Next, we introduce a new interaction mechanism, the Dual-Channel Cross-Modal Context Interaction module (DCCMCI). This module not only mines correlated contextual sentiment information within modalities but also explores positive and negative correlation contextual sentiment information between modalities. We conducted extensive experiments on two benchmark datasets, MOSI and MOSEI, and the results indicate that our proposed method offers state-of-the-art approaches. • Multimodal sentiment analysis framework using hierarchical denoising representation disentanglement. • Hierarchical Denoising Representation Disentanglement (HDRD) Module to generate noise-free modal representations. • Dual-channel Cross-modal-context Interaction (DCCMCI) Module for intra-modal and inter-modal contextual interaction. [ABSTRACT FROM AUTHOR]

Class imbalance problems pose significant challenges in the field of data mining. The skewed distribution of classes in imbalanced datasets often leads conventional classification methods to neglect the importance of minority classes, favoring the majority ones. In this paper, we propose an imbalanced complemented subspace representation model with adaptive weight learning to address imbalanced classification challenges. This approach incorporates a novel regularization technique and an adaptive weighting mechanism. The regularization technique integrates a complemented subspace term based on space theory into the efficient collaborative representation-based classification (CRC) framework, enhancing the overall accuracy of existing CRC-based methods. Furthermore, it takes into account both intra-class and inter-class density information to assign greater weights to minority classes. This highlights the contribution of minority classes and mitigates bias towards majority classes. Additionally, it is demonstrated that the proposed model can be efficiently solved with a closed-form solution. Extensive experiments conducted on diverse imbalanced datasets showcase the superiority of our method over most state-of-the-art imbalanced classification algorithms. • A complemented subspace regularization term is introduced into CRC. • An adaptive weight learning strategy is present. • The closed-form solution is provided to ensure the efficiency of our model. • Experimental results show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Anomaly detection in time series data is crucial for many fields such as healthcare, meteorology, and industrial fault detection. However, traditional unsupervised time series anomaly detection methods suffer from biased anomaly measurement under contaminated training data. Most of existing methods employ hard strategies for contamination calibration by assigning pseudo-label to training data. These hard strategies rely on threshold selection and result in suboptimal performance. To address this problem, in this paper, we propose a novel unsupervised anomaly detection framework for contaminated time series (NegCo), which builds an effective soft contamination calibration strategy by exploiting the observed negative correlation between semantic representation and anomaly detection inherent within the autoencoder framework. We innovatively redefine anomaly detection in data contamination scenarios as an optimization problem rooted in this negative correlation. To model this negative correlation, we introduce a dual construct: morphological similarity captures semantic distinctions relevant to normality, while reconstruction consistency quantifies deviations indicative of anomalies. Firstly, the morphological similarity is effectively measured based on the representative normal samples generated from the center of the learned Gaussian distribution. Then, an anomaly measurement calibration loss function is designed based on negative correlation between morphological similarity and reconstruction consistency, to calibrate the biased anomaly measurement caused by contaminated samples. Extensive experiments on various time series datasets show that the proposed NegCo outperforms state-of-the-art baselines, achieving an improvement of 6.2% to 26.8% in A rea U nder the R eceiver O perating C haracteristics (AUROC) scores, particularly in scenarios with heavily contaminated training data. • Unsupervised time series anomaly detection under data contamination. • Calibrating the biased anomaly measurement by exploiting the negative correlation. • Normal samples from a learned Gaussian distribution to model negative correlation. • Single forward propagation enables anomaly detection using the trained autoencoder. [ABSTRACT FROM AUTHOR]

Session-based recommendations (SBR) aim to predict the user's next choice of items based on historical data. It is hard to access the interaction information between users and we can only analyze the user's behavioral preferences based on the current session characteristics, which makes the recommendation task in this field quite challenging. Recently, considerable research has grown up around the theme of SBR. Previous works apply attention mechanisms and Graph Neural Networks (GNN) to achieve remarkable results. However, these methods ignore two main points: one is losing sight of the specific position of items in the session; the other is to drive global preference with local preference without considering the offset of the target preference among items in the session. This paper proposes a Global Target Preference Attention Network (GTPAN) Model with position information for the session-based recommendation. We introduce a position-aware embedding module to eliminate the effect of position missing. Considering that each item in the session is potentially rich in latent information of target preference, we use a target preference attention layer to learn the target preference vector of the session. Extensive experiments on three real datasets show that the proposed GTPAN model outperforms state-of-the-art session-based recommendation methods, especially on datasets with long sessions. [ABSTRACT FROM AUTHOR]