Foundation models pre-trained on large-scale source datasets are reshaping the traditional training paradigm for time series classification. However, existing time series foundation models primarily focus on forecasting tasks and often overlook classification-specific challenges, such as modeling interpretable shapelets that capture class-discriminative temporal features. To bridge this gap, we propose UniShape, a unified shape-aware foundation model designed for time series classification. UniShape incorporates a shape-aware adapter that adaptively aggregates multiscale discriminative subsequences (shapes) into class tokens, effectively selecting the most relevant subsequence scales to enhance model interpretability. Meanwhile, a prototype-based pretraining module is introduced to jointly learn instance- and shape-level representations, enabling the capture of transferable shape patterns. Pre-trained on a large-scale multi-domain time series dataset comprising 1.89 million samples, UniShape exhibits superior generalization across diverse target domains. Experiments on 128 UCR datasets and 30 additional time series datasets demonstrate that UniShape achieves state-of-the-art classification performance, with interpretability and ablation analyses further validating its effectiveness.

Time-Series (TS) data has grown in importance with the rise of Internet of Things devices like sensors, but its labeling remains costly and complex. While Unsupervised Domain Adaptation (UDAs) offers an effective solution, growing data privacy concerns have led to the development of Source-Free UDA (SFUDAs), enabling model adaptation to target domains without accessing source data. Despite their potential, applying existing SFUDAs to TS data is challenging due to the difficulty of transferring temporal dependencies-an essential characteristic of TS data-particularly in the absence of source samples. Although prior works attempt to address this by specific source pretraining designs, such requirements are often impractical, as source data owners cannot be expected to adhere to particular pretraining schemes. To address this, we propose Temporal Source Recovery (TemSR), a framework that leverages the intrinsic properties of TS data to generate a source-like domain and recover source temporal dependencies. With this domain, TemSR enables dependency transfer to the target domain without accessing source data or relying on source-specific designs, thereby facilitating effective and practical TS-SFUDA. TemSR features a masking-recovery-optimization process to generate a source-like distribution with restored temporal dependencies. This distribution is further refined through local context-aware regularization to preserve local dependencies, and anchor-based recovery diversity maximization to promote distributional diversity. Together, these components enable effective temporal dependency recovery and facilitate transfer across domains using standard UDA techniques. Extensive experiments across seven TS tasks demonstrate the effectiveness of TemSR, which even surpasses existing TS-SFUDA methods that require source-specific designs.

RNA is intricately involved in aberrant cellular functions and a wide range of disease processes, playing pivotal roles in gene regulation, viral replication, and innate immunity. Consequently, it has emerged as a highly promising therapeutic target. To accelerate the discovery of such drugs, it is essential to develop an effective computational method for predicting RNA-small molecule affinity. Therefore, we propose ASRSMA as an atomiclevel structure-aware model with contrastive pre-training for RNA-small molecule binding affinity prediction. ASRSMA represents RNA and small molecules at atomic resolution, enabling the capture of fine-grained structural features. It incorporates an atom-pair encoding module and an inter-molecular interaction module to model intra- and inter-molecular interactions. In addition, a self-supervised contrastive learning strategy is employed during pre-training, maximising the similarity between different views of the same complex while minimising similarities across different complexes, thereby yielding deep representations with strong generalisation capacity. Experimental results demonstrate that ASRSMA significantly outperforms state-of-the-art baseline models in predicting RNA-small molecule binding affinities.

Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained model from an annotated source domain to an unlabelled target domain without accessing the source data, thereby preserving data privacy. While existing SFDA methods have proven effective in reducing reliance on source data, they struggle to perform well on multivariate time series (MTS) due to their failure to consider the intrinsic spatial correlations inherent in MTS data. These spatial correlations are crucial for accurately representing MTS data and preserving invariant information across domains. To address this challenge, we propose Temporal Restoration and Spatial Rewiring (TERSE), a novel and concise SFDA method tailored for MTS data. Specifically, TERSE comprises a customized spatial-temporal feature encoder designed to capture the underlying spatial-temporal characteristics, coupled with both temporal restoration and spatial rewiring tasks to reinstate latent representations of the temporally masked time series and the spatially masked correlated structures. During the target adaptation phase, the target encoder is guided to produce spatially and temporally consistent features with the source domain by leveraging the source pre-trained temporal restoration and spatial rewiring networks. Therefore, TERSE can effectively model and transfer spatial-temporal dependencies across domains, facilitating implicit feature alignment. In addition, as the first approach to simultaneously consider spatial-temporal consistency in MTS-SFDA, TERSE can also be integrated as a versatile plug-and-play module into established SFDA methods. Extensive experiments on three real-world time series datasets demonstrate the effectiveness and versatility of our approach. Our code is available at https://github.com/Tokenmw/TERSE-master.

RNA plays a critical role in cellular processes, and its dysregulation is linked to many diseases, positioning RNA-targeted drugs as an important area of research. Accurate prediction of RNA-small molecule binding sites is crucial for advancing RNA-targeted therapies. Although deep learning has shown promise in this area, challenges remain in integrating and processing multi-dimensional data, such as RNA sequences and structural features, particularly given the inherent flexibility of RNA structures. In this study, we present MVRBind, a multi-view graph convolutional network designed to predict RNA-small molecule binding sites. MVRBind generates feature representations of RNA nucleotides across different structural levels. To effectively integrate these features, we developed a multi-view feature fusion module that constructs graphs based on RNA's primary, secondary, and tertiary structural views, enabling the model to capture diverse aspects of RNA structure. In addition, we fuse embeddings from multi-scale to obtain a comprehensive representation of RNA nucleotides, which is then used to predict RNA-small molecule binding sites. Extensive experiments demonstrate that MVRBind consistently outperforms baseline methods in various experimental settings. Our MVRBind shows exceptional performance in predicting binding sites for both the holo and apo forms of RNA, even when RNA adopts multiple conformations. These results suggest that MVRBind offers a robust model for structure-based RNA analysis, contributing toward accurate prediction and analysis of RNA-small molecule binding sites. All datasets and resource codes are available at https://github.com/cschen-y/MVRBind.

Remaining useful life (RUL) prediction is an essential component for prognostics and health management of a system. Due to the powerful ability of nonlinear modeling, deep learning (DL) models have emerged as leading solutions by capturing temporal dependencies within time series sensory data. However, in RUL prediction tasks, data are typically collected from multiple sensors, introducing spatial dependencies in the form of sensor correlations. Existing methods are limited in effectively modeling and capturing the spatial dependencies, restricting their performance to learn representative features for RUL prediction. To overcome the limitations, we propose a novel LOcal-GlObal correlation fusion-based framework (LOGO). Our approach combines both local and global information to model sensor correlations effectively. From a local perspective, we account for local correlations that represent dynamic changes of sensor relationships in local ranges. Simultaneously, from a global perspective, we capture global correlations that depict relatively stable relations between sensors. An adaptive fusion mechanism is proposed to automatically fuse the correlations from different perspectives. Subsequently, we define sequential micrographs for each sample to effectively capture the fused correlations. Graph neural network (GNN) is introduced to capture the spatial dependencies within each micrograph, and the temporal dependencies between these sequential micrographs are then captured. This approach allows us to effectively model and capture the dependency information within the data for accurate RUL prediction. Extensive experiments have been conducted, verifying the effectiveness of our method.

Multivariate Time-Series (MTS) data is crucial in various application fields. With its sequential and multi-source (multiple sensors) properties, MTS data inherently exhibits Spatial-Temporal (ST) dependencies, involving temporal correlations between timestamps and spatial correlations between sensors in each timestamp. To effectively leverage this information, Graph Neural Network-based methods (GNNs) have been widely adopted. However, existing approaches separately capture spatial dependency and temporal dependency and fail to capture the correlations between Different sEnsors at Different Timestamps (DEDT). Overlooking such correlations hinders the comprehensive modelling of ST dependencies within MTS data, thus restricting existing GNNs from learning effective representations. To address this limitation, we propose a novel method called Fully-Connected Spatial-Temporal Graph Neural Network (FC-STGNN), including two key components namely FC graph construction and FC graph convolution. For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT. Further, we devise FC graph convolution with a moving-pooling GNN layer to effectively capture the ST dependencies for learning effective representations. Extensive experiments show the effectiveness of FC-STGNN on multiple MTS datasets compared to SOTA methods. The code is available at https://github.com/Frank-Wang-oss/FCSTGNN.

Contrastive learning, as a self-supervised learning paradigm, becomes popular for Multivariate Time-Series (MTS) classification. It ensures the consistency across different views of unlabeled samples and then learns effective representations for these samples. Existing contrastive learning methods mainly focus on achieving temporal consistency with temporal augmentation and contrasting techniques, aiming to preserve temporal patterns against perturbations for MTS data. However, they overlook spatial consistency that requires the stability of individual sensors and their correlations. As MTS data typically originate from multiple sensors, ensuring spatial consistency becomes essential for the overall performance of contrastive learning on MTS data. Thus, we propose Graph-Aware Contrasting for spatial consistency across MTS data. Specifically, we propose graph augmentations including node and edge augmentations to preserve the stability of sensors and their correlations, followed by graph contrasting with both node- and graph-level contrasting to extract robust sensor- and global-level features. We further introduce multi-window temporal contrasting to ensure temporal consistency in the data for each sensor. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on various MTS classification tasks. The code is available at https://github.com/Frank-Wang-oss/TS-GAC.

MOTIVATION: RNA is implicated in numerous aberrant cellular functions and disease progressions, highlighting the crucial importance of RNA-targeted drugs. To accelerate the discovery of such drugs, it is essential to develop an effective computational method for predicting RNA-small molecule affinity (RSMA). Recently, deep learning-based computational methods have been promising due to their powerful nonlinear modeling ability. However, the leveraging of advanced deep learning methods to mine the diverse information of RNAs, small molecules, and their interaction still remains a great challenge. RESULTS: In this study, we present DeepRSMA, an innovative cross-attention-based deep learning method for RSMA prediction. To effectively capture fine-grained features from RNA and small molecules, we developed nucleotide-level and atomic-level feature extraction modules for RNA and small molecules, respectively. Additionally, we incorporated both sequence and graph views into these modules to capture features from multiple perspectives. Moreover, a transformer-based cross-fusion module is introduced to learn the general patterns of interactions between RNAs and small molecules. To achieve effective RSMA prediction, we integrated the RNA and small molecule representations from the feature extraction and cross-fusion modules. Our results show that DeepRSMA outperforms baseline methods in multiple test settings. The interpretability analysis and the case study on spinal muscular atrophy demonstrate that DeepRSMA has the potential to guide RNA-targeted drug design. AVAILABILITY AND IMPLEMENTATION: The codes and data are publicly available at https://github.com/Hhhzj-7/DeepRSMA.

Unsupervised Domain Adaptation (UDA) methods have been successful in reducing label dependency by minimizing the domain discrepancy between labeled source domains and unlabeled target domains. However, these methods face challenges when dealing with Multivariate Time-Series (MTS) data. MTS data typically originates from multiple sensors, each with its unique distribution. This property poses difficulties in adapting existing UDA techniques, which mainly focus on aligning global features while overlooking the distribution discrepancies at the sensor level, thus limiting their effectiveness for MTS data. To address this issue, a practical domain adaptation scenario is formulated as Multivariate Time-Series Unsupervised Domain Adaptation (MTS-UDA). In this paper, we propose SEnsor Alignment (SEA) for MTS-UDA, aiming to address domain discrepancy at both local and global sensor levels. At the local sensor level, we design endo-feature alignment, which aligns sensor features and their correlations across domains. To reduce domain discrepancy at the global sensor level, we design exo-feature alignment that enforces restrictions on global sensor features. We further extend SEA to SEA++ by enhancing the endo-feature alignment. Particularly, we incorporate multi-graph-based higher-order alignment for both sensor features and their correlations. Extensive empirical results have demonstrated the state-of-the-art performance of our SEA and SEA++ on six public MTS datasets for MTS-UDA.

Unsupervised Domain Adaptation (UDA) methods can reduce label dependency by mitigating the feature discrepancy between labeled samples in a source domain and unlabeled samples in a similar yet shifted target domain. Though achieving good performance, these methods are inapplicable for Multivariate Time-Series (MTS) data. MTS data are collected from multiple sensors, each of which follows various distributions. However, most UDA methods solely focus on aligning global features but cannot consider the distinct distributions of each sensor. To cope with such concerns, a practical domain adaptation scenario is formulated as Multivariate Time-Series Unsupervised Domain Adaptation (MTS-UDA). In this paper, we propose SEnsor Alignment (SEA) for MTS-UDA to reduce the domain discrepancy at both the local and global sensor levels. At the local sensor level, we design the endo-feature alignment to align sensor features and their correlations across domains, whose information represents the features of each sensor and the interactions between sensors. Further, to reduce domain discrepancy at the global sensor level, we design the exo-feature alignment to enforce restrictions on the global sensor features. Meanwhile, MTS also incorporates the essential spatial-temporal dependencies information between sensors, which cannot be transferred by existing UDA methods. Therefore, we model the spatial-temporal information of MTS with a multi-branch self-attention mechanism for simple and effective transfer across domains. Empirical results demonstrate the state-of-the-art performance of our proposed SEA on two public MTS datasets for MTS-UDA. The code is available at https://github.com/Frank-Wang-oss/SEA

Surface defect is a serious problem in real-world manufacturing system and it is important to use vision-based recognition to ensure the surface quality of products. Currently, due to the ability of automatic feature extraction, deep learning models, such as convolutional neural network (CNN), have been widely used in this area. However, these CNN-based models may not solve a problem well - inter-class similarities and intra-class variations (ISIV), which affect their ability of feature extraction and thus influence their recognition performance. To address this problem, this paper introduces a graph guidance mechanism into CNN to improve the ability of feature extraction, called Graph guided Convolutional Neural Network (GCNN). Firstly, GCNN defines a graph by computing the similarities between training samples. Secondly, the graph is introduced into VGG11, a popular CNN structure, to increase the inter-class distances and decrease the intra-class distances between defect samples. Meanwhile, a learnable coefficient is introduced into the training process to balance the effect of graph guidance automatically. The experimental results on four famous surface defect datasets demonstrate that the graph guidance helps CNN models have better ability of feature extraction and thus achieve better performance. Compared with state-of-the-art models, the proposed method can achieve the best performance. Furthermore, the final discussion shows that the learnable coefficient can help the proposed model to gain better performance, and that the proposed model increases a little computation cost compared to its original CNN model.Note to Practitioners—This paper is motivated by the problem in real-world manufacturing process – inter-class similarities and intra-class variations. Most of current CNN-based models may not solve this problem well, which limits their applications in real-world system. This paper proposes a graph guidance mechanism and introduces it to the training of CNN. The proposal can improve the ability of feature extraction, and thus have better performance than those without the graph guidance. By applying the proposal to four examples, the results show that the proposal is more feasible and effective than the state-of-the-art models in surface defect recognition. Furthermore, the mechanism assists the training of CNN and is removed in the process of recognition, so it will not increase time and occupied memory in recognition, and meanwhile, only limited computation cost is increased in training process.