Knowledge-Based Systems最新文献

{"title":"Federated feature reconstruction with collaborative star networks","authors":"Yihong Zhang ,&nbsp;Yuan Gao ,&nbsp;Maoguo Gong,&nbsp;Hao Li,&nbsp;Yuanqiao Zhang,&nbsp;Sijia Zhang","doi":"10.1016/j.knosys.2025.113463","DOIUrl":"10.1016/j.knosys.2025.113463","url":null,"abstract":"<div><div>Federal learning provides a secure platform for sharing sensitive data, yet imposes stringent requirements on the data. Non-IID data often cannot fully enjoy the convenience it offers. When clients possess divergent feature sets, retaining only the common features is a prevalent yet suboptimal practice. This paper proposes a novel omnidirectional federated learning framework that employs a Star collaboration network designed to leverage independent information from client nodes for feature reconstruction of other clients. It establishes an approximate distribution network, reinforcing feature correlations while overcoming data isolation seen in traditional federal learning. Additionally, homomorphic encryption is utilized to ensure data security throughout the transmission process. Experimental evaluations on structured datasets demonstrate that the reconstructed prediction results closely approximate those under the condition of complete data, confirming the effectiveness of the Star network in data completion and multi-party prediction scenarios.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113463"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EAEFA-R: Multiple learning-based ensemble artificial electric field algorithm for global optimization","authors":"Dikshit Chauhan ,&nbsp;Anupam Yadav ,&nbsp;Rammohan Mallipeddi","doi":"10.1016/j.knosys.2025.113453","DOIUrl":"10.1016/j.knosys.2025.113453","url":null,"abstract":"<div><div>Adjusting the search behaviors of swarm-based algorithms is crucial for solving real-world optimization challenges. Researchers have developed ensemble strategies and self-adaptive mechanisms to enhance the optimization ability of individual algorithms by balancing global and local search capabilities. Inspired by these advancements, this paper proposes a physics-based artificial electric field algorithm with three improvement strategies and an attraction–repulsion operator (EAEFA-R) to enhance diversity and escape local optima. These strategies are probabilistically selected using a dynamic adaptation mechanism. The effectiveness of EAEFA-R is assessed through extensive analysis of exploration-exploitation dynamics and diversity, and it is evaluated on two real-parameter test suites, CEC 2017 and CEC 2022, across 10, 20, 30, 50, and 100-dimensional search spaces. Compared to fifteen state-of-the-art algorithms, including AEFA variants and other optimization algorithms, EAEFA-R demonstrates superior solution accuracy, convergence rate, search capability, and stability performance. The overall ranking highlights its exceptional potential for solving challenging optimization problems, outperforming other state-of-the-art algorithms across various dimensions. The MATLAB source code of EAEFA-R is available at <span><span>https://github.com/ChauhanDikshit</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113453"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diachronic semantic encoding based on pre-trained language model for temporal knowledge graph reasoning","authors":"Yunteng Deng ,&nbsp;Jia Song ,&nbsp;Zhongliang Yang ,&nbsp;Yilin Long ,&nbsp;Li Zeng ,&nbsp;Linna Zhou","doi":"10.1016/j.knosys.2025.113479","DOIUrl":"10.1016/j.knosys.2025.113479","url":null,"abstract":"<div><div>Temporal Knowledge Graph Reasoning (TKGR) aims to infer missing facts at specific timestamps. However, most existing methods primarily focus on the local and global evolutionary characteristics of temporal knowledge graphs (TKG), often neglecting the inherent semantic information of historical facts. The oversight limits the understanding of the diachronic evolution of facts, thereby limiting the ability to predict future missing facts. To address these issues, we propose a TKGR model with <strong>D</strong>iachronic <strong>S</strong>emantic <strong>E</strong>ncoding based on a <strong>P</strong>re-trained language model, called <strong>DSEP</strong>. It uses a pre-trained language model (PLM) to learn the evolutionary characteristics of historical related facts of the entity or relation to be predicted, so as to enhance the understanding of historical facts by the graph encoder used to capture the local evolutionary characteristics of the temporal knowledge graph. Additionally, to further narrow the prediction scope, DSEP incorporates historical fact correlation matrix in its prediction results. Experimental results on four benchmark datasets demonstrate that DSEP significantly improves the performance of relation prediction in temporal knowledge graphs, with an average improvement of 20.9% in MRR<span><span>¹</span></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113479"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decentralized Contrastive Learning for generalized zero-shot image classification","authors":"Ya Chen ,&nbsp;Zhihao Zhang ,&nbsp;Pei Wang ,&nbsp;Feng Tian","doi":"10.1016/j.knosys.2025.113466","DOIUrl":"10.1016/j.knosys.2025.113466","url":null,"abstract":"<div><div>Generalized zero-shot learning (GZSL) aims to learn a model on known classes that can adapt to a test set comprising both known and unknown classes. Recent GZSL research in image classification has made significant progress by utilizing representation learning techniques. However, the challenge of generating discriminative representations for fine-grained classes with close relevance remains unresolved. To address this problem, we introduce a Decentralized Contrastive Learning (DCL) framework that seamlessly integrates a nested Wasserstein GAN (WGAN) with decentralized contrastive representation learning. Our nested WGAN incorporates the representation learning module within the discriminator, enabling the model to simultaneously train the representations and differentiate them in a synergistic manner. Moreover, our decentralized contrastive learning module enhances the discriminative nature of representations by preserving calibration based on class information without additional parameters during training. We further provide theoretical analysis for DCL, uncovering its superiority in learning discriminative representations and its robustness in handling mixed features. Experiments on show that DCL outperforms the state-of-the-art models by margins of about 3%, 4% and 3% on CUB, SUN and aPY datasets.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113466"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CharFormer: Character-oriented attention network for string edit distance","authors":"Xijuan Liu ,&nbsp;Haobo Wei ,&nbsp;Peilun Yang ,&nbsp;Haiyang Hu","doi":"10.1016/j.knosys.2025.113482","DOIUrl":"10.1016/j.knosys.2025.113482","url":null,"abstract":"<div><div>String similarity computation plays a crucial role in numerous real-world applications, such as similarity search and sequence alignment. String Edit Distance (SED) is a representative similarity metric that effectively measures the similarity between strings. However, its quadratic complexity makes the computation of SED challenging, especially for large datasets. Consequently, in recent years, an increasing number of algorithms have adopted deep learning techniques to accelerate SED computation. However, we observe that existing methods often employ a bi-encoder framework to learn the features of individual strings, which leads to neglect of the matching information across strings. Moreover, these methods fail to fully leverage subsequence information and the sampling space. To this end, we propose a character-oriented attention network named CharFormer to learn the computation of SED. Specifically, CharFormer operates at the character granularity, leveraging both the intra-sequence information of individual input strings and the inter-sequence information between them to learn the representations of characters and strings. Subsequently, CharFormer uses two prediction heads to simultaneously utilize these two types of information to predict the similarity between strings. Additionally, we incorporate the similarity between substrings to provide extra supervision and design a novel sampling method to fully exploit the sampling space. Extensive experiments demonstrate the superiority of CharFormer over state-of-the-art algorithms and the efficacy of the proposed methods.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113482"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FactorVQVAE: Discrete latent factor model via Vector Quantized Variational Autoencoder","authors":"Namhyoung Kim,&nbsp;Seung Eun Ock,&nbsp;Jae Wook Song","doi":"10.1016/j.knosys.2025.113460","DOIUrl":"10.1016/j.knosys.2025.113460","url":null,"abstract":"<div><div>This study introduces FactorVQVAE, the first integration of the Vector Quantized Variational Autoencoder (VQVAE) into factor modeling, providing a novel framework for predicting cross-sectional stock returns and constructing systematic investment portfolios. The model employs a two-stage architecture to improve the extraction and utilization of latent financial factors. In the first stage, an encoder–decoder-quantizer compresses high-dimensional input data into discrete latent factors through vector quantization, addressing posterior collapse and ensuring distinct representations. In the second stage, an autoregressive Transformer captures sequential dependencies among these latent factors, enabling precise return predictions. Empirical results in the CSI300 and S&amp;P500 markets demonstrate FactorVQVAE’s superior performance. The model achieves the best Rank IC and Rank ICIR scores, surpassing the state-of-the-art latent factor models in varying market conditions. In portfolio evaluations, FactorVQVAE consistently excels in both Top-<span><math><mi>k</mi></math></span> Drop-<span><math><mi>n</mi></math></span> and Long–Short strategies, translating predictive accuracy into robust investment performance. In particular, it delivers the highest risk-adjusted returns, highlighting its ability to balance returns and risks effectively. These findings position FactorVQVAE as a significant advancement in integrating modern deep learning methodologies with financial factor modeling. Its adaptability, robustness, and exceptional performance in portfolio investment establish it as a promising tool for systematic investing and financial analytics.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113460"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Temporal knowledge graph fusion with neural ordinary differential equations for the predictive maintenance of electromechanical equipment","authors":"Jiawei Lu ,&nbsp;Hanyuan Chen ,&nbsp;Jianwei Chen ,&nbsp;Zhongcheng Xiao ,&nbsp;Ren Li ,&nbsp;Gang Xiao ,&nbsp;Qibing Wang","doi":"10.1016/j.knosys.2025.113450","DOIUrl":"10.1016/j.knosys.2025.113450","url":null,"abstract":"<div><div>Predictive Maintenance is the primary strategy for optimizing operational efficiency and reducing the maintenance costs of electromechanical equipment. However, existing Predictive Maintenance approaches suffer from significant shortcomings, such as the inability to learn the dynamic evolution of fault and maintenance events within massive, heterogeneous datasets and the lack of effective models to handle this complex data. To address these issues, we propose a temporal knowledge graph (TKG) reasoning method. First, we construct a TKG based on an ontology defined by the heterogeneous data features of electromechanical equipment. Second, we propose a Dynamic Graph Embedding model, which captures the dynamic evolution of the non-equal-interval events in the TKG by combining neural ordinary differential equations with a graph convolutional neural network. Furthermore, we design a Dynamic Hawkes Transformer to identify the evolutionary process and predicting future events based on historical fault and maintenance data. Finally, we use elevators as a case study to compare the proposed method with other advanced methods and demonstrate its effectiveness in TKG reasoning. Our proposed method excels in fault and maintenance event prediction, as well as time prediction, for electromechanical equipment.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113450"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Textual semantics enhancement adversarial hashing for cross-modal retrieval","authors":"Lei Zhu ,&nbsp;Runbing Wu ,&nbsp;Deyin Liu ,&nbsp;Chengyuan Zhang ,&nbsp;Lin Wu ,&nbsp;Ying Zhang ,&nbsp;Shichao Zhang","doi":"10.1016/j.knosys.2025.113303","DOIUrl":"10.1016/j.knosys.2025.113303","url":null,"abstract":"<div><div>Supervised cross-modal hashing seeks to embed rich semantic information into binary hash codes, thereby enhancing semantic discrimination. Despite substantial advancements in cross-modal semantic learning, two critical challenges remain: (1) the fine-grained semantic information inherent in individual words within text contents is underutilized; and (2) more efficient constraints are required to mitigate the distributional heterogeneity across modalities. To overcome these issues, we introduce a <u><strong>T</strong></u>extual <u><strong>S</strong></u>emantics <u><strong>E</strong></u>nhancement <u><strong>A</strong></u>dersarial <u><strong>H</strong></u>ashing method, abbreviated as <strong>TSEAH</strong>, aimed at further improving hashing retrieval performance. Our approach introduces an effective textual semantics enhancement strategy involving a Bag-of-Words Self-Attention (BWSA) mechanism, which accentuates fine-grained semantics from textual content. This mechanism facilitates the transfer of fine-grained semantic knowledge from texts to images. Furthermore, we incorporate an adversarial hashing strategy within the cross-modal hashing learning process to ensure semantic distribution consistency across different modalities. Importantly, our solution achieves impressive results without the need for complex visual-language pre-training models. Comparative evaluations across three commonly used datasets demonstrate that our method achieves outstanding average accuracy: 90.41<span><math><mtext>%</mtext></math></span> on MIRFLICKR-25K, 82.86<span><math><mtext>%</mtext></math></span> on NUW-SIDE, and 83.53<span><math><mtext>%</mtext></math></span> on MS COCO, outperforming the state-of-the-art baselines by a significant margin ranging from 1.97<span><math><mtext>%</mtext></math></span> to 2.51<span><math><mtext>%</mtext></math></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113303"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143824293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PRADA: Prompt-guided Representation Alignment and Dynamic Adaption for time series forecasting","authors":"Yinhao Liu ,&nbsp;Zhenyu Kuang ,&nbsp;Hongyang Zhang ,&nbsp;Chen Li ,&nbsp;Feifei Li ,&nbsp;Xinghao Ding","doi":"10.1016/j.knosys.2025.113478","DOIUrl":"10.1016/j.knosys.2025.113478","url":null,"abstract":"<div><div>Time series forecasting endeavors to construct models capable of predicting future values and trends grounded in historical observations. However, current LLM-based approaches migrate the inference power of LLM to the time series forecasting through prompt guidance, but ignore the modality gap between time series and natural language. This gap arises from the fact that time series have periodic and non-periodic patterns that are not present in natural language, hindering the capabilities of LLM-based models. In addition, the potential statistical property drift in time series makes the model rely on spurious correlation features, limiting the capture of spatio-temporal dependencies. To tackle the unique problems, we introduce the Prompt-guided Representation Alignment and Dynamic Adaption (PRADA) method, which harnesses multi-view Text-Series Adaptive Alignment (TSAA) guided by learnable prompts to capture the representations of different patterns. Specifically, we first decompose the input time series into different components and align orthogonal prompts consisting of learnable context vectors with time series embeddings independently for LLM’s input adaption. Furthermore, the time-frequency dual constraint is introduced to empower the model to capture the overlooked label autocorrelation from both the time and frequency domains. Through multi-view adaptive alignment guided by learnable prompts, PRADA is able to dynamically model spatio-temporal dependencies and adapt to the semantic gap between time series and natural language, which enables LLM-based models to obtain more robust times series representations in real scenarios. Experiments on multiple public datasets demonstrate the state-of-the-art (SOTA) performance of PRADA in time series forecasting. The code will be available at <span><span>https://github.com/HowardLiu28/PRADA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113478"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Balance recovery and collaborative adaptation approach for federated fault diagnosis of inconsistent machine groups","authors":"Bin Yang ,&nbsp;Yaguo Lei ,&nbsp;Naipeng Li ,&nbsp;Xiang Li ,&nbsp;Xiaosheng Si ,&nbsp;Chuanhai Chen","doi":"10.1016/j.knosys.2025.113480","DOIUrl":"10.1016/j.knosys.2025.113480","url":null,"abstract":"<div><div>Due to data privacy concerns and long-distance communication overhead, federated learning-based intelligent diagnosis offers a promising solution for ensuring the efficiency and reliability of machine groups in data decentralization. However, the data information from different machine nodes in a group are often inconsistent, leading to two key challenges in current federated intelligent diagnosis research: (1) data imbalance especially with respect to unseen faults, which causes the diagnosis model to become skewed, and (2) label space shifts across machine nodes, resulting in significant misalignment between the local and global distributions. As a consequence, the global diagnosis model struggles to effectively recognize unseen and under-represented fault states, and is often under-generalized to other machine nodes, especially when only a limited number of labeled samples are available. To address these challenges, this article presents a balance recovery and collaborative adaptation (BRCA) framework for federated intelligent diagnosis. The BRCA framework utilizes a central server to capture the inconsistent distribution information from each machine node, and further solves the Wasserstein barycenter to create a global distribution that carries complementary information. This barycenter is then broadcast to the client side to guide local model updates. At each client, convolutional autoencoders are constrained to supplement synthetic data for unseen and under-represented fault states, helping to restore a balanced decision boundary. Moreover, local distributions are aligned with the global barycenter through the designed adaptation trajectory that directionally ties subcategories with the same label. This is expected to correct discrepancies caused by label space shifts. The proposed BRCA is demonstrated in two federated intelligent diagnosis cases: one involving diverse machine-used bearings and the other involving different planetary gearboxes. The results show that BRCA can mitigate the performance degradation caused by data inconsistency, and achieve higher diagnosis accuracy than existing federated methods on other machine nodes even when there are very few labeled samples available.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113480"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}