Unsupervised time series representation learning, driven by recent advances in contrastive learning-based methods, has become a critical component for downstream tasks like forecasting and classification. However, time series data exhibit complex temporal dependencies and spectral patterns, posing challenges for existing approaches to adapt robustly. Moreover, existing contrastive learning-based approaches overlook frequency-domain information and struggle with selecting effective negative samples, further hindering model performance. To address these issues, we propose S a URL-TS, a novel self-adaptive framework for unsupervised time series representation learning. First, it dynamically learns dataset-specific augmentations to generate high-quality positive samples. Second, an adaptive self-supervised learning module with a multi-domain encoder captures both temporal and spectral patterns without relying on negative samples. Third, a representation-wise attention mechanism assigns dynamic weights to representations across domains. To the best of our knowledge, S a URL-TS is the first self-supervised learning framework to jointly model temporal and spectral patterns across both augmentation and learning stages. Extensive experiments confirm the superior performance of S a URL-TS over state-of-the-art models. Notably, its adaptive data augmentation module is plug-and-play and can be integrated into other contrastive learning frameworks, and its learning stage is capable of adapting to a wide range of time series patterns. Our codebase is available at https://github.com/YusenL/SAURL-TS .

Knowledge-based Visual Question Answering (KB-VQA) extends general Visual Question Answering by requiring external knowledge beyond the provided visual and textual inputs, facilitating more complex real-world applications. KB-VQA introduces unique challenges, including the alignment of heterogeneous information from diverse modalities and sources, the retrieval of relevant knowledge from large-scale and noisy repositories, and the execution of complex reasoning to infer answers from the combined context. With the advancement of large language models, KB-VQA systems have undergone a notable transformation, where LLMs serve as powerful knowledge repositories, retrieval-augmented generators and strong reasoners. Despite substantial progress, there is a lack of a recent, systematic survey that organizes and reviews the evolving landscape of existing KB-VQA methods. This survey aims to fill this gap by establishing a structured taxonomy of KB-VQA approaches and decomposing mainstream systems into three fundamental stages: knowledge representation, knowledge retrieval, and knowledge reasoning. Through an examination of existing techniques employed at each stage, this survey identifies persistent challenges and outlines promising future research directions, providing a foundation for advancing KB-VQA models and their applications.

The goal of Personalized Federated Learning (PFL) achieves model personalization on statistical heterogeneous scenarios. Existing PFL approaches roughly treat the entire model parameters as a whole unit for generating personalized weights, and neglect the latent correlations among parameters of different client models, which is crucial for model personalization by the same learning tasks on statistical heterogeneity. To solve this issue, we propose a graph-guided aggregation framework for layer-wised PFL, namely FedHigh. The framework leverages layered knowledge sharing of client models to generate latent correlation graphs in the hyperbolic space. The latent correlation graphs can efficiently guide the personalized aggregation. Experimental results demonstrate that FedHigh achieves significant accuracy improvements up to 42.6%, 33.1%, and 7.5% on graph, computer vision (CV), and natural language processing (NLP) datasets, respectively. Meanwhile, FedHigh accelerates convergence speed up to 52.6% compared to state-of-the-art baselines on CV datasets. Additionally, the scalability of FedHigh also attractively outperforms other baselines with different world sizes.

Heterogeneous Federated Learning (HtFL) enables collaborative learning across clients with diverse model architectures and non-IID data distributions, which are prevalent in real-world edge computing applications. Existing HtFL approaches typically employ proxy datasets to facilitate knowledge sharing or implement coarse-grained model-level knowledge transfer. However, such approaches not only elevate risks of user privacy leakage but also lead to the loss of fine-grained model-specific knowledge, ultimately creating barriers to effective knowledge sharing. To address these challenges, we propose FedFree, a novel data-free and model-free HtFL framework featuring two key innovations. First, FedFree introduces a reverse layer-wise knowledge transfer mechanism that aggregates heterogeneous client models into a global model solely using Gaussian-based pseudo data, eliminating reliance on proxy datasets. Second, it leverages Knowledge Gain Entropy (KGE) to guide targeted layer-wise knowledge alignment, ensuring that each client receives the most relevant global updates tailored to its specific architecture. We provide rigorous theoretical convergence guarantees for FedFree and conduct extensive experiments on CIFAR-10 and CIFAR-100. Results demonstrate that FedFree achieves substantial performance gains, with relative accuracy improving up to 46.3% over state-of-the-art baselines. The framework consistently excels under highly heterogeneous model/data distributions and in large scale settings.

Knowledge graphs (KGs) consist of well-organized external information and have been proven to enhance recommendation quality effectively. Most KG-aware recommender systems are developed using real number space embeddings. In recent years, learning representations in the hypercomplex space has gained success and attention. Compared to single-component real-valued vectors, multi-component hypercomplex embeddings offer greater expressiveness, facilitating more meaningful modeling of users, items, entities, and their relations in the user-item interaction graph and KG. In this paper, we explore the integration of hypercomplex algebras in KG-aware recommendation and propose a Hypercomplex Knowledge Graph-aware Recommender (HKGR) method. Our HKGR models the interaction graph and KG in the hypercomplex space by utilizing specially designed hypercomplex graph neural networks. In particular, HKGR employs a hypercomplex attention-based aggregator to capture the structure and semantics of the KG. In the recommendation prediction phase, we design a hypercomplex interaction network that can approximate the high-order component interactions between users and items. Furthermore, we introduce a hypercomplex contrastive learning operator to strengthen cooperative signals between the interaction graph and KG modelings. Experiment results on the four real-world datasets show that our HKGR outperforms the state-of-the-art recommender baselines.

Accurate detection and subsequent cleanup of floating waste are critical for ecosystem protection. However, existing methods face significant challenges in dealing with unpredictable weather, limiting their generalization capabilities. This paper proposes a novel plug-and-play architecture called Image Enhancer with Spatial Search and Aggregation (SpatialIE) . This architecture includes a novel encoder block (KANsformer) based on KANs and a dynamic decoder module leveraging prompt-based learning. The KANsformer in the encoder enhances the model’s ability to learn complex non-linear relationships in degraded images . At the same time, the Multi-Order-Based Prompt Block in the decoder enables dynamic optimization of feature processing strategies. These components allow SpatialIE to refine detection strategies to accommodate unknown weather conditions adaptively. We integrate SpatialIE with common YOLO detectors in an end-to-end training framework using the FloW-img and Water Surface Object Detection Dataset (WSODD) datasets. Experimental results show that our method delivers outstanding performance across multiple and single degradation scenarios, achieving an optimal balance between detection accuracy and storage efficiency.

In social networks, echo chambers form when users primarily encounter information that reinforces their existing views with limited exposure to different perspectives. This self-reinforcing isolation worsens societal issues such as division and declining public discourse. Traditional approaches attempt to mitigate echo chambers by analyzing observable interaction patterns to identify their formative mechanisms. However, they overlook unobserved implicit factors, called hidden confounders in causal inference, that significantly influence content exposure and user behaviors despite not being directly captured in the data. To address this, we propose Causal Echo Diffusion Attenuator (CEDA) , a novel framework that integrates causal learning with sequential recommendations to detect and adjust for hidden confounders in social networks. Generally, CEDA comprises four key components: (1) User Dual Modelling builds comprehensive user embeddings by combining users’ attributes and structural information to fully capture behavior patterns. (2) Causal Transformer then estimates residual embeddings that account for hidden confounders, incorporating them into the Transformer as causal adjustments for unbiased user embeddings. (3) Social Diffusion Predictor uses unbiased user embeddings to jointly optimize diffusion prediction accuracy and information diversity. (4) Targeted Interventions strategically reshapes information flows to disrupt echo chambers based on the generated prediction and diversity insights. Extensive experiments demonstrate CEDA’s superior performance in both predicting information diffusion patterns and mitigating echo chambers.

Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method is particularly pertinent when entities possess datasets with identical sample identifiers but diverse attributes. Recent privacy regulations emphasize an individual'sright to be forgotten, which necessitates the ability for models to unlearn specific training data. The primary challenge is to develop a mechanism to eliminate the influence of a specific client from a model without erasing all relevant data from other clients. Our research investigates the removal of a single client's contribution within the VFL framework. We introduce an innovative modification to traditional VFL by employing a mechanism that inverts the typical learning trajectory with the objective of extracting specific data contributions. This approach seeks to optimize model performance using gradient ascent, guided by a pre-defined constrained model. We also introduce a backdoor mechanism to verify the effectiveness of the unlearning procedure. Our method avoids fully accessing the initial training data and avoids storing parameter updates. Empirical evidence shows that the results align closely with those achieved by retraining from scratch. Utilizing gradient ascent, our unlearning approach addresses key challenges in VFL, laying the groundwork for future advancements in this domain.

Recently, there has been a surge in recommendations based on heterogeneous information networks (HINs), attributed to their ability to integrate complex and rich semantics. Despite this advancement, most HIN-based recommenders overlook two critical aspects. First, they often fail to consider HIN's heterophily nature, hindering the capture of non-local structures in HINs. Second, most methods lack the capability for logical reasoning. In this paper, we propose a novel structure- and logic-aware heterogeneous graph learning framework for recommender systems (SLHRec). Our SLHRec contains a structure-aware module and a logic-aware module. The former uses network geometry to construct non-local neighborhoods for nodes in HINs, and then introduces a graph neural network to integrate constructed neighbors for modeling the heterophily of HINs. The logic-aware module uses the Markov logic network (MLN) to infuse logic rules into heterogeneous graph learning, thereby boosting logic reasoning in recommendations. Furthermore, we utilize contrastive learning to model cooperative signals between modules, enabling them to complement each other. In the prediction stage, both modules contribute to generating recommendations. Compared with several strong recommender baselines, our SLHRec achieves superior performance on four real-world datasets.

Human action recognition has been explored in healthcare, sports, and entertainment, with a recent shift toward manufacturing settings for monitoring assembly tasks. Identifying assembly actions is crucial for improving human-robot collaboration and optimizing the assembly process. However, the complexity of assembly tasks poses challenges for action recognition methods, with single-modality methods struggling to capture the complex dynamics and context. We proposed the multimodal ConvLSTM-AssNet and C3D-AssNet methods, which use RGB, RGB-A, and depth data. The models are tested in single, double, and triple stream configurations, with attention mechanisms integrated to focus on relevant features. The proposed models are evaluated on the HA4M dataset. Attention-Guided C3D-AssNet is most accurate for single (RGB-A: 97.10%) and double streams (RGB-A + Depth: 98.84%), while ConvLSTM-AssNet performs best for triple streams (RGB + RGB-A + Depth: 97.30%). This research advances multimodal assembly action recognition for manufacturing applications.

Product titles on e-commerce marketplaces often suffer from verbosity and inaccuracy, hindering effective communication of essential product details to customers. Refining titles to be more concise and informative is crucial for better user experience and product promotion. Recent solutions to product title refinement follow the standard text extractive and generative methods. Some also leverage multimodal information, e.g. using product images to supplement original titles with visual knowledge. However, these generative methods often produce additional terms not endorsed by sellers. Thus, it remains challenging to incorporate visual information missing from original titles into refined titles without excessively introducing novel terms. Additionally, most existing methods require human-labeled datasets, which are laborious to construct. In response to the two challenges, we present a self-supervised multimodal framework (HLATR) for title refinement that comprises two key modules: (1) a perturbated sample generator that constructs training data by systematically mining homogeneous listing information and (2) a title refinement network that effectively harnesses visual information to refine the original titles. To explicitly balance the extraction from original titles and the generation of supplementary novel terms, we adapt the copy mechanism that is guided by a focused refinement loss. Extensive experiments demonstrate that our proposed framework consistently outperforms others in generating refined titles that contain essential multimodal semantics with minimal deviation from the original ones.

Accurate and reliable optical remote sensing image-based small-ship detection is crucial for maritime surveillance systems, but existing methods often struggle with balancing detection performance and computational complexity. In this article, we propose a novel lightweight framework called HSI-ShipDetectionNet that is based on high-order spatial interactions (HSIs) and is suitable for deployment on resource-limited platforms, such as satellites and unmanned aerial vehicles. HSI-ShipDetectionNet includes a prediction branch specifically for tiny ships and a lightweight hybrid attention block (LHAB) for reduced complexity. In addition, the use of an HSI module improves advanced feature understanding and modeling ability. Our model is evaluated using the public Kaggle and FAIR1M marine ship detection datasets and compared with multiple state-of-the-art models including small object detection models, lightweight detection models, and ship detection models. The results show that HSI-ShipDetectionNet outperforms the other models in terms of detection performance while being lightweight and suitable for deployment on resource-limited platforms.

To reduce manual tasks and to minimise the risks from a customer, many insurance companies have applied ar-tificial intelligence (AI) solutions, including, but not limited to, machine learning (ML) and deep learning (DL). Exclusion anal-ysis is one of the primary tasks in terms of minimising the risks a customer imposes on a life insurance company. Although a few research studies have made this the primary focus, they have yet to provide explainable research for the exclusion analysis to assist the underwriting process (UP) using ML/DL methods. Therefore, this paper makes the process of exclusion classification, along with its explainability, its primary concentration to assist the underwriters in understanding the underwriting data taken from the customer disclosure information. First, we explore this problem by applying a set of four multi-label classifiers (named binary relevance, classifier chains, label powerset, and ensemble learning) blended with five ML techniques (named multinomial Naive Bayes, support vector classifier, logistic regression, random forest, decision tree), using the data provided by one of the leading insurance companies in Australia. Then, we consider the best-performing model's classification probability and feature importance as input for the explainable ML system - Shapley additive explanations and introduced explainability outcome - as a quality assurance report (QAR). This paper offers an extensive empirical evaluation by comparing different metrics and human underwriters' reviews. Finally, the result demonstrates that the binary relevance algorithm combined with the decision tree classifier outperforms other existing methods for explainable exclusion, providing a better overview of the customer's risk profile.

Abstract Emotion recognition (ER) from speech signals is a robust approach since it cannot be imitated like facial expression or text based sentiment analysis. Valuable information underlying the emotions are significant for human-computer interactions enabling intelligent machines to interact with sensitivity in the real world. Previous ER studies through speech signal processing have focused exclusively on associations between different signal mode decomposition methods and hidden informative features. However, improper decomposition parameter selections lead to informative signal component losses due to mode duplicating and mixing. In contrast, the current study proposes VGG-optiVMD, an empowered variational mode decomposition algorithm, to distinguish meaningful speech features and automatically select the number of decomposed modes and optimum balancing parameter for the data fidelity constraint by assessing their effects on the VGG16 flattening output layer. Various feature vectors were employed to train the VGG16 network on different databases and assess VGG-optiVMD reproducibility and reliability. One, two, and three-dimensional feature vectors were constructed by concatenating Mel-frequency cepstral coefficients, Chromagram, Mel spectrograms, Tonnetz diagrams, and spectral centroids. Results confirmed a synergistic relationship between the fine-tuning of the signal sample rate and decomposition parameters with classification accuracy, achieving state-of-the-art 96.09% accuracy in predicting seven emotions on the Berlin EMO-DB database.

Recently, deep learning techniques have yielded immense success on recommender systems. However, one weakness of most deep methods is that, users/items mutual semantic relationships, which are latent in the user-item interactions, are not distilled out explicitly. Moreover, most methods have been primarily focused on representation learning in euclidean geometry. Since recent studies have shown that the bipartite graph structure has the non-euclidean latent anatomy, euclidean embeddings may suffer from a certain degree of distortion. In this work, we presentHyperbolicNeuralCollaborativeRecommender (HNCR), a deep hyperbolic representation learning method that exploits mutual semantic relationships among users/items for collaborative filtering tasks. HNCR first introduces a neighbor construction strategy to build user and item semantic neighborhoods. Then HNCR develops a framework based on deep learning and hyperbolic geometry to integrate constructed neighborhoods into recommendation. To evaluate our method, we conduct experiments on the four datasets. Experimental results show the superiority of HNCR compared with its euclidean counterpart and state-of-the-art recommendation baselines. The results also indicate that hyperbolic representations can reflect meaningful data insights.

Hypercomplex algebras are well-developed in the area of mathematics. Recently, several hypercomplex recommendation approaches have been proposed and yielded great success. However, two vital issues have not been well-considered in existing hypercomplex recommenders. First, these methods are only designed for specific and low-dimensional hypercomplex algebras (e.g., complex and quaternion algebras), ignoring the exploration and utilization of high-dimensional ones. Second, most recommenders treat every user-item interaction as an isolated data instance, without considering high-order collaborative relationships.

Alzheimer's Disease (AD) is one of the most common forms of neuropsychological disorder in elderly people. It is a slow progressive disease affecting the brain cells. This affects the cognitive abilities of people and their daily activities. During the course of the disease, memory gets brutally affected too. Working as well as long-term declarative memory deteriorates in AD patients. Due to this deterioration of the memory, AD patients tend to show a decline in their communicative skills as well. This decline is reflected in their speech. AD patients usually have poor grammar along with very low coherent ideas. Also, they tend to repeat the words very often and hence become unclear on the message they are trying to convey. As the disease progresses, the speech is completely impaired, and the patients are left to sing or utter words that are totally out of context. Stopwords are the words that are most commonly used in language and it is often hypothesized that AD patients use them much often as compared to Control Normal (CN) subjects. It is seen that due to the degeneration of brain cells in AD patients, they have a tendency to use a lot of stopwords to fill their perplexities in their statements. In this paper, the usefulness of the stopwords in capturing the linguistic information of the patients suffering from AD are discussed. Learning algorithms are evaluated by including stopwords and dropping stopwords at preprocessing to draw comparisons.

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly labeled data, which however could be incompetent when there is only one sentence in a bag. In this paper, we propose a brand-new light-weight neural framework to address the distantly supervised relation extraction problem and alleviate the defects in previous selective attention framework. Specifically, in the proposed framework, 1) we use an entity-aware word embedding method to integrate both relative position information and head/tail entity embeddings, aiming to highlight the essence of entities for this task; 2) we develop a self-attention mechanism to capture the rich contextual dependencies as a complement for local dependencies captured by piecewise CNN; and 3) instead of using selective attention, we design a pooling-equipped gate, which is based on rich contextual representations, as an aggregator to generate bag-level representation for final relation classification. Compared to selective attention, one major advantage of the proposed gating mechanism is that, it performs stably and promisingly even if only one sentence appears in a bag and thus keeps the consistency across all training examples. The experiments on NYT dataset demonstrate that our approach achieves a new state-of-the-art performance in terms of both AUC and top-n precision metrics.

In large-scale software development projects, change impact analysis (CIA) plays an important role in controlling software design evolution. Identifying and accessing the effects of software changes using traceability links between various software artifacts is a common practice during the software development cycle. Recently, research in automated traceability-link recovery has received broad attention in the software maintenance community to reduce the manual maintenance cost of trace links by developers. In this study, we conducted a systematic literature review related to automatic traceability link recovery approaches with a focus on CIA. We identified 33 relevant studies and investigated the following aspects of CIA: traceability approaches, CIA sets, degrees of evaluation, trace direction and methods for recovering traceability link between artifacts of different types. Our review indicated that few traceability studies focused on designing and testing impact analysis sets, presumably due to the scarcity of datasets. Based on the findings, we urge further industrial case studies. Finally, we suggest developing traceability tools to support fully automatic traceability approaches, such as machine learning and deep learning.

Privacy preserving in machine learning is a crucial issue in industry informatics since data used for training in industries usually contain sensitive information. Existing differentially private machine learning algorithms have not considered the impact of data correlation, which may lead to more privacy leakage than expected in industrial applications. For example, data collected for traffic monitoring may contain some correlated records due to temporal correlation or user correlation. To fill this gap, in this article, we propose a correlation reduction scheme with differentially private feature selection considering the issue of privacy loss when data have correlation in machine learning tasks. The proposed scheme involves five steps with the goal of managing the extent of data correlation, preserving the privacy, and supporting accuracy in the prediction results. In this way, the impact of data correlation is relieved with the proposed feature selection scheme, and moreover the privacy issue of data correlation in learning is guaranteed. The proposed method can be widely used in machine learning algorithms, which provide services in industrial areas. Experiments show that the proposed scheme can produce better prediction results with machine learning tasks and fewer mean square errors for data queries compared to existing schemes.

Traceability links between various software artifacts of a system aid software engineers in system comprehension, verification and change impact analysis. Establishing trace links between software artifacts manually is an error-prone and costly task. Recently, studies in automated traceability link recovery area have received broad attention in the software maintenance community aiming to overcome the challenges of manual trace links maintenance process. In these studies, the trace links results generated by an automated trace recovery approach are presented either in a bland textual matrix format (e.g., tabular format) or two-dimensional graphical formats (e.g. tree view, hierarchical leaf node). Therefore, it is challenging for software engineers to explore the inter-relationships between various artifacts at once (e.g., which test cases and source code files/methods are related to a particular requirement). In this position paper, we propose a hierarchical trace map visualization technique to explore inter-relationships between various artifacts at once naturally and intuitively.

Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. At present, the vast majority of GCNs use a neighborhood aggregation framework to learn a continuous and compact vector, then performing a pooling operation to generalize graph embedding for the classification task. These approaches have two disadvantages in the graph classification task: (1)when only the largest sub-graph structure (k-hop neighbor) is used for neighborhood aggregation, a large amount of early-stage information is lost during the graph convolution step; (2) simple average/sum pooling or max pooling utilized, which loses the characteristics of each node and the topology between nodes. In this paper, we propose a novel framework called, dual attention graph convolutional networks (DAGCN) to address these problems. DAGCN automatically learns the importance of neighbors at different hops using a novel attention graph convolution layer, and then employs a second attention component, a self-attention pooling layer, to generalize the graph representation from the various aspects of a matrix graph embedding. The dual attention network is trained in an end-to-end manner for the graph classification task. We compare our model with state-of-the-art graph kernels and other deep learning methods. The experimental results show that our framework not only outperforms other baselines but also achieves a better rate of convergence.