In recent years, single-domain generalization(SDG) fault diagnosis has become a prominent research focus in intelligent fault diagnosis due to its ability to generalize to previously unseen target domains based solely on a single source domain. The primary aim of domain generalization is to identify the intrinsic invariances underlying diverse data distributions, which have been found to be closely related to causality. While most existing fault diagnosis methods based on causal inference emphasize the invariance of causal features across domains, this study considers a stronger form of stability—namely, the cross domain consistency of features’ causal contributions to fault labels. Accordingly, a novel fault diagnosis method is proposed, which integrates Multi-scale Style Enhancement (MSSE) with Causal Contribution Alignment (CCA) to achieve SDG. First, to make up for the lack of data diversity in the source domain, domain shifts are simulated and diverse pseudo-domain samples are generated using a MSSE module. Second, causal contributions of features to diagnostic labels are quantified through causal attribution. Finally, the alignment of causal contributions of features between source and pseudo domains is enforced through contrastive learning and domain adversarial training, thereby promoting stable and cross domain invariant causal representations. Comprehensive experimental evaluations on two benchmark datasets verify that the proposed method consistently outperforms existing fault diagnosis approaches.

Most deep learning-based time series clustering models concentrate on data representation in a separate process from clustering. This leads to that clustering loss cannot guide feature extraction. Moreover, most methods solely analyze data from the temporal domain, disregarding the potential within the frequency domain. To address these challenges, we introduce a novel end-to-end Cross-Domain Contrastive learning model for time series Clustering (CDCC). Firstly, it integrates the clustering process and feature extraction using contrastive constraints at both cluster-level and instance-level. Secondly, the data is encoded simultaneously in both temporal and frequency domains, leveraging contrastive learning to enhance within-domain representation. Thirdly, cross-domain constraints are proposed to align the latent representations and category distribution across domains. With the above strategies, CDCC not only achieves end-to-end output but also effectively integrates frequency domains. Extensive experiments and visualization analysis are conducted on 40 time series datasets from UCR, demonstrating the superior performance of the proposed model.

Accurately detecting emotions in conversation is a necessary yet challenging task due to the complexity of emotions and dynamics in dialogues. The emotional state of a speaker can be influenced by many different factors, such as interlocutor stimulus, dialogue scene, and topic. In this work, we propose a conversational speech emotion recognition method to deal with capturing attentive contextual dependency and speaker-sensitive interactions. First, we use a pretrained WavLM model to extract frame-based audio representation in individual utterances. Second, an attentive bi-directional gated recurrent unit (GRU) models contextual-sensitive information and explores listener dependency and speaker influence jointly in a simple, fast, parameter-efficient way. The experiments conducted on the standard conversational dataset MELD demonstrate the effectiveness of the proposed method when compared against state-of the-art methods.

Neural Collapse (NC) was a recently discovered phenomenon that the output features and the classifier weights of the neural network converge to optimal geometric structures at the Terminal Phase of Training (TPT) under various losses. However, the relationship between these optimal structures at TPT and the classification performance remains elusive, especially in imbalanced learning. Even though it is noticed that fixing the classifier to an optimal structure can mitigate the minority collapse problem, the performance is still not comparable to the classical imbalanced learning methods with a learnable classifier. In this work, we find that the optimal structure can be designed to represent a better classification rule, and thus achieve better performance. In particular, we justify that, to achieve better classification, the features from the minor classes should align with more directions. This justification then yields a decision rule called the Generalized Classification Rule (GCR) and we also term these directions as the centers of the classes. Then we study the NC under an MSE-type loss via the Unconstrained Features Model (UFM) framework where (1) the features from a class tend to collapse to the mean of the corresponding centers of that class (named Neural Collapse to Multiple Centers (NCMC)) at the global optimum, and (2) the original classifier approximates a surrogate to GCR when NCMC occurs. Based on the analysis, we develop a strategy for determining the number of centers and propose a Cosine Loss function for the fixed classifier that induces NCMC. Our experiments have shown that the Cosine Loss can induce NCMC and has performance on long-tail classification comparable to the classical imbalanced learning methods.

Multimodal emotion recognition (MER) is a fundamental complex research problem due to the uncertainty of human emotional expression and the heterogeneity gap between different modalities. Audio and text modalities are particularly important for a human participant in understanding emotions. Although many successful attempts have been designed multimodal representations for MER, there still exist multiple challenges to be addressed: 1) bridging the heterogeneity gap between multimodal features and model inter- and intramodal interactions of multiple modalities; 2) effectively and efficiently modeling the contextual dynamics in the conversation sequence. In this paper, we propose Cross-Modal RoBERTa (CM-RoBERTa) model for emotion detection from spoken audio and corresponding transcripts. As the core unit of the CM-RoBERTa, parallel self- and cross- attention is designed to dynamically capture inter- and intra-modal interactions of audio and text. Specially, the mid-level fusion and residual module are employed to model longterm contextual dependencies and learn modality-specific patterns. We evaluate the approach on the MELD dataset and the experimental results show the proposed approach achieves the state-of-art performance on the dataset.

Textual emotion recognition in conversations has gained increasing attention in recent years for the growing amount of applications it can serve, e.g., human-robot interactions, recommended systems. However, most existing approaches are either based on BERT-based model which fail to exploit crucial information about the long-text context, or resort to complex entanglement of neural network architectures resulting in less stable training procedures and slower inference time. To bridge this gap, we first propose a fast, compact and parameter-efficient framework based on fine-tuned pre-trained RoBERTa model with a CNN-LSTM network for textual emotion recognition in conversations. First, we fine-tune the pre-tranined RoBERTa model to effectively learn long-term emotion-relevant context information. Second, convolutional neural network coupled with the bidirectional long short-term memory and joint reinforced blocks are utilized to recognize emotion in conversations. Extensive experiments are conducted on benchmark emotion MELD dataset, and the results show that our model outperforms a wide range of strong baselines and achieves competitive results with the state-of-art approaches.