Neurocomputing最新文献

Robust jointly sparse 2-dimensional projection fuzzy clustering with local manifold structure preservation 具有局部流形结构保留的鲁棒联合稀疏二维投影模糊聚类

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-04 DOI: 10.1016/j.neucom.2026.132970

Wu Chengmao , Fengchao Gong

Dimensionality reduction clustering methods combine feature reduction and clustering to analyze high-dimensional image data. However, 1D projection subspace clustering vectorizes 2D images into 1D vectors, disrupting spatial correlations and causing information loss. Two-stage models that separate reduction and clustering lack coordination, leading to suboptimal results. We propose a robust sparse two-dimensional projection fuzzy clustering method with local manifold constraints to improve image clustering. Each cluster is represented by a bilinear orthogonal subspace, and F1-norm reconstruction error updates sample memberships. A similarity matrix captures affinities, while a Laplacian matrix preserves manifold geometry during dimensionality reduction. Optimization uses block coordinate descent to alternately refine the projection matrix, cluster centroids, and membership matrix until convergence. This unified, unsupervised model avoids image vectorization, reducing computational complexity and preserving spatial relationships. Experiments on nine benchmark datasets show the RS2DPFC-LMS algorithm improves accuracy by 2.47 % and normalized mutual information by 2 %, demonstrating superior clustering performance, parameter stability, and noise robustness.

降维聚类方法将特征约简和聚类相结合，对高维图像数据进行分析。然而，一维投影子空间聚类将二维图像矢量化为一维向量，破坏了空间相关性，造成信息丢失。分离约简和聚类的两阶段模型缺乏协调，导致次优结果。提出了一种具有局部流形约束的鲁棒稀疏二维投影模糊聚类方法。每个聚类由双线性正交子空间表示，f1范数重构误差更新样本隶属度。相似矩阵捕获相似性，而拉普拉斯矩阵在降维过程中保留流形几何。优化采用分块坐标下降交替优化投影矩阵、聚类质心和隶属度矩阵，直至收敛。这种统一的无监督模型避免了图像矢量化，降低了计算复杂度并保留了空间关系。在9个基准数据集上的实验表明，RS2DPFC-LMS算法的准确率提高了2.47 %，归一化互信息提高了2 %，表现出了优异的聚类性能、参数稳定性和噪声鲁棒性。

{"title":"Robust jointly sparse 2-dimensional projection fuzzy clustering with local manifold structure preservation","authors":"Wu Chengmao , Fengchao Gong","doi":"10.1016/j.neucom.2026.132970","DOIUrl":"10.1016/j.neucom.2026.132970","url":null,"abstract":"<div><div>Dimensionality reduction clustering methods combine feature reduction and clustering to analyze high-dimensional image data. However, 1D projection subspace clustering vectorizes 2D images into 1D vectors, disrupting spatial correlations and causing information loss. Two-stage models that separate reduction and clustering lack coordination, leading to suboptimal results. We propose a robust sparse two-dimensional projection fuzzy clustering method with local manifold constraints to improve image clustering. Each cluster is represented by a bilinear orthogonal subspace, and F1-norm reconstruction error updates sample memberships. A similarity matrix captures affinities, while a Laplacian matrix preserves manifold geometry during dimensionality reduction. Optimization uses block coordinate descent to alternately refine the projection matrix, cluster centroids, and membership matrix until convergence. This unified, unsupervised model avoids image vectorization, reducing computational complexity and preserving spatial relationships. Experiments on nine benchmark datasets show the RS2DPFC-LMS algorithm improves accuracy by 2.47 % and normalized mutual information by 2 %, demonstrating superior clustering performance, parameter stability, and noise robustness.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 132970"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Entropy-aware event-triggered neural control for finite-time practical consensus of heterogeneous multi-agent systems under DoS attacks DoS攻击下异构多智能体系统有限时间实际共识的熵感知事件触发神经控制

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-16 DOI: 10.1016/j.neucom.2026.133020

Hongwei Ren , Weiyi Li , Zhiping Peng , Feiqi Deng

This paper investigates the finite-time practical consensus problem for heterogeneous second-order multi-agent systems subject to denial-of-service attacks. An entropy-aware event-triggered neural control framework is proposed that integrates multidimensional entropy-based attack detection across temporal, spatial, and frequency domains, entropy-guided adaptive event-triggering mechanisms, and finite-time control augmented by radial basis function neural network compensation for unknown heterogeneous dynamics. Rigorous Lyapunov-based theoretical analysis establishes finite-time practical consensus with explicit settling-time bounds dependent on initial conditions while excluding Zeno behavior. Simulation results demonstrate that, under diverse attack patterns, the proposed method achieves consensus in 10.04 s (4.0% faster than resilient event-triggered control) with only 4672 transmissions (approximately 80.5% reduction), validating superior attack resilience and communication efficiency.

研究了异构二阶多智能体系统在拒绝服务攻击下的有限时间实际一致性问题。提出了一种熵感知的事件触发神经控制框架，该框架集成了跨时间、空间和频域的多维熵攻击检测，熵引导的自适应事件触发机制，以及对未知异构动态进行径向基函数神经网络补偿增强的有限时间控制。严格的李雅普诺夫理论分析建立了有限时间的实际共识，明确的沉降时间边界依赖于初始条件，同时排除了齐诺行为。仿真结果表明，在不同攻击模式下，该方法在10.04 s内达成共识（比弹性事件触发控制快4.0%），仅传输4672次（减少约80.5%），验证了优越的攻击弹性和通信效率。

引用次数: 0

EHC k-NN: Elliptic hypercomplex distance metrics for dimension-adaptive k-nearest neighbor EHC - k-NN：自适应k近邻的椭圆超复距离度量

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-11 DOI: 10.1016/j.neucom.2026.133051

Kaan Arik , Arzu Sürekçi , Hidayet Hüda Kösal

<div><div>This study introduces a dimension-adaptive k-Nearest Neighbor (k-NN) model that employs a family of elliptic hypercomplex distance metrics, addressing the limitations of Euclidean geometry in heterogeneous and correlated data with tabular and image datasets. The approach reshapes the feature space using a negative real parameter <span><math><mi>p</mi><mo><</mo><mn>0</mn></math></span>, enabling curvature-controlled neighborhoods that better capture local structure. In the proposed method, each data instance is represented as an <span><math><mi>n</mi></math></span>-dimensional elliptic hypercomplex number, and distances are computed through a norm that re-weights even- and odd- indexed components depending on <span><math><mi>p</mi></math></span>. The proposed method is dimension-adaptive in the sense that each real-valued feature vector of length <span><math><mi>d</mi></math></span> is mapped to the smallest elliptic hypercomplex algebra of dimension <span><math><msup><mn>2</mn><mrow><mi>m</mi></mrow></msup></math></span> satisfying <span><math><msup><mn>2</mn><mrow><mi>m</mi><mo>−</mo><mn>1</mn></mrow></msup><mo><</mo><mi>d</mi><mo>≤</mo><msup><mn>2</mn><mrow><mi>m</mi></mrow></msup></math></span>. When <span><math><mi>d</mi><mo>≠</mo><msup><mn>2</mn><mrow><mi>m</mi></mrow></msup></math></span>, the remaining components are zero-padded, so distance computations are carried out consistently in the corresponding <span><math><msup><mn>2</mn><mrow><mi>m</mi></mrow></msup></math></span>-dimensional elliptic hypercomplex space. Experiments were conducted on five tabular UCI + two image-derived benchmarks selected for their diversity in feature types and class structure. Performance was evaluated using classification performance evaluation metrics under identical <span><math><mi>k</mi></math></span> settings. The proposed metric yields clear gains over Euclidean k-NN, particularly in <em>Wine</em> (approximately <span><math><mn>2.0</mn></math></span>-<span><math><mn>2.3</mn><mi>%</mi></math></span>) and <em>Breast Cancer</em> (approximately <span><math><mn>1.4</mn><mi>%</mi></math></span>). Improvements are moderate in <em>Car Evaluation</em>, while <em>Iris</em> and <em>Banknote Authentication</em> exhibit minimal change due to saturated separability and dominant attributes. On image-derived benchmarks (Seeds/Wheat and Image Segmentation), the proposed metric also delivers consistent improvements, typically around +2.0-2.7% in accuracy and +2.4-2.9% in F1-score compared with Euclidean k-NN. Further comparisons against metric-learning and manifold-inspired baselines (LMNN and geodesic distance) indicate that the proposed hypercomplex metric remains competitive and stable across neighborhood sizes, reinforcing its robustness beyond Euclidean geometry. Overall, the results indicate that the performance gains stem from the <span><math><mi>p</mi></math></span>-induced anisotropy of the elliptic hypercomplex norm, which reshapes neighborhood

本研究引入了一个维度自适应的k-最近邻（k-NN）模型，该模型采用了一系列椭圆超复距离度量，解决了欧几里得几何在表格和图像数据集的异构和相关数据中的局限性。该方法使用负实参数p<；0重塑特征空间，使曲率控制的邻域能够更好地捕获局部结构。在该方法中，每个数据实例被表示为一个n维椭圆超复数，并通过一个范数来计算距离，该范数根据p重新加权偶指数和奇指数分量。该方法是自适应的，因为每个长度为d的实值特征向量被映射到满足2m - 1<；d≤2m维的最小椭圆超复数代数。当d≠2m时，将剩余分量补零，在相应的2m维椭圆超复空间中一致进行距离计算。实验在5个表格UCI + 2个基于特征类型和类结构多样性而选择的图像衍生基准上进行。在相同的k设置下，使用分类性能评估指标对性能进行评估。与欧几里得k-NN相比，该指标的收益明显增加，特别是在葡萄酒（约2.0-2.3%）和乳腺癌（约1.4%）方面。汽车评估方面的改进是适度的，而虹膜和钞票认证由于饱和可分离性和主导属性而表现出最小的变化。在图像衍生基准（种子/小麦和图像分割）上，与欧几里得k-NN相比，所提出的度量也提供了一致的改进，通常在精度上约为+2.0-2.7%，f1得分为+2.4-2.9%。与度量学习和流形启发基线（LMNN和测地线距离）的进一步比较表明，所提出的超复度量在邻域大小上保持竞争和稳定，增强了其超越欧几里德几何的鲁棒性。总体而言，结果表明，性能的提高源于椭圆型超复范数的p诱导各向异性，它重塑了邻域几何，以更好地与异质和相关的特征结构对齐，从而使椭圆型超复k-NN成为欧几里得k-NN的鲁棒替代品。

{"title":"EHC k-NN: Elliptic hypercomplex distance metrics for dimension-adaptive k-nearest neighbor","authors":"Kaan Arik , Arzu Sürekçi , Hidayet Hüda Kösal","doi":"10.1016/j.neucom.2026.133051","DOIUrl":"10.1016/j.neucom.2026.133051","url":null,"abstract":"<div><div>This study introduces a dimension-adaptive k-Nearest Neighbor (k-NN) model that employs a family of elliptic hypercomplex distance metrics, addressing the limitations of Euclidean geometry in heterogeneous and correlated data with tabular and image datasets. The approach reshapes the feature space using a negative real parameter <span><math><mi>p</mi><mo><</mo><mn>0</mn></math></span>, enabling curvature-controlled neighborhoods that better capture local structure. In the proposed method, each data instance is represented as an <span><math><mi>n</mi></math></span>-dimensional elliptic hypercomplex number, and distances are computed through a norm that re-weights even- and odd- indexed components depending on <span><math><mi>p</mi></math></span>. The proposed method is dimension-adaptive in the sense that each real-valued feature vector of length <span><math><mi>d</mi></math></span> is mapped to the smallest elliptic hypercomplex algebra of dimension <span><math><msup><mn>2</mn><mrow><mi>m</mi></mrow></msup></math></span> satisfying <span><math><msup><mn>2</mn><mrow><mi>m</mi><mo>−</mo><mn>1</mn></mrow></msup><mo><</mo><mi>d</mi><mo>≤</mo><msup><mn>2</mn><mrow><mi>m</mi></mrow></msup></math></span>. When <span><math><mi>d</mi><mo>≠</mo><msup><mn>2</mn><mrow><mi>m</mi></mrow></msup></math></span>, the remaining components are zero-padded, so distance computations are carried out consistently in the corresponding <span><math><msup><mn>2</mn><mrow><mi>m</mi></mrow></msup></math></span>-dimensional elliptic hypercomplex space. Experiments were conducted on five tabular UCI + two image-derived benchmarks selected for their diversity in feature types and class structure. Performance was evaluated using classification performance evaluation metrics under identical <span><math><mi>k</mi></math></span> settings. The proposed metric yields clear gains over Euclidean k-NN, particularly in <em>Wine</em> (approximately <span><math><mn>2.0</mn></math></span>-<span><math><mn>2.3</mn><mi>%</mi></math></span>) and <em>Breast Cancer</em> (approximately <span><math><mn>1.4</mn><mi>%</mi></math></span>). Improvements are moderate in <em>Car Evaluation</em>, while <em>Iris</em> and <em>Banknote Authentication</em> exhibit minimal change due to saturated separability and dominant attributes. On image-derived benchmarks (Seeds/Wheat and Image Segmentation), the proposed metric also delivers consistent improvements, typically around +2.0-2.7% in accuracy and +2.4-2.9% in F1-score compared with Euclidean k-NN. Further comparisons against metric-learning and manifold-inspired baselines (LMNN and geodesic distance) indicate that the proposed hypercomplex metric remains competitive and stable across neighborhood sizes, reinforcing its robustness beyond Euclidean geometry. Overall, the results indicate that the performance gains stem from the <span><math><mi>p</mi></math></span>-induced anisotropy of the elliptic hypercomplex norm, which reshapes neighborhood ","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 133051"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147386372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Congestion-aware platoon re-sequencing optimization for electric vehicles using deep reinforcement learning 基于深度强化学习的电动汽车拥堵感知排重排序优化

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-13 DOI: 10.1016/j.neucom.2026.133040

Chu Peng, Shaopan Guo, Miao Liu, Long Xiao

With the development of Vehicle-to-Vehicle (V2V) communication, the non-fixed platoon method has become feasible, enabling vehicles to adjust positions dynamically, balance energy use, and improve efficiency. However, existing methods ignore the dynamic nature of traffic conditions. When road space is limited, platoon re-sequencing may become unsafe or even infeasible. To address these challenges, we propose a congestion-aware platoon re-sequencing optimization framework for electric vehicles (EVs) using deep reinforcement learning. The framework consists of two modules: a Traffic Congestion-Aware (TCA) module and a Deep Reinforcement Learning (DRL) module. Specifically, the TCA module predicts traffic congestion categories and incorporates them as constraints in the optimization process, overcoming the limitations of non-fixed platoon methods that neglect the safety and feasibility impacts of traffic congestion on re-sequencing. The DRL module, built on the Trust Region Policy Optimization (TRPO) algorithm, takes the EV State-of-Charge (SoC) and predicted traffic congestion categories as environmental observations. It restricts re-sequencing operations under congested conditions to prevent invalid actions and simultaneously manages the computational complexity that arises with increasing platoon size. Experimental results demonstrate that, compared to existing reinforcement learning methods without congestion constraints, our proposed framework reduces the frequency of platoon re-sequencing by 34.4%. Moreover, it achieves a 23.6% reduction in the final standard deviation of the SoC across all vehicles compared to existing re-sequencing algorithms, indicating that the unbalanced energy consumption of the vehicles has been reduced.

随着车对车（V2V）通信技术的发展，非固定排法成为可能，使车辆能够动态调整位置，平衡能源使用，提高效率。然而，现有的方法忽略了交通条件的动态性。当道路空间有限时，排重排序可能变得不安全甚至不可行的。为了解决这些挑战，我们提出了一个使用深度强化学习的电动汽车（ev）拥堵感知队列重新排序优化框架。该框架由两个模块组成：交通拥堵感知（TCA）模块和深度强化学习（DRL）模块。具体而言，TCA模块预测交通拥堵类别，并将其作为约束纳入优化过程，克服了非固定排法忽略交通拥堵对重排序的安全性和可行性影响的局限性。DRL模块基于信任区域策略优化（Trust Region Policy Optimization， TRPO）算法，将EV SoC （State-of-Charge，充电状态）和预测的交通拥堵类别作为环境观测。它限制了拥挤条件下的重排序操作，以防止无效操作，同时管理随着队列规模增加而产生的计算复杂性。实验结果表明，与现有的无拥塞约束的强化学习方法相比，我们提出的框架将排重排序的频率降低了34.4%。此外，与现有的重排序算法相比，该算法在所有车辆上的SoC最终标准差降低了23.6%，这表明车辆的不平衡能耗已经减少。

{"title":"Congestion-aware platoon re-sequencing optimization for electric vehicles using deep reinforcement learning","authors":"Chu Peng, Shaopan Guo, Miao Liu, Long Xiao","doi":"10.1016/j.neucom.2026.133040","DOIUrl":"10.1016/j.neucom.2026.133040","url":null,"abstract":"<div><div>With the development of Vehicle-to-Vehicle (V2V) communication, the non-fixed platoon method has become feasible, enabling vehicles to adjust positions dynamically, balance energy use, and improve efficiency. However, existing methods ignore the dynamic nature of traffic conditions. When road space is limited, platoon re-sequencing may become unsafe or even infeasible. To address these challenges, we propose a congestion-aware platoon re-sequencing optimization framework for electric vehicles (EVs) using deep reinforcement learning. The framework consists of two modules: a Traffic Congestion-Aware (TCA) module and a Deep Reinforcement Learning (DRL) module. Specifically, the TCA module predicts traffic congestion categories and incorporates them as constraints in the optimization process, overcoming the limitations of non-fixed platoon methods that neglect the safety and feasibility impacts of traffic congestion on re-sequencing. The DRL module, built on the Trust Region Policy Optimization (TRPO) algorithm, takes the EV State-of-Charge (SoC) and predicted traffic congestion categories as environmental observations. It restricts re-sequencing operations under congested conditions to prevent invalid actions and simultaneously manages the computational complexity that arises with increasing platoon size. Experimental results demonstrate that, compared to existing reinforcement learning methods without congestion constraints, our proposed framework reduces the frequency of platoon re-sequencing by 34.4%. Moreover, it achieves a 23.6% reduction in the final standard deviation of the SoC across all vehicles compared to existing re-sequencing algorithms, indicating that the unbalanced energy consumption of the vehicles has been reduced.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 133040"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147386361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automatic self-supervised learning for social recommendations 社会推荐的自动自监督学习

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-11 DOI: 10.1016/j.neucom.2026.133024

Xin He , Wenqi Fan , Ying Wang , Mingchen Sun , Xin Wang

In recent years, researchers have leveraged social relations to enhance recommendation performance. However, most existing social recommendation methods require carefully designed auxiliary social tasks tailored to specific scenarios, which depend heavily on domain knowledge and expertise. To address this limitation, we propose Automatic Self-supervised Learning for Social Recommendations (AusRec), which integrates multiple self-supervised auxiliary tasks with an automatic weighting mechanism to adaptively balance their contributions through a meta-learning optimization framework. This design enables the model to automatically learn the optimal importance of each auxiliary task, thereby enhancing representation learning in social recommendations. Extensive experiments on several real-world datasets demonstrate that AusRec consistently outperforms state-of-the-art baselines by 3.3%–10.7% in Recall@10 and 1.4%–7.1% in NDCG@10, validating its effectiveness and robustness across different recommendation scenarios. The code is available at: https://github.com/hexin5515/AusRec.

近年来，研究人员利用社会关系来提高推荐性能。然而，大多数现有的社会推荐方法需要精心设计针对特定场景的辅助社会任务，这在很大程度上依赖于领域知识和专业知识。为了解决这一限制，我们提出了用于社会推荐的自动自监督学习（AusRec），它将多个自监督辅助任务与自动加权机制集成在一起，通过元学习优化框架自适应地平衡它们的贡献。该设计使模型能够自动学习每个辅助任务的最优重要性，从而增强社会推荐中的表示学习。在几个真实数据集上进行的大量实验表明，AusRec在Recall@10和NDCG@10上的表现始终优于最先进的基线，分别为3.3%-10.7%和1.4%-7.1%，验证了其在不同推荐场景中的有效性和稳健性。代码可从https://github.com/hexin5515/AusRec获得。

{"title":"Automatic self-supervised learning for social recommendations","authors":"Xin He , Wenqi Fan , Ying Wang , Mingchen Sun , Xin Wang","doi":"10.1016/j.neucom.2026.133024","DOIUrl":"10.1016/j.neucom.2026.133024","url":null,"abstract":"<div><div>In recent years, researchers have leveraged social relations to enhance recommendation performance. However, most existing social recommendation methods require carefully designed auxiliary social tasks tailored to specific scenarios, which depend heavily on domain knowledge and expertise. To address this limitation, we propose Automatic Self-supervised Learning for Social Recommendations (AusRec), which integrates multiple self-supervised auxiliary tasks with an automatic weighting mechanism to adaptively balance their contributions through a meta-learning optimization framework. This design enables the model to automatically learn the optimal importance of each auxiliary task, thereby enhancing representation learning in social recommendations. Extensive experiments on several real-world datasets demonstrate that AusRec consistently outperforms state-of-the-art baselines by 3.3%–10.7% in Recall@10 and 1.4%–7.1% in NDCG@10, validating its effectiveness and robustness across different recommendation scenarios. The code is available at: <span><span>https://github.com/hexin5515/AusRec</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 133024"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147386376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive wavelet decomposition and event-aware high-frequency modeling network for multivariate time series forecasting 多变量时间序列预测的自适应小波分解和事件感知高频建模网络

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-16 DOI: 10.1016/j.neucom.2026.133089

Mengdi Gong, Chengci Wang, Jie Yu, Lingyu Xu

Multivariate time series (MTS) forecasting has wide applications in real-world domains such as traffic, weather, and ocean monitoring. However, real-world MTS data often exhibit multiscale non-stationary patterns. These patterns arise from the dynamic coupling between long-term trends and sudden local events, making accurate forecasting highly challenging. Existing methods primarily rely on global modeling or fixed decomposition strategies. However, such approaches fail to adapt to varying spatiotemporal data and diverse task contexts. They cannot effectively disentangle trend and event sequences in accordance with the characteristics of time series data. Moreover, they cannot model unstable high-frequency events. To address these issues, we propose an Adaptive Wavelet Decomposition and Event-aware High-frequency Modeling Network (AweHF). The model employs an Adaptive Wavelet Decomposition module (AWD) to decouple the original sequence into low-frequency trends and high-frequency events in a data-driven way, avoiding the limitations of fixed wavelet bases. Subsequently, we apply a lightweight multilayer perceptron (MLP) to capture long-term dependencies in the trend component. In addition, we design a Time Aggregation Network (TAN) and Dual-Source Personalized Graph Convolution (DSPGC) to jointly model the volatility and instability of the event component. Finally, the bidirectional interaction fusion mechanism is used to integrate the trend and event components to fully exploit their complementary advantages. We conducted extensive experiments on six real-world datasets from multiple domains, and our results demonstrate that AweHF consistently outperforms all state-of-the-art baselines, achieving an average MAE reduction of more than 3.8% across the datasets. Code is available at this repository: https://github.com/WangChengci/AweHF.

多变量时间序列（MTS）预测在交通、天气和海洋监测等现实领域有着广泛的应用。然而，现实世界的MTS数据往往表现出多尺度非平稳模式。这些模式产生于长期趋势和突发局部事件之间的动态耦合，这使得准确预测极具挑战性。现有方法主要依赖于全局建模或固定分解策略。然而，这种方法不能适应不同的时空数据和不同的任务背景。它们不能根据时间序列数据的特点有效地分离趋势序列和事件序列。此外，它们不能模拟不稳定的高频事件。为了解决这些问题，我们提出了一个自适应小波分解和事件感知高频建模网络（AweHF）。该模型采用自适应小波分解模块（AWD），以数据驱动的方式将原始序列解耦为低频趋势和高频事件，避免了固定小波基的局限性。随后，我们应用轻量级多层感知器（MLP）来捕获趋势组件中的长期依赖关系。此外，我们设计了一个时间聚合网络（TAN）和双源个性化图卷积（DSPGC）来共同建模事件组件的波动性和不稳定性。最后，采用双向交互融合机制，将趋势和事件两部分进行融合，充分发挥其互补优势。我们对来自多个领域的六个真实数据集进行了广泛的实验，结果表明，AweHF始终优于所有最先进的基线，在数据集上平均降低了3.8%以上的MAE。代码可在此存储库中获得：https://github.com/WangChengci/AweHF。

{"title":"Adaptive wavelet decomposition and event-aware high-frequency modeling network for multivariate time series forecasting","authors":"Mengdi Gong, Chengci Wang, Jie Yu, Lingyu Xu","doi":"10.1016/j.neucom.2026.133089","DOIUrl":"10.1016/j.neucom.2026.133089","url":null,"abstract":"<div><div>Multivariate time series (MTS) forecasting has wide applications in real-world domains such as traffic, weather, and ocean monitoring. However, real-world MTS data often exhibit multiscale non-stationary patterns. These patterns arise from the dynamic coupling between long-term trends and sudden local events, making accurate forecasting highly challenging. Existing methods primarily rely on global modeling or fixed decomposition strategies. However, such approaches fail to adapt to varying spatiotemporal data and diverse task contexts. They cannot effectively disentangle trend and event sequences in accordance with the characteristics of time series data. Moreover, they cannot model unstable high-frequency events. To address these issues, we propose an Adaptive Wavelet Decomposition and Event-aware High-frequency Modeling Network (AweHF). The model employs an Adaptive Wavelet Decomposition module (AWD) to decouple the original sequence into low-frequency trends and high-frequency events in a data-driven way, avoiding the limitations of fixed wavelet bases. Subsequently, we apply a lightweight multilayer perceptron (MLP) to capture long-term dependencies in the trend component. In addition, we design a Time Aggregation Network (TAN) and Dual-Source Personalized Graph Convolution (DSPGC) to jointly model the volatility and instability of the event component. Finally, the bidirectional interaction fusion mechanism is used to integrate the trend and event components to fully exploit their complementary advantages. We conducted extensive experiments on six real-world datasets from multiple domains, and our results demonstrate that AweHF consistently outperforms all state-of-the-art baselines, achieving an average MAE reduction of more than 3.8% across the datasets. Code is available at this repository: <span><span>https://github.com/WangChengci/AweHF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 133089"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147386319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Time-frequency-based pyramid channel network for long-term time series forecasting 基于时频的金字塔信道网络长期时间序列预测

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-11 DOI: 10.1016/j.neucom.2026.133022

Zhiqiang Jiang , Yongsheng Dong , Min Han , Haotian Yang , Xiaotong Chen

Many time-domain and frequency-domain based methods have been proposed for long-term time series forecasting. In order to obtain the seasonal correlation of different channels and time series features at different time scales, we propose a brand-new time-frequency-based pyramid channel network (TPCNet) for long-term time series forecasting. Particularly, we first build a multi-channel seasonal feature attention residual fusion structure to obtain seasonal correlations between different channels by using the short-time Fourier transform, residual ideas, and fusion operations of multiple kernels’ different channels. We then propose a dual-dimensional attention residual pyramid structure to obtain time series features at different time scales by using tensor summation operations, residual ideas, and attention mechanisms. Finally, we obtain time-series prediction results through fully connected operations. Our proposed TPCNet shows competitive prediction performance when compared with many sample classical methods on GeForce RTX 4060Ti, according to the results of experiments on six commonly used time series datasets.

人们提出了许多基于时域和频域的长期时间序列预测方法。为了获得不同时间尺度下不同通道与时间序列特征的季节相关性，提出了一种全新的基于时频的金字塔通道网络（TPCNet）用于长期时间序列预报。其中，首先利用短时傅里叶变换、残差思想和多核不同通道的融合运算，构建多通道季节特征关注残差融合结构，获取不同通道之间的季节相关性；然后，我们提出了一个二维注意残差金字塔结构，利用张量求和运算、残差思想和注意机制来获得不同时间尺度下的时间序列特征。最后，通过全连通运算得到时间序列预测结果。在六个常用的时间序列数据集上进行的实验结果表明，与许多经典方法相比，我们提出的TPCNet在GeForce RTX 4060Ti上的预测性能具有竞争力。

{"title":"Time-frequency-based pyramid channel network for long-term time series forecasting","authors":"Zhiqiang Jiang , Yongsheng Dong , Min Han , Haotian Yang , Xiaotong Chen","doi":"10.1016/j.neucom.2026.133022","DOIUrl":"10.1016/j.neucom.2026.133022","url":null,"abstract":"<div><div>Many time-domain and frequency-domain based methods have been proposed for long-term time series forecasting. In order to obtain the seasonal correlation of different channels and time series features at different time scales, we propose a brand-new time-frequency-based pyramid channel network (TPCNet) for long-term time series forecasting. Particularly, we first build a multi-channel seasonal feature attention residual fusion structure to obtain seasonal correlations between different channels by using the short-time Fourier transform, residual ideas, and fusion operations of multiple kernels’ different channels. We then propose a dual-dimensional attention residual pyramid structure to obtain time series features at different time scales by using tensor summation operations, residual ideas, and attention mechanisms. Finally, we obtain time-series prediction results through fully connected operations. Our proposed TPCNet shows competitive prediction performance when compared with many sample classical methods on GeForce RTX 4060Ti, according to the results of experiments on six commonly used time series datasets.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 133022"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147386370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fight light with light: A review of physical adversarial attack within light transmission pipeline 以光斗光：光传输管道内物理对抗性攻击研究综述

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-16 DOI: 10.1016/j.neucom.2026.133034

Guojia Li , Simin Xu , Yan Cao , Mingyue Cao , Yihong Zhang

Deep Neural Networks (DNNs) remain vulnerable to physical adversarial attacks. Attacks that target the light transmission pipeline exhibit heightened stealthiness while posing severe real-world threats due to their flexible and deployable nature. To advance the understanding of this emerging threat, we establish a unified framework that systematically analyzes the entire light transmission pipeline as a contiguous attack surface. Within this framework, we identify two primary attack vectors, manipulating light transmission channel and attacking image perception device, and systematically characterize their methodologies across nine key attributes. We further formalize the optimization process for generating adversarial light patterns and assess the physical deployment methods of such attacks. Furthermore, we propose a graded framework for evaluating the transferability and demonstrate that while physical adversarial examples in this domain exhibit high stealthiness, their transferability across different model architectures remains limited. Finally, we outline current challenges and discuss future research directions.

深度神经网络（dnn）仍然容易受到物理对抗性攻击。针对光传输管道的攻击表现出更高的隐蔽性，同时由于其灵活性和可部署性，构成了严重的现实威胁。为了促进对这种新兴威胁的理解，我们建立了一个统一的框架，系统地分析整个光传输管道作为一个连续的攻击面。在此框架内，我们确定了两个主要的攻击向量，操纵光传输通道和攻击图像感知设备，并系统地描述了它们在九个关键属性上的方法。我们进一步形式化了生成对抗性光模式的优化过程，并评估了此类攻击的物理部署方法。此外，我们提出了一个评估可转移性的分级框架，并证明尽管该领域的物理对抗示例表现出高隐身性，但它们在不同模型架构之间的可转移性仍然有限。最后，我们概述了当前面临的挑战，并讨论了未来的研究方向。

{"title":"Fight light with light: A review of physical adversarial attack within light transmission pipeline","authors":"Guojia Li , Simin Xu , Yan Cao , Mingyue Cao , Yihong Zhang","doi":"10.1016/j.neucom.2026.133034","DOIUrl":"10.1016/j.neucom.2026.133034","url":null,"abstract":"<div><div>Deep Neural Networks (DNNs) remain vulnerable to physical adversarial attacks. Attacks that target the light transmission pipeline exhibit heightened stealthiness while posing severe real-world threats due to their flexible and deployable nature. To advance the understanding of this emerging threat, we establish a unified framework that systematically analyzes the entire light transmission pipeline as a contiguous attack surface. Within this framework, we identify two primary attack vectors, manipulating light transmission channel and attacking image perception device, and systematically characterize their methodologies across nine key attributes. We further formalize the optimization process for generating adversarial light patterns and assess the physical deployment methods of such attacks. Furthermore, we propose a graded framework for evaluating the transferability and demonstrate that while physical adversarial examples in this domain exhibit high stealthiness, their transferability across different model architectures remains limited. Finally, we outline current challenges and discuss future research directions.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 133034"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147386328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generalist multimodal AI: A review of architectures, challenges and opportunities 多面手多模态人工智能：架构、挑战和机遇的回顾

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-03 DOI: 10.1016/j.neucom.2026.132933

Sai Munikoti, Ian Stewart, Sameera Horawalavithana, Henry Kvinge, Tegan Emerson, Sandra Thompson, Karl Pazdernik

Multimodal models are expected of be a critical component to future advances in artificial intelligence. This field is starting to grow rapidly with a surge of new design elements motivated by the success of foundation models in natural language processing (NLP) and vision. It is widely hoped that further extending the foundation models to multiple modalities (e.g., text, image, video, sensor, time series, graph, etc.) will ultimately lead to generalist multimodal models, i.e., one model across different data modalities and tasks. However, there is little research that systematically analyzes recent multimodal models (particularly the ones that work beyond text and vision) with respect to the underlying architecture proposed. Therefore, this work provides a fresh perspective on generalist multimodal models (GMMs) via a novel architecture and training configuration specific taxonomy. This includes factors such as Unifiability, Modularity, and Adaptability that are pertinent and essential to the wide adoption and application of GMMs. The review further highlights key challenges and prospects for the field and guides researchers into the new advancements.

多模态模型有望成为人工智能未来发展的关键组成部分。随着自然语言处理（NLP）和视觉领域基础模型的成功，新的设计元素激增，这一领域开始迅速发展。人们普遍希望，进一步将基础模型扩展到多模态（如文本、图像、视频、传感器、时间序列、图形等），最终将导致通才多模态模型，即跨不同数据模态和任务的一个模型。然而，很少有研究系统地分析最近的多模态模型（特别是那些超越文本和视觉的模型）所提出的底层架构。因此，这项工作通过一种新的体系结构和训练配置特定的分类法，为通才多模态模型（GMMs）提供了一个新的视角。这包括诸如统一性、模块化和适应性等因素，这些因素对于gmm的广泛采用和应用是相关的和必不可少的。该综述进一步强调了该领域的主要挑战和前景，并指导研究人员进入新的进展。

{"title":"Generalist multimodal AI: A review of architectures, challenges and opportunities","authors":"Sai Munikoti, Ian Stewart, Sameera Horawalavithana, Henry Kvinge, Tegan Emerson, Sandra Thompson, Karl Pazdernik","doi":"10.1016/j.neucom.2026.132933","DOIUrl":"10.1016/j.neucom.2026.132933","url":null,"abstract":"<div><div>Multimodal models are expected of be a critical component to future advances in artificial intelligence. This field is starting to grow rapidly with a surge of new design elements motivated by the success of foundation models in natural language processing (NLP) and vision. It is widely hoped that further extending the foundation models to multiple modalities (e.g., text, image, video, sensor, time series, graph, etc.) will ultimately lead to generalist multimodal models, i.e., one model across different data modalities and tasks. However, there is little research that systematically analyzes recent multimodal models (particularly the ones that work beyond text and vision) with respect to the underlying architecture proposed. Therefore, this work provides a fresh perspective on generalist multimodal models (GMMs) via a novel architecture and training configuration specific taxonomy. This includes factors such as <em>Unifiability</em>, <em>Modularity</em>, and <em>Adaptability</em> that are pertinent and essential to the wide adoption and application of GMMs. The review further highlights key challenges and prospects for the field and guides researchers into the new advancements.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 132933"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147386360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Leveraging intra-modal and inter-modal interaction for multi-modal entity alignment 利用模态内和模态间的交互来实现多模态实体对齐

IF 6.5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neurocomputing

Pub Date : 2026-05-01 Epub Date: 2026-02-12 DOI: 10.1016/j.neucom.2026.133017

Zhiwei Hu , Víctor Gutiérrez-Basulto , Zhiliang Xiang , Ru Li , Jeff Z. Pan

Multi-modal entity alignment (MMEA) aims to identify equivalent entity pairs across different multi-modal knowledge graphs (MMKGs). Existing approaches focus on how to better encode and aggregate information from different modalities. However, it is not trivial to leverage multi-modal knowledge in entity alignment due to the modal heterogeneity. In this paper, we propose a Multi-Grained Interaction framework for Multi-Modal Entity Alignment (MIMEA), which effectively realizes multi-granular interaction within the same modality or between different modalities. MIMEA is composed of four modules: i) a Multi-modal Knowledge Embedding module, which extracts modality-specific representations with multiple individual encoders; ii) a Probability-guided Modal Fusion module, which employs a probability guided approach to integrate uni-modal representations into joint-modal embeddings, while considering the interaction between uni-modal representations; iii) an Optimal Transport Modal Alignment module, which introduces an optimal transport mechanism to encourage the interaction between uni-modal and joint-modal embeddings; iv) a Modal-adaptive Contrastive Learning module, which distinguishes the embeddings of equivalent entities from those of non-equivalent ones, for each modality. Extensive experiments conducted on two real-world datasets demonstrate the strong performance of MIMEA compared to the SoTA. Datasets and code are available at the following website: https://github.com/zhiweihu1103/MEA-MIMEA.

多模态实体对齐（MMEA）旨在识别不同多模态知识图（MMKGs）之间的等效实体对。现有的方法侧重于如何更好地编码和聚合来自不同模式的信息。然而，由于模态异质性，在实体对齐中利用多模态知识并非易事。本文提出了一种多模态实体对齐（MIMEA）的多粒度交互框架，该框架有效地实现了同一模态内或不同模态之间的多粒度交互。MIMEA由四个模块组成：i)多模态知识嵌入模块，该模块使用多个单独的编码器提取特定于模态的表示；ii)概率引导模态融合模块，该模块采用概率引导方法将单模态表示集成到联合模态嵌入中，同时考虑单模态表示之间的相互作用；iii)最佳运输模式对齐模块，它引入了最佳运输机制，以鼓励单模态和联合模态嵌入之间的相互作用；iv)模态自适应对比学习模块，用于区分每个模态的等效实体嵌入和非等效实体嵌入。在两个真实数据集上进行的大量实验表明，与SoTA相比，MIMEA具有强大的性能。数据集和代码可在以下网站获得：https://github.com/zhiweihu1103/MEA-MIMEA。

{"title":"Leveraging intra-modal and inter-modal interaction for multi-modal entity alignment","authors":"Zhiwei Hu , Víctor Gutiérrez-Basulto , Zhiliang Xiang , Ru Li , Jeff Z. Pan","doi":"10.1016/j.neucom.2026.133017","DOIUrl":"10.1016/j.neucom.2026.133017","url":null,"abstract":"<div><div>Multi-modal entity alignment (MMEA) aims to identify equivalent entity pairs across different multi-modal knowledge graphs (MMKGs). Existing approaches focus on how to better encode and aggregate information from different modalities. However, it is not trivial to leverage multi-modal knowledge in entity alignment due to the modal heterogeneity. In this paper, we propose a <strong>M</strong>ulti-Grained <strong>I</strong>nteraction framework for <strong>M</strong>ulti-Modal <strong>E</strong>ntity <strong>A</strong>lignment (<strong>MIMEA</strong>), which effectively realizes multi-granular interaction within the same modality or between different modalities. MIMEA is composed of four modules: i) a <em>Multi-modal Knowledge Embedding</em> module, which extracts modality-specific representations with multiple individual encoders; ii) a <em>Probability-guided Modal Fusion</em> module, which employs a probability guided approach to integrate uni-modal representations into joint-modal embeddings, while considering the interaction between uni-modal representations; iii) an <em>Optimal Transport Modal Alignment</em> module, which introduces an optimal transport mechanism to encourage the interaction between uni-modal and joint-modal embeddings; iv) a <em>Modal-adaptive Contrastive Learning</em> module, which distinguishes the embeddings of equivalent entities from those of non-equivalent ones, for each modality. Extensive experiments conducted on two real-world datasets demonstrate the strong performance of MIMEA compared to the SoTA. Datasets and code are available at the following website: <span><span>https://github.com/zhiweihu1103/MEA-MIMEA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"676 ","pages":"Article 133017"},"PeriodicalIF":6.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147386721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0