Neural Networks最新文献_第3页

A dimensional structure based knowledge distillation method for cross-modal learning 一种基于维度结构的跨模态学习知识升华方法。

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-02-03 DOI: 10.1016/j.neunet.2026.108672

Lingyu Si , Hongwei Dong , Fan Yang , Shouyou Huang , Junzhi Yu , Fuchun Sun

Transferring informative dark knowledge from other modalities has become a common approach to solving learning tasks that are challenging to accomplish independently due to limitations in data quality. However, research on why the transferred knowledge works has not been extensively explored. To address this issue, in this paper, we discover the correlation between feature discriminability and its dimensional structure (DS) by observing the features extracted from modalities with high and low data quality within the same learning task. On this basis, we express DS using the spatial distribution of intermediate features and the channel-wise correlation of output features. We empirically find that the DS of high-quality features is better than that of low-quality ones. This inspires us to propose a novel DS-based knowledge distillation method for better supervised cross-modal learning (CML) performance. Instead of merely mimicking the logits or features from the high-quality modality, the proposed method leverages its structural knowledge to guide the low-quality modality. Specifically, it enforces uniform distribution of intermediate features and channel-wise independence of deep features in the low-quality modality, thereby enhancing semantic learning and improving performance. This is especially useful when the performance gap between dual modalities is relatively large. Furthermore, this paper introduces a new CML dataset for the task of marine target recognition, named IIS-ISCAS, to promote community development. The dataset includes more than 10,000 paired samples from 8 distinct marine targets with optics and radar modalities and is continuously being updated. Experimental results on six visual benchmark transformed datasets and six CML datasets validate the effectiveness of the proposed method.

对于由于数据质量的限制而难以独立完成的学习任务，从其他模式转移信息性暗知识已经成为解决这些任务的常用方法。然而，对于知识迁移为什么会起作用的研究还没有得到广泛的探讨。为了解决这一问题，本文通过观察同一学习任务中从高质量和低质量模态中提取的特征，发现特征可判别性与其维度结构（DS）之间的相关性。在此基础上，我们使用中间特征的空间分布和输出特征的通道相关来表示DS。实证发现，高质量特征的DS优于低质量特征的DS。这启发我们提出了一种新的基于分布式决策系统的知识蒸馏方法，以获得更好的监督跨模态学习（CML）性能。该方法不是简单地模仿高质量模态的逻辑或特征，而是利用其结构知识来指导低质量模态。具体而言，它在低质量模态中强制中间特征的均匀分布和深度特征的通道独立性，从而增强语义学习和提高性能。当双模之间的性能差距相对较大时，这尤其有用。在此基础上，本文引入了一种新的CML数据集，即IIS-ISCAS，用于海洋目标识别，以促进社区的发展。该数据集包括来自8个不同海洋目标的10,000多个配对样本，具有光学和雷达模式，并不断更新。在6个视觉基准转换数据集和6个CML数据集上的实验结果验证了该方法的有效性。

{"title":"A dimensional structure based knowledge distillation method for cross-modal learning","authors":"Lingyu Si , Hongwei Dong , Fan Yang , Shouyou Huang , Junzhi Yu , Fuchun Sun","doi":"10.1016/j.neunet.2026.108672","DOIUrl":"10.1016/j.neunet.2026.108672","url":null,"abstract":"<div><div>Transferring informative dark knowledge from other modalities has become a common approach to solving learning tasks that are challenging to accomplish independently due to limitations in data quality. However, research on why the transferred knowledge works has not been extensively explored. To address this issue, in this paper, we discover the correlation between feature discriminability and its dimensional structure (DS) by observing the features extracted from modalities with high and low data quality within the same learning task. On this basis, we express DS using the spatial distribution of intermediate features and the channel-wise correlation of output features. We empirically find that the DS of high-quality features is better than that of low-quality ones. This inspires us to propose a novel DS-based knowledge distillation method for better supervised cross-modal learning (CML) performance. Instead of merely mimicking the logits or features from the high-quality modality, the proposed method leverages its structural knowledge to guide the low-quality modality. Specifically, it enforces uniform distribution of intermediate features and channel-wise independence of deep features in the low-quality modality, thereby enhancing semantic learning and improving performance. This is especially useful when the performance gap between dual modalities is relatively large. Furthermore, this paper introduces a new CML dataset for the task of marine target recognition, named IIS-ISCAS, to promote community development. The dataset includes more than 10,000 paired samples from 8 distinct marine targets with optics and radar modalities and is continuously being updated. Experimental results on six visual benchmark transformed datasets and six CML datasets validate the effectiveness of the proposed method.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108672"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146158719","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}

引用次数: 0

MCDNet: Morphological-conditional dual-view fusion for 3D tubular structure segmentation 基于形态条件的双视图融合三维管状结构分割

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-01-19 DOI: 10.1016/j.neunet.2026.108614

Zhiyan Wang , Changjian Wang , Kele Xu , Zhongshun Tang , Yan Zhuang , Jiani Zou , Fangyi Liu

Accurate segmentation of 3D tubular structures in medical images is critical for clinical diagnosis and interventional planning. Although deep learning methods have advanced significantly, most existing approaches exhibit limited generalizability due to their reliance on structure-specific morphological priors. Consequently, these models are often constrained to particular anatomical regions–such as the colorectal tract, vasculature, or arteries–leading to suboptimal performance when applied across varied organ systems. Moreover, the joint modeling of global and local morphological characteristics remains underexplored in the context of tubular structure segmentation. To address these limitations, we propose MCDNet, a Morphological-Conditional Dual-view Network that integrates both contextual and morphological information through a target-adaptive Morphological-Conditional Convolution (MCConv). The network is composed of three sequential modules: (1) a morphological feature extraction stage leveraging MCConv to enhance structural sensitivity across diverse tubular geometries; (2) a contextual feature learning stage employing a cross-fusion mechanism that synergistically combines convolutional and attention-based representations; and (3) a residual self-attention fusion module that reinforces feature integration from decoupled morphological and contextual branches. We evaluate MCDNet on four benchmark datasets encompassing diverse tubular segmentation tasks. Experimental results demonstrate that MCDNet achieves superior performance over state-of-the-art methods, with an average Dice coefficient improvement of 6.93% and a 10.61% reduction in Hausdorff distance relative to a strong baseline. The source code is publicly available at https://github.com/wzydcg/MCDNet.

医学图像中三维管状结构的准确分割对临床诊断和介入规划至关重要。尽管深度学习方法取得了显著进展，但大多数现有方法由于依赖于特定结构的形态学先验而表现出有限的泛化性。因此，这些模型通常局限于特定的解剖区域，如结肠直肠、脉管系统或动脉，导致在应用于不同器官系统时表现不佳。此外，在管状结构分割的背景下，全局和局部形态特征的联合建模仍然没有得到充分的探索。为了解决这些限制，我们提出了MCDNet，一个形态条件双视图网络，通过目标自适应形态条件卷积（MCConv）集成上下文和形态信息。该网络由三个连续模块组成：(1)利用MCConv的形态特征提取阶段，以提高不同管状结构的结构灵敏度；(2)上下文特征学习阶段，采用交叉融合机制，协同结合卷积和基于注意的表征；(3)残差自关注融合模块，增强了从解耦的形态和上下文分支中整合特征的能力。我们在包含不同管状分割任务的四个基准数据集上评估MCDNet。实验结果表明，MCDNet比最先进的方法具有更好的性能，相对于强基线，平均Dice系数提高了6.93%，Hausdorff距离减少了10.61%。源代码可在https://github.com/wzydcg/MCDNet上公开获得。

{"title":"MCDNet: Morphological-conditional dual-view fusion for 3D tubular structure segmentation","authors":"Zhiyan Wang , Changjian Wang , Kele Xu , Zhongshun Tang , Yan Zhuang , Jiani Zou , Fangyi Liu","doi":"10.1016/j.neunet.2026.108614","DOIUrl":"10.1016/j.neunet.2026.108614","url":null,"abstract":"<div><div>Accurate segmentation of 3D tubular structures in medical images is critical for clinical diagnosis and interventional planning. Although deep learning methods have advanced significantly, most existing approaches exhibit limited generalizability due to their reliance on structure-specific morphological priors. Consequently, these models are often constrained to particular anatomical regions–such as the colorectal tract, vasculature, or arteries–leading to suboptimal performance when applied across varied organ systems. Moreover, the joint modeling of global and local morphological characteristics remains underexplored in the context of tubular structure segmentation. To address these limitations, we propose MCDNet, a Morphological-Conditional Dual-view Network that integrates both contextual and morphological information through a target-adaptive Morphological-Conditional Convolution (MCConv). The network is composed of three sequential modules: (1) a morphological feature extraction stage leveraging MCConv to enhance structural sensitivity across diverse tubular geometries; (2) a contextual feature learning stage employing a cross-fusion mechanism that synergistically combines convolutional and attention-based representations; and (3) a residual self-attention fusion module that reinforces feature integration from decoupled morphological and contextual branches. We evaluate MCDNet on four benchmark datasets encompassing diverse tubular segmentation tasks. Experimental results demonstrate that MCDNet achieves superior performance over state-of-the-art methods, with an average Dice coefficient improvement of 6.93% and a 10.61% reduction in Hausdorff distance relative to a strong baseline. The source code is publicly available at <span><span>https://github.com/wzydcg/MCDNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108614"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081675","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}

引用次数: 0

Reinforcement learning via conservative agent for environments with random delays 基于保守代理的随机延迟环境强化学习。

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-01-27 DOI: 10.1016/j.neunet.2026.108645

Jongsoo Lee , Jangwon Kim , Jiseok Jeong , Soohee Han

Real-world reinforcement learning applications are often subject to unavoidable delayed feedback from the environment. Under such conditions, the standard state representation may no longer induce Markovian dynamics unless additional information is incorporated at decision time, which introduces significant challenges for both learning and control. While numerous delay-compensation methods have been proposed for environments with constant delays, those with random delays remain largely unexplored due to their inherent variability and unpredictability. In this study, we propose a robust agent for decision-making under bounded random delays, termed the conservative agent. This agent reformulates the random-delay environment into a constant-delay surrogate, which enables any constant-delay method to be directly extended to random-delay environments without modifying their algorithmic structure. Apart from a maximum delay, the conservative agent does not require prior knowledge of the underlying delay distribution and maintains performance invariant to changes in the delay distribution as long as the maximum delay remains unchanged. We present a theoretical analysis of conservative agent and evaluate its performance on diverse continuous control tasks from the MuJoCo benchmarks. Empirical results demonstrate that it significantly outperforms existing baselines in terms of both asymptotic performance and sample efficiency.

现实世界的强化学习应用经常受到来自环境的不可避免的延迟反馈的影响。在这种情况下，除非在决策时加入额外的信息，否则标准状态表示可能不再诱导马尔可夫动态，这对学习和控制都带来了重大挑战。虽然许多延迟补偿方法已被提出用于具有恒定延迟的环境，但那些具有随机延迟的环境由于其固有的可变性和不可预测性而在很大程度上仍未被探索。在本研究中，我们提出了一种鲁棒的决策代理，称为保守代理。该代理将随机延迟环境重新表述为恒定延迟代理，这使得任何恒定延迟方法都可以直接扩展到随机延迟环境，而无需修改其算法结构。除了最大延迟之外，保守代理不需要预先知道潜在的延迟分布，只要最大延迟保持不变，就可以保持延迟分布变化的性能不变。我们提出了保守代理的理论分析，并从MuJoCo基准评估了其在各种连续控制任务上的性能。实证结果表明，在渐近性能和样本效率方面，它明显优于现有的基线。

{"title":"Reinforcement learning via conservative agent for environments with random delays","authors":"Jongsoo Lee , Jangwon Kim , Jiseok Jeong , Soohee Han","doi":"10.1016/j.neunet.2026.108645","DOIUrl":"10.1016/j.neunet.2026.108645","url":null,"abstract":"<div><div>Real-world reinforcement learning applications are often subject to unavoidable delayed feedback from the environment. Under such conditions, the standard state representation may no longer induce Markovian dynamics unless additional information is incorporated at decision time, which introduces significant challenges for both learning and control. While numerous delay-compensation methods have been proposed for environments with constant delays, those with random delays remain largely unexplored due to their inherent variability and unpredictability. In this study, we propose a robust agent for decision-making under bounded random delays, termed the <em>conservative agent</em>. This agent reformulates the random-delay environment into a constant-delay surrogate, which enables any constant-delay method to be directly extended to random-delay environments without modifying their algorithmic structure. Apart from a maximum delay, the conservative agent does not require prior knowledge of the underlying delay distribution and maintains performance invariant to changes in the delay distribution as long as the maximum delay remains unchanged. We present a theoretical analysis of conservative agent and evaluate its performance on diverse continuous control tasks from the MuJoCo benchmarks. Empirical results demonstrate that it significantly outperforms existing baselines in terms of both asymptotic performance and sample efficiency.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108645"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146120912","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}

引用次数: 0

A knowledge-driven self-supervised learning method for enhancing EEG-based emotion recognition 一种增强基于脑电图的情绪识别的知识驱动自监督学习方法。

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-02-02 DOI: 10.1016/j.neunet.2026.108676

Hanqi Wang , Jingyu Zhang , Peng Ye , Kun Yang , Jichuan Xiong , Xuefeng Liu , Tao Chen , Liang Song

Emotion recognition brain-computer interface (BCI) using electroencephalography (EEG) is crucial for human-computer interaction, medicine, and neuroscience. However, the scarcity of labeled EEG data limits progress in this field. To address this, self-supervised learning has gained attention as a promising approach. Despite its potential, self-supervised methods face two key challenges: (1) ensuring emotion-related information is effectively preserved, as its loss can degrade emotion recognition performance, and (2) overcoming inter-subject variability in EEG signals, which hinders generalization across subjects. To tackle these issues, we propose a novel knowledge-driven self-supervised learning framework for EEG emotion recognition. Our method incorporates domain knowledge to approximate the extraction of statistical feature differential entropy (DE), aiming to preserve emotion-related and generalizable information. The framework consists of two cascaded components as hard and soft alignments: a multi-branch convolutional differential entropy learning (MCDEL) module that simulates the DE extraction process, and a contrastive entropy alignment (CEA) module that exposes complex emotional semantics in high-dimensional space. Experiment results show that our method exhibits superior performance over existing self-supervised methods. The subject-independent mean accuracy and standard deviation of our method reached 84.48% ± 5.79 on SEED and 67.64% ± 6.35 and 68.63% ± 7.77 on the Arousal and Valence dimensions of DREAMER, respectively. We conduct an ablation study to demonstrate the contribution of each proposed component. Moreover, the t-SNE visualization intuitively presents the effect of our method on reducing inter-subject variability and discriminating emotional states.

基于脑电图（EEG）的情绪识别脑机接口（BCI）在人机交互、医学和神经科学等领域具有重要意义。然而，标记脑电图数据的稀缺性限制了这一领域的进展。为了解决这个问题，自我监督学习作为一种有前途的方法得到了关注。尽管具有潜力，但自监督方法面临两个关键挑战：(1)确保情绪相关信息得到有效保存，因为情绪相关信息的丢失会降低情绪识别的性能；(2)克服脑电信号在受试者之间的可变性，这阻碍了受试者之间的泛化。为了解决这些问题，我们提出了一种新的知识驱动的自监督学习框架。该方法结合领域知识来近似提取统计特征微分熵（DE），旨在保留情感相关和可推广的信息。该框架由两个级联组件组成，分别为硬对齐和软对齐：模拟DE提取过程的多分支卷积微分熵学习（MCDEL）模块，以及在高维空间中暴露复杂情感语义的对比熵对齐（CEA）模块。实验结果表明，该方法优于现有的自监督方法。该方法在SEED维度上的平均正确率为84.48% ± 5.79，在dream的唤醒维度和效价维度上的平均正确率为67.64% ± 6.35，标准差为68.63% ± 7.77。我们进行了消融研究，以证明每个提出的组成部分的贡献。此外，t-SNE可视化直观地展示了我们的方法在减少主体间变异性和区分情绪状态方面的效果。

{"title":"A knowledge-driven self-supervised learning method for enhancing EEG-based emotion recognition","authors":"Hanqi Wang , Jingyu Zhang , Peng Ye , Kun Yang , Jichuan Xiong , Xuefeng Liu , Tao Chen , Liang Song","doi":"10.1016/j.neunet.2026.108676","DOIUrl":"10.1016/j.neunet.2026.108676","url":null,"abstract":"<div><div>Emotion recognition brain-computer interface (BCI) using electroencephalography (EEG) is crucial for human-computer interaction, medicine, and neuroscience. However, the scarcity of labeled EEG data limits progress in this field. To address this, self-supervised learning has gained attention as a promising approach. Despite its potential, self-supervised methods face two key challenges: (1) ensuring emotion-related information is effectively preserved, as its loss can degrade emotion recognition performance, and (2) overcoming inter-subject variability in EEG signals, which hinders generalization across subjects. To tackle these issues, we propose a novel knowledge-driven self-supervised learning framework for EEG emotion recognition. Our method incorporates domain knowledge to approximate the extraction of statistical feature differential entropy (DE), aiming to preserve emotion-related and generalizable information. The framework consists of two cascaded components as hard and soft alignments: a multi-branch convolutional differential entropy learning (MCDEL) module that simulates the DE extraction process, and a contrastive entropy alignment (CEA) module that exposes complex emotional semantics in high-dimensional space. Experiment results show that our method exhibits superior performance over existing self-supervised methods. The subject-independent mean accuracy and standard deviation of our method reached 84.48% ± 5.79 on SEED and 67.64% ± 6.35 and 68.63% ± 7.77 on the Arousal and Valence dimensions of DREAMER, respectively. We conduct an ablation study to demonstrate the contribution of each proposed component. Moreover, the t-SNE visualization intuitively presents the effect of our method on reducing inter-subject variability and discriminating emotional states.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108676"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146158637","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}

引用次数: 0

Adversarially robust neural network decision boundaries via tropical geometry 基于热带几何的对抗鲁棒神经网络决策边界

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-01-20 DOI: 10.1016/j.neunet.2026.108624

Kurt Pasque , Christopher Teska , Ruriko Yoshida , Keiji Miura , Jefferson Huang

We introduce a simple, easy to implement, and computationally efficient tropical convolutional neural network architecture that is robust against adversarial attacks. We exploit the tropical nature of piece-wise linear neural networks by embedding the data in the tropical projective torus. This can be accomplished with a single additional hidden layer called a tropical embedding layer, and can in principle be added to any neural network architecture. We study the geometry of the resulting decision boundary, and find that like adversarial training and various regularization techniques that have been proposed, adding the tropical embedding layer tends to increase the number of linear regions associated with the decision boundaries. Our numerical experiments show that our approach achieves state-of-the-art levels of adversarial robustness, while requiring much less computational time than adversarial training.

我们介绍了一个简单、易于实现、计算效率高的热带卷积神经网络架构，该架构对对抗性攻击具有鲁棒性。我们通过将数据嵌入热带投影环面来利用分段线性神经网络的热带特性。这可以通过一个称为热带嵌入层的附加隐藏层来完成，原则上可以添加到任何神经网络架构中。我们研究了生成的决策边界的几何形状，发现与已经提出的对抗训练和各种正则化技术一样，添加热带嵌入层倾向于增加与决策边界相关的线性区域的数量。我们的数值实验表明，我们的方法达到了最先进的对抗鲁棒性水平，同时所需的计算时间比对抗训练少得多。

引用次数: 0

Gender-independent kinship verification network via fuzzy disentangling and multi-metric inference 基于模糊解缠和多度量推理的性别无关亲属关系验证网络

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-02-06 DOI: 10.1016/j.neunet.2026.108691

Lei Li , Quan Zhou , Shanshan Gao , Chaoran Cui , Zhaoqiang Xia

Kinship verification aims to determine whether two individuals share a familial relationship based on facial information. Cross-gender relationships (i.e., Father-Daughter and Mother-Son) continue to face formidable challenges due to the diversity and uncertainty of genetic inheritance. Existing studies primarily focus on extracting robust features and measuring similarity, with limited attention given to the fuzziness of gender differences. To address this issue, this paper proposes a kinship verification framework based on a fuzzy neural network, which adaptively extracts gender-independent kinship features and handles relationship fuzziness to improve cross-gender verification performance. Specifically, the Swin Transformer, which has demonstrated excellent performance in facial analysis, is employed to extract initial features. A fuzzy neural network is then designed to disentangle gender and kinship features, with a gender recognition task introduced to further enhance this disentanglement and improve the gender independence of kinship features. Subsequently, a multi-metric fuzzy reasoning module is adopted to integrate kinship features, extract latent kinship cues, and leverage a contrastive loss function to effectively mine potential negative sample information, thereby significantly enhancing the model’s robustness. Experimental results on three publicly available datasets demonstrate that the proposed method achieves state-of-the-art performance.

亲属关系验证的目的是根据面部信息确定两个人是否具有家庭关系。由于基因遗传的多样性和不确定性，跨性别关系（即父女关系和母子关系）继续面临着巨大的挑战。现有的研究主要集中在提取鲁棒特征和度量相似性上，对性别差异的模糊性关注较少。针对这一问题，本文提出了一种基于模糊神经网络的亲属关系验证框架，该框架自适应提取与性别无关的亲属关系特征，并对关系模糊性进行处理，以提高跨性别验证的性能。具体而言，采用在人脸分析中表现优异的Swin Transformer提取初始特征。然后设计了模糊神经网络来解开性别和亲属特征的纠缠，并引入性别识别任务来进一步增强这种纠缠，提高亲属特征的性别独立性。随后，采用多度量模糊推理模块整合亲属关系特征，提取潜在的亲属关系线索，并利用对比损失函数有效挖掘潜在的负样本信息，显著增强了模型的鲁棒性。在三个公开数据集上的实验结果表明，该方法达到了最先进的性能。

{"title":"Gender-independent kinship verification network via fuzzy disentangling and multi-metric inference","authors":"Lei Li , Quan Zhou , Shanshan Gao , Chaoran Cui , Zhaoqiang Xia","doi":"10.1016/j.neunet.2026.108691","DOIUrl":"10.1016/j.neunet.2026.108691","url":null,"abstract":"<div><div>Kinship verification aims to determine whether two individuals share a familial relationship based on facial information. Cross-gender relationships (i.e., Father-Daughter and Mother-Son) continue to face formidable challenges due to the diversity and uncertainty of genetic inheritance. Existing studies primarily focus on extracting robust features and measuring similarity, with limited attention given to the fuzziness of gender differences. To address this issue, this paper proposes a kinship verification framework based on a fuzzy neural network, which adaptively extracts gender-independent kinship features and handles relationship fuzziness to improve cross-gender verification performance. Specifically, the Swin Transformer, which has demonstrated excellent performance in facial analysis, is employed to extract initial features. A fuzzy neural network is then designed to disentangle gender and kinship features, with a gender recognition task introduced to further enhance this disentanglement and improve the gender independence of kinship features. Subsequently, a multi-metric fuzzy reasoning module is adopted to integrate kinship features, extract latent kinship cues, and leverage a contrastive loss function to effectively mine potential negative sample information, thereby significantly enhancing the model’s robustness. Experimental results on three publicly available datasets demonstrate that the proposed method achieves state-of-the-art performance.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108691"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174307","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}

引用次数: 0

Cross-view contrastive representation learning on meta-path induced graphs with node features for bundle recommendation 基于节点特征的元路径诱导图的交叉视图对比表示学习。

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-01-29 DOI: 10.1016/j.neunet.2026.108669

Peng Zhang , Zhendong Niu , Ru Ma , Shunpan Liang , Fuzhi Zhang

Bundle recommendation is designed to suggest a set of correlated items to a user in a holistic manner rather than recommending these items separately. Recent methods introduce contrastive learning (CL) to refine the node representations learned from different graphs (generally termed the item and bundle views) for better recommendation performance. Unfortunately, these methods have two deficiencies. Firstly, few of them explicitly model the user-user and bundle-bundle relationships simultaneously from both the item and bundle views, leading to the underutilization of high-order relationships between users (bundles). Secondly, they use InfoNCE as the contrastive loss, which overlooks the graph structure as supervised signals in defining positive (negative) samples, resulting in anchor-like nodes being treated as negative samples. To tackle these deficiencies, an approach of cross-view contrastive representation learning (CCRL) on meta-path induced graphs with node features is proposed for bundle recommendation. First, we introduce meta-path to model the user-user and bundle-bundle relationships as meta-path induced graphs with node features from both the item and bundle views. Second, we perform graph representation learning on the meta-path induced graphs with node features to procure the user (bundle) representations and introduce a contrastive loss that supports multiple positive samples to build a cross-view graph CL mechanism for refining the learned user (bundle) representations. Finally, the model is trained with a joint optimization objective. Experiments on the benchmark datasets manifest that our approach surpasses the baselines in bundle recommendation.

捆绑推荐的目的是以整体的方式向用户推荐一组相关的项目，而不是单独推荐这些项目。最近的方法引入了对比学习（CL），以改进从不同图（通常称为项目和束视图）学习到的节点表示，以获得更好的推荐性能。不幸的是，这些方法有两个缺陷。首先，它们很少同时从项视图和包视图显式地建模用户-用户和包-包关系，导致用户（包）之间的高阶关系未得到充分利用。其次，他们使用InfoNCE作为对比损失，在定义正（负）样本时忽略了图结构作为监督信号，导致锚点样节点被视为负样本。为了解决这些不足，提出了一种基于节点特征的元路径诱导图的交叉视图对比表示学习（cross-view comparative representation learning， CCRL）方法，用于包推荐。首先，我们引入元路径，将用户-用户和bundle-bundle关系建模为元路径诱导的图，其中包含来自项目视图和bundle视图的节点特征。其次，我们对具有节点特征的元路径诱导图进行图表示学习，以获得用户（束）表示，并引入支持多个正样本的对比损失，以构建交叉视图图CL机制，以精炼学习到的用户（束）表示。最后，用联合优化目标对模型进行训练。在基准数据集上的实验表明，我们的方法在包推荐方面优于基线。

{"title":"Cross-view contrastive representation learning on meta-path induced graphs with node features for bundle recommendation","authors":"Peng Zhang , Zhendong Niu , Ru Ma , Shunpan Liang , Fuzhi Zhang","doi":"10.1016/j.neunet.2026.108669","DOIUrl":"10.1016/j.neunet.2026.108669","url":null,"abstract":"<div><div>Bundle recommendation is designed to suggest a set of correlated items to a user in a holistic manner rather than recommending these items separately. Recent methods introduce <u>c</u>ontrastive <u>l</u>earning (CL) to refine the node representations learned from different graphs (generally termed the item and bundle views) for better recommendation performance. Unfortunately, these methods have two deficiencies. Firstly, few of them explicitly model the user-user and bundle-bundle relationships simultaneously from both the item and bundle views, leading to the underutilization of high-order relationships between users (bundles). Secondly, they use InfoNCE as the contrastive loss, which overlooks the graph structure as supervised signals in defining positive (negative) samples, resulting in anchor-like nodes being treated as negative samples. To tackle these deficiencies, an approach of <u>c</u>ross-view <u>c</u>ontrastive <u>r</u>epresentation <u>l</u>earning (CCRL) on meta-path induced graphs with node features is proposed for bundle recommendation. First, we introduce meta-path to model the user-user and bundle-bundle relationships as meta-path induced graphs with node features from both the item and bundle views. Second, we perform graph representation learning on the meta-path induced graphs with node features to procure the user (bundle) representations and introduce a contrastive loss that supports multiple positive samples to build a cross-view graph CL mechanism for refining the learned user (bundle) representations. Finally, the model is trained with a joint optimization objective. Experiments on the benchmark datasets manifest that our approach surpasses the baselines in bundle recommendation.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108669"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146114722","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}

引用次数: 0

Improved exponential stability of time delay neural networks via separated-matrix-based integral inequalities 利用分离矩阵积分不等式改进时滞神经网络的指数稳定性。

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-01-27 DOI: 10.1016/j.neunet.2026.108643

Yuanyuan Zhang, Xinzuo Ma, Seakweng Vong

This paper studies the exponential stability of neural networks with time delays. A separated-matrix-based integral inequality is proposed to incorporate more delay information. It not only reflects the information of each component in the state-related vector but also considers the cross terms among the three components, significantly reducing the inherent conservativeness of traditional methods. By constructing a Lyapunov-Krasovskii functional with separation-matrix-based integral and a linear matrix inequality framework via quadratic negative definiteness, less conservative stability criteria are established. Two numerical examples demonstrate the method superiority in maximum allowable delay bounds and computational efficiency compared to existing approaches.

研究了具有时滞的神经网络的指数稳定性。提出了一种基于分离矩阵的积分不等式来包含更多的延迟信息。它不仅反映了状态相关向量中每个分量的信息，而且考虑了三个分量之间的交叉项，大大降低了传统方法固有的保守性。通过构造基于分离矩阵积分的Lyapunov-Krasovskii泛函和基于二次负确定性的线性矩阵不等式框架，建立了低保守性稳定性判据。两个算例表明，该方法在最大允许延迟界和计算效率方面优于现有方法。

引用次数: 0

Adaptive sample repulsion against class-specific counterfactuals for explainable imbalanced classification 针对可解释的不平衡分类的类特定反事实的自适应样本排斥。

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-01-30 DOI: 10.1016/j.neunet.2026.108652

Yu Hao , Xin Gao , Xinping Diao , Yuan Li , Yukun Lin , Tianyang Chen , Qiangwei Li , Jiawen Lu

Enhancing model classification capability for samples within overlapping regions in complex feature spaces remains a key challenge in imbalanced classification research. Existing mainstream methods at the data-level and algorithm-level primarily rely on original sample distribution information to reduce overlap impact, without deeply modeling the causal relationship between features and labels. Furthermore, these approaches often overlook instance-level explanations that could guide deep discriminative information mining for samples of different classes in overlapping regions, thus the improvement on classification performance and model credibility may be constrained. This paper proposes an explainable imbalanced classification framework with adaptive sample repulsion against class-specific counterfactuals (CSCF-SR), forming a closed-loop between explanation generation and classification decisions by dynamically regulating the feature-space distribution through generated counterfactual samples. Two core phases are jointly optimized. (1) Counterfactual searching: a class-specific dual-actor architecture based on reinforcement learning decouples perturbation policy learning for majority and minority classes. A multi-step dynamic perturbation mechanism is designed to control counterfactual search behavior more precisely and smoothly, effectively generating reliable counterfactual samples. (2) Adaptive sample repulsion against counterfactuals: exploiting the inter-class discriminative information in displacement vectors between counterfactual and original samples, each original sample is adaptively perturbed along the direction opposite to its counterfactual. This fine-grained regulation gradually displaces samples from the overlapping region and clarifies class boundaries. Experiments on 50 imbalanced datasets demonstrate that CSCF-SR has a performance advantage over 27 typical imbalanced classification methods on both F1-score and G-mean, with more pronounced improvements on 25 datasets with severe class overlap.

提高模型对复杂特征空间中重叠区域样本的分类能力一直是不平衡分类研究的关键挑战。现有数据级和算法级的主流方法主要依靠原始样本分布信息来减少重叠影响，没有对特征与标签之间的因果关系进行深入建模。此外，这些方法往往忽略了实例级解释，而实例级解释可以指导对重叠区域中不同类别的样本进行深度判别信息挖掘，从而限制了分类性能和模型可信度的提高。本文提出了一种针对类特定反事实的自适应样本排斥的可解释不平衡分类框架（CSCF-SR），通过生成的反事实样本动态调节特征空间分布，在解释生成和分类决策之间形成闭环。两个核心相联合优化。(1)反事实搜索：一种基于强化学习的类特定双参与者架构，解耦了多数类和少数类的扰动策略学习。设计了多步动态摄动机制，更精确、流畅地控制反事实搜索行为，有效地生成可靠的反事实样本。(2)自适应样本对反事实的排斥：利用反事实和原始样本之间位移向量中的类间判别信息，每个原始样本沿与其反事实相反的方向自适应扰动。这种细粒度的调节逐渐取代了重叠区域的样本，并澄清了类边界。在50个不平衡数据集上的实验表明，CSCF-SR在f1得分和g均值上都比27种典型的不平衡分类方法具有性能优势，在25个类重叠严重的数据集上的改进更为明显。

{"title":"Adaptive sample repulsion against class-specific counterfactuals for explainable imbalanced classification","authors":"Yu Hao , Xin Gao , Xinping Diao , Yuan Li , Yukun Lin , Tianyang Chen , Qiangwei Li , Jiawen Lu","doi":"10.1016/j.neunet.2026.108652","DOIUrl":"10.1016/j.neunet.2026.108652","url":null,"abstract":"<div><div>Enhancing model classification capability for samples within overlapping regions in complex feature spaces remains a key challenge in imbalanced classification research. Existing mainstream methods at the data-level and algorithm-level primarily rely on original sample distribution information to reduce overlap impact, without deeply modeling the causal relationship between features and labels. Furthermore, these approaches often overlook instance-level explanations that could guide deep discriminative information mining for samples of different classes in overlapping regions, thus the improvement on classification performance and model credibility may be constrained. This paper proposes an explainable imbalanced classification framework with adaptive sample repulsion against class-specific counterfactuals (CSCF-SR), forming a closed-loop between explanation generation and classification decisions by dynamically regulating the feature-space distribution through generated counterfactual samples. Two core phases are jointly optimized. (1) Counterfactual searching: a class-specific dual-actor architecture based on reinforcement learning decouples perturbation policy learning for majority and minority classes. A multi-step dynamic perturbation mechanism is designed to control counterfactual search behavior more precisely and smoothly, effectively generating reliable counterfactual samples. (2) Adaptive sample repulsion against counterfactuals: exploiting the inter-class discriminative information in displacement vectors between counterfactual and original samples, each original sample is adaptively perturbed along the direction opposite to its counterfactual. This fine-grained regulation gradually displaces samples from the overlapping region and clarifies class boundaries. Experiments on 50 imbalanced datasets demonstrate that CSCF-SR has a performance advantage over 27 typical imbalanced classification methods on both F1-score and G-mean, with more pronounced improvements on 25 datasets with severe class overlap.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108652"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146120771","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}

引用次数: 0

Multi-step first: A lightweight deep reinforcement learning strategy for robust continuous control with partial observability 多步优先：面向部分可观察性鲁棒连续控制的轻量级深度强化学习策略。

IF 6.3 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2025-12-27 DOI: 10.1016/j.neunet.2025.108521

Lingheng Meng , Rob Gorbet , Michael Burke , Dana Kulić

Deep Reinforcement Learning (DRL) has made considerable advances in simulated and physical robot control tasks, especially when problems admit a fully observed Markov Decision Process (MDP) formulation. When observations only partially capture the underlying state, the problem becomes a Partially Observable MDP (POMDP), and performance rankings between algorithms can change. We empirically compare Proximal Policy Optimization (PPO), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Soft Actor-Critic (SAC) on representative POMDP variants of continuous-control benchmarks. Contrary to widely reported MDP results where TD3 and SAC typically outperform PPO, we observe an inversion: PPO attains higher robustness under partial observability. We attribute this to the stabilizing effect of multi-step bootstrapping. Furthermore, incorporating multi-step targets into TD3 (MTD3) and SAC (MSAC) improves their robustness. These findings provide practical guidance for selecting and adapting DRL algorithms in partially observable settings without requiring new theoretical machinery.

深度强化学习（DRL）在模拟和物理机器人控制任务方面取得了相当大的进步，特别是当问题承认完全观察到的马尔可夫决策过程（MDP）公式时。当观察结果只能部分捕获底层状态时，问题就变成了部分可观察的MDP (POMDP)，并且算法之间的性能排名可能会发生变化。我们在连续控制基准的代表性POMDP变体上实证比较了近端策略优化（PPO）、双延迟深度确定性策略梯度（TD3）和软行为者-评论家（SAC）。与广泛报道的MDP结果相反，TD3和SAC通常优于PPO，我们观察到一个反转：PPO在部分可观察性下具有更高的鲁棒性。我们将此归因于多步自举的稳定效应。此外，将多步目标纳入TD3 （MTD3）和SAC （MSAC）中，提高了它们的鲁棒性。这些发现为在不需要新的理论机制的情况下在部分可观察的环境中选择和适应DRL算法提供了实践指导。

{"title":"Multi-step first: A lightweight deep reinforcement learning strategy for robust continuous control with partial observability","authors":"Lingheng Meng , Rob Gorbet , Michael Burke , Dana Kulić","doi":"10.1016/j.neunet.2025.108521","DOIUrl":"10.1016/j.neunet.2025.108521","url":null,"abstract":"<div><div>Deep Reinforcement Learning (DRL) has made considerable advances in simulated and physical robot control tasks, especially when problems admit a fully observed Markov Decision Process (MDP) formulation. When observations only partially capture the underlying state, the problem becomes a Partially Observable MDP (POMDP), and performance rankings between algorithms can change. We empirically compare Proximal Policy Optimization (PPO), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Soft Actor-Critic (SAC) on representative POMDP variants of continuous-control benchmarks. Contrary to widely reported MDP results where TD3 and SAC typically outperform PPO, we observe an inversion: PPO attains higher robustness under partial observability. We attribute this to the stabilizing effect of multi-step bootstrapping. Furthermore, incorporating multi-step targets into TD3 (MTD3) and SAC (MSAC) improves their robustness. These findings provide practical guidance for selecting and adapting DRL algorithms in partially observable settings without requiring new theoretical machinery.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108521"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146138146","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}

引用次数: 0