Federated learning (FL) is a distributed machine learning algorithm that enables multiple devices to collaboratively train a global model with data privacy protection. However, in real-world scenarios, the prevalent non-independent and identically distributed (non-IID) and long-tailed data across devices results in significant performance degradation in FL. Although numerous federated long-tailed learning methods have been proposed to address this issue, they typically rely on extensive iterative communication or public datasets, resulting in high communication overhead and potential privacy and security risks. To address these challenges, we propose OFLT, a one-shot federated long-tailed learning framework that aims to improve the global model’s performance in FL under non-IID and long-tailed data in a single communication round. Specifically, OFLT employs class center-based contrastive learning and feature decorrelation for discriminative representation learning on clients, enhancing the intra-class compactness and inter-class separability. Subsequently, supervised distillation-based generator training and adaptive logit calibration are introduced on the server to mitigate class bias in the ensemble output of local models, and the calibrated knowledge is distilled into the global model. Extensive experiments on four image datasets demonstrate that OFLT outperforms state-of-the-art baselines under various settings, consistently improving not only overall accuracy but also performance on medium-shot and few-shot classes.

Parallel computing approaches have illustrated promising potential in accelerating state estimation (SE). How to efficiently handle data processing and updating has become a crucial problem in improving the performance of SE. This article proposes a fully parallel and scalable approach (BMPGNC) based on balanced measurements partitioning and graph node-centric hash (GNCH) storage, to accelerate fast decoupled state estimation (FDSE) for largescale power systems, which is based on graph model multithread parallelism without any centralized preprocessing. A GNCH model is presented for compressed data storage and fast data access, where a balanced measurement partitioning is utilized for load balancing over multiple threads. Four GNCH-based algorithms are proposed for parallel data processing and updating. Extensive experiments were conducted over six benchmark test systems. The results show BMPGNC achieves superior performance on accelerating FDSE without compromising high accuracy, thereby achieving fast, energy-efficient, and high-accuracy FDSE for large-scale power systems.

Hierarchical federated learning (HFL) is a privacy-preserving distributed machine learning framework with a client-edge-cloud hierarchy, where multiple edge servers perform partial model aggregation to reduce costly communication with the cloud server. Nevertheless, most existing HFL methods require extensive iterative communication and public datasets, which not only increase communication overhead but also raise privacy and security concerns. Moreover, non-independent and identically distributed (non-IID) data among devices can significantly impact the accuracy of the global model in HFL. To address these challenges, we propose a multi-level one-shot HFL framework (MOHFL), which aims to improve the performance of the global model in a single communication round. Specifically, we employ conditional variational autoencoders (CVAEs) as local models and use the aggregated decoders to generate an IID training set for the global model, thereby mitigating the negative impact of non-IID data. We improve the performance of CVAEs under different levels of data heterogeneity through a dominant class-based data selection method. Subsequently, an edge aggregation scheme based on multi-teacher knowledge distillation and contrastive learning is proposed to aggregate the knowledge from local decoders to edge decoders. Extensive experiments on four real-world datasets demonstrate that MOHFL is very competitive against four state-of-the-art baselines under various settings.

Recently, many post hoc graph neural network (GNN) explanation methods have been explored to uncover GNNs' predictive behaviors by analyzing the embeddings produced by the GNN models. However, these methods suffer from explanation ambiguity inherent in learned graph embeddings because aggregation-based embeddings can lead to the loss of unique identifiers for individual graph components and, thus, allow noncausal nodes that are adjacent to true causal patterns to unintentionally embody causal information in their embeddings, hindering the explanations from faithfully representing the true insights of GNNs' predictive reasoning. In this article, we present an embedding ambiguity-sensitive GNN explanation framework (EAGX). EAGX can effectively mitigate the impact of embedding-induced explanation ambiguity by creating edges' ambiguity feature extractor, exploring edges' predictive relevance, and integrating them into the explanation process, thereby capturing each graph component's contribution to the predictions. Specifically, we first propose a centroid-constrained fuzzy c-means algorithm to construct an ambiguity feature extractor. Then, we leverage the ambiguity features for edges to develop the ambiguity-based edge attribution module for assigning a prediction relevance score to each edge. Finally, instead of focusing only on the edges with high influence to the GNN prediction, we introduce a joint optimization strategy to refine the learning process of our edge attribution module, empowering EAGX to capture the subtle interplay of both causal and noncausal subgraphs on model predictions, which further improve the explainability of GNN predictions. Experimental results demonstrate that EAGX outperforms the leading explainers on most evaluation metrics, underscoring its effectiveness in generating reliable and precise explanations for GNNs.

Text clustering, as one of the most fundamental challenges in unsupervised learning, aims at grouping semantically similar text segments without relying on human annotations. With the rapid development of deep learning, deep clustering has achieved significant advantages over traditional clustering methods. Despite the effectiveness, most existing deep text clustering methods rely heavily on representations pre-trained in general domains, which may not be the most suitable solution for clustering in specific target domains. To address this issue, we propose CEIL, a novel Classification-Enhanced Iterative Learning framework for short text clustering, which aims at generally promoting the clustering performance by introducing a classification objective to iteratively improve feature representations. In each iteration, we first adopt a language model to retrieve the initial text representations, from which the clustering results are collected using our proposed Category Disentangled Contrastive Clustering (CDCC) algorithm. After strict data filtering and aggregation processes, samples with clean category labels are retrieved, which serve as supervision information to update the language model with the classification objective via a prompt learning approach. Finally, the updated language model with improved representation ability is used to enhance clustering in the next iteration. Extensive experiments demonstrate that the CEIL framework significantly improves the clustering performance over iterations, and is generally effective on various clustering algorithms. Moreover, by incorporating CEIL on CDCC, we achieve the state-of-the-art clustering performance on a wide range of short text clustering benchmarks outperforming other strong baseline methods.

Dependency tree-based methods might be susceptible to the dependency tree due to that they inevitably introduce noisy information and neglect the rich relation information between words. In this paper, we propose a learnable dependency-based double graph (LD2G) model for aspect-based sentiment classification. We use multi-task learning for domain adaptive pretraining, which combines Biaffine Attention and Mask Language Model by incorporating features such as structure, relations and linguistic features in the sentiment text. Then we utilize the dependency enhanced double graph-based MPNN to deeply fuse structure features and relation features that are affected with each other for ASC. Experiment on four benchmark datasets shows that our model is superior to the state-of-the-art approaches.

Ontology reuse offers great benefits by measuring and comparing ontologies. However, the state of art approaches for measuring ontologies neglects the problems of both the polymorphism of ontology representation and the addition of implicit semantic knowledge. One way to tackle these problems is to devise a mechanism for ontology measurement that is stable, the basic criteria for automatic measurement. In this paper, we present a graph derivation representation based approach (GDR) for stable semantic measurement, which captures structural semantics of ontologies and addresses those problems that cause unstable measurement of ontologies. This paper makes three original contributions. First, we introduce and define the concept of semantic measurement and the concept of stable measurement. We present the GDR based approach, a three-phase process to transform an ontology to its GDR. Second, we formally analyze important properties of GDRs based on which stable semantic measurement and comparison can be achieved successfully. Third but not the least, we compare our GDR based approach with existing graph based methods using a dozen real world exemplar ontologies. Our experimental comparison is conducted based on nine ontology measurement entities and distance metric, which stably compares the similarity of two ontologies in terms of their GDRs.

Abstract With the drastic development of semantic‐driven applications, assessing the quality of ontologies has received more attention. Measuring and assessing the quality of ontologies can help ontology engineers to control project management and reduce the risk of project failures. However, most of the existing ontology metrics for measuring and assessing the quality of ontologies are defined based on ontology structure, and neglect the stability of ontology measurement. In this paper, we concentrate on stable ontology measurement by using semantically derived ontology metrics. We propose four ontology cohesion metrics, which fully consider the implicitly expressed semantic information and are defined based on ontological semantics rather than ontology structure. Before measuring and assessing an ontology, we materialize a pre‐processing for stable ontology measurement by treating the ontology. The proposed ontology cohesion metrics are theoretically validated by the validation criteria of object‐oriented software. The experimental results show that we can successfully collect more semantic knowledge from the testing ontologies for stable ontology measurement by using the proposed ontology cohesion metrics. The ontology cohesion metrics proposed in this paper can be reasonably used as a cogent complementarity of existing ontology metrics. Copyright © 2010 John Wiley & Sons, Ltd.

As the Internet environment becomes more and more dynamic, open and mutable, future software have to be more autonomic, reactive, adaptive, cooperative, and evolvable. To meet the need, we introduce emerging service cooperation middleware providing such infrastructure support. Derived from Chinese ancient five-elements ideology, a similar service cooperation philosophy is developed. Complying the idea, we develop a workflow system, PI, supporting Process Intelligence. We believe that the service cooperation will become a feasible solution to the future complex environment.