The rapid expansion of electric vehicles (EVs) charging stations underscores the urgent need for robust anomaly detection systems capable of identifying potential malfunctions while preserving data privacy. Federated Learning (FL) has emerged as a promising solution, enabling collaborative model training without requiring raw data sharing. However, applying conventional FL approaches to charging station networks presents significant challenges, including non-independent and identically distributed (non-IID) data and gradient conflicts among clients. To address these challenges, we introduce FedPareto, a novel Pareto-optimal FL framework designed to manage gradient conflicts and counter malicious attacks in charging station anomaly detection. FedPareto features a gradient conflict-aware aggregation method, which adaptively adjusts client weights based on cosine similarity between gradients, and a gradient magnitude reshaping strategy to enhance model convergence. Theoretical analysis demonstrates that FedPareto achieves a convergence rate of O($\frac{1}{T}$) and attains Pareto-optimal solutions under standard smoothness and convexity assumptions. Extensive experiments on real-world charging station datasets validate FedPareto’s effectiveness. It outperforms state-of-the-art methods, exhibits better robustness against gradient-based attacks, and ensures equitable performance distribution across clients. These results highlight FedPareto’s potential as a reliable and scalable solution for anomaly detection in EV charging station networks.

Open Relation Extraction (OpenRE) seeks to identify and extract novel relational facts between named entities from unlabeled data without pre-defined relation schemas. Traditional OpenRE methods typically assume that the unlabeled data consists solely of novel relations or is pre-divided into known and novel instances. However, in real-world scenarios, novel relations are arbitrarily distributed. In this paper, we propose a generalized OpenRE setting that considers unlabeled data as a mixture of both known and novel instances. To address this, we propose MixORE, a two-phase framework that integrates relation classification and clustering to jointly learn known and novel relations. Experiments on three benchmark datasets demonstrate that MixORE consistently outperforms competitive baselines in known relation classification and novel relation clustering. Our findings contribute to the advancement of generalized OpenRE research and real-world applications.

Distantly-Supervised Named Entity Recognition (DS-NER) uses knowledge bases or dictionaries for annotations, reducing manual efforts but rely on large human labeled validation set. In this paper, we introduce a real-life DS-NER dataset, QTL, where the training data is annotated using domain dictionaries and the test data is annotated by domain experts. This dataset has a small validation set, reflecting real-life scenarios. Existing DS-NER approaches fail when applied to QTL, which motivate us to re-examine existing DS-NER approaches. We found that many of them rely on large validation sets and some used test set for tuning inappropriately. To solve this issue, we proposed a new approach, token-level Curriculum-based Positive-Unlabeled Learning (CuPUL), which uses curriculum learning to order training samples from easy to hard. This method stabilizes training, making it robust and effective on small validation sets. CuPUL also addresses false negative issues using the Positive-Unlabeled learning paradigm, demonstrating improved performance in real-life applications.

federated graph learning (FGL) has emerged as a promising paradigm for privacy-preserving collaborative learning in Social Internet of Things (SIoT), where nodes form complex interconnected networks. Existing FGL approaches face significant challenges including model degradation in handling nonindependent and identically distributed (non-IID) data and maintaining model performance across heterogeneous nodes. This article proposes framework via layer-wised clustering (FedLWC), a novel layer-wised clustering framework inspired by evolutionary processes is proposed to enhance the effectiveness of FGL. FedLWC designs three key aspects: 1) a fisher information matrix-based layer selection mechanism that identifies and evaluates critical model layers, which can reduce parameter redundancy; 2) a layer intersection clustering algorithm that preserves common key layers while accommodating local features; and 3) an adaptive layer merge strategy that effectively combines global shared layers with clustered key layers. To make sure that the proposed approach is rigorous, we conduct theoretical convergence analysis for the proposed framework under non-IID conditions. Extensive experiments on multiple benchmark graph datasets demonstrate FedLWC’s performance, achieving an average accuracy improvement of 7.01% compared to state-of-the-art federated learning methods.

Federated learning (FL) faces significant challenges in scenarios with nonindependent and identically distributed (non-IID) data distributions across participating clients. Traditional aggregation-based approaches often struggle with the inherent misalignment between local and global optimization objectives, which leads to gradient divergence and suboptimal generalization performance. This article proposes a novel FL framework that replaces conventional aggregation with a biologically inspired model symbiosis approach called FedSym, which employs a dual-level symbiotic mechanism. Ectosymbiosis performs coarse-grained hierarchical parameter recombinations through random layer-wise model combination, while endosymbiosis enables fine-grained intralayer parameter fusion through weighted averaging, collectively steering model updates toward flatter loss landscapes. Our theoretical analysis demonstrates that FedSym’s convergence rate is$O({}{1}/{T})$under non-IID conditions, which matches the convergence properties of FedAvg. Extensive evaluations across multiple datasets and model architectures show that FedSym achieves substantial improvements over state-of-the-art FL methods, particularly in challenging scenarios with high data heterogeneity, and demonstrates robust performance across varying numbers of participating clients and federation scales.

Given the significant growth potential in households' energy consumption in China, studying household consumption behavior becomes even more valuable. This study explores factors influencing the shift in households' energy-saving preferences from habitual energy-saving behavior to consumption-oriented energy-saving behavior, as well as to analyze the potential for using other green alternatives to traditional energy in energy consumption. Empirical results reveal an inverted U-shaped relationship between household income and energy consumption, occurring when energy-saving awareness (ESA) exceeds a critical threshold. Below this threshold, household income is positively correlated with energy consumption. Further analysis indicated that once income exceeds the turning point, households' higher ESA leads to reduced energy consumption, indicating potential for green alternatives in higher-income households. Overall, the study highlights how awareness and income interact to shape energy-saving choices, emphasizing the potential for sustainable energy options in affluent households.

To reduce human annotations for relation extraction (RE) tasks, distantly supervised approaches have been proposed, while struggling with low performance. In this work, we propose a novel DSRE-NLI framework, which considers both distant supervision from existing knowledge bases and indirect supervision from pretrained language models for other tasks. DSRE-NLI energizes an off-the-shelf natural language inference (NLI) engine with a semi-automatic relation verbalization (SARV) mechanism to provide indirect supervision and further consolidates the distant annotations to benefit multi-classification RE models. The NLI-based indirect supervision acquires only one relation verbalization template from humans as a semantically general template for each relationship, and then the template set is enriched by high-quality textual patterns automatically mined from the distantly annotated corpus. With two simple and effective data consolidation strategies, the quality of training data is substantially improved. Extensive experiments demonstrate that the proposed framework significantly improves the SOTA performance (up to 7.73% of F1) on distantly supervised RE benchmark datasets. Our code is available at https://github.com/kangISU/DSRE-NLI.

Unsupervised relation extraction (URE) aims to extract relations between named entities from raw text without requiring manual annotations or pre-existing knowledge bases.In recent studies of URE, researchers put a notable emphasis on contrastive learning strategies for acquiring relation representations.However, these studies often overlook two important aspects: the inclusion of diverse positive pairs for contrastive learning and the exploration of appropriate loss functions.In this paper, we propose AugURE with both within-sentence pairs augmentation and augmentation through crosssentence pairs extraction to increase the diversity of positive pairs and strengthen the discriminative power of contrastive learning.We also identify the limitation of noise-contrastive estimation (NCE) loss for relation representation learning and propose to apply margin loss for sentence pairs.Experiments on NYT-FB and TACRED datasets demonstrate that the proposed relation representation learning and a simple K-Means clustering achieves state-ofthe-art performance.Source code is available 1 .

China has been actively developing wind power for several decades, and its installed capacity has grown rapidly, which can be largely attributed to the favorable policy support and subsidies provided to wind power investments. However, China's resource-based strategy for wind power layout may not be fully taking into account the information on electricity demand. Therefore, the authors aim to identify the key factors driving the regional distribution of wind power in China, with a particular focus on the relationship between wind farm investments and local electricity demand. The study reveals that, compared to earlier stages of development, wind power installation growth is now more concentrated in regions with high electricity demand rather than just in resource-rich areas. Moreover, the model results demonstrate that the leading effect of demand on wind investment is more pronounced in resource-rich regions than in other areas. Demand information and mechanism analysis highlight the significant role of zoning policies in moderating the impact of demand on wind power siting and investment.

Force sensing is highly desirable in minimally invasive medical applications, since this feature shows great potential for reducing tissue damage and enhancing manipulation safety. However, embedding force sensors in medical devices is challenging and costly. This article explores the possibility to use shape sensing as a measure to extract force information. In this work, a model-based approach that allows simultaneous shape and force sensing is proposed. Shape information is reconstructed employing a multicore fiber with fiber Bragg grating sensors spaced over the fiber length. This fiber is capable of distributed 3D shape sensing. It is shown how by making use of extended Kalman filter and a mechanics model of the flexible instrument, it becomes possible to estimate both the magnitudes and locations of externally applied forces. Experiments were carried out to validate the proposed method for both one and two external forces applied at arbitrary locations in different directions on a flexible instrument. Results show that one-directional force magnitude and location can be estimated with an average error of 23.08 mN (15.39%) and 11.06 mm (6.51%), respectively. For two-directional forces, results of the load near the base show an average error of 52.01 mN (30.59%) for the magnitude and 29.24 mm (17.20%) for the location. For the load applied simultaneously near the tip, the mean magnitude error is 16.79 mN (11.19%) and the average location error is 10.18 mm (5.99%). The force sensing algorithm can run in real time with an approximate frequency of 59 Hz. In these experiments, it can be observed that the force-sensing accuracy, which depends on the sensitivity of the shape of flexible instruments with respect to the external force, can vary drastically in function of the force application point and force direction.