Neural Networks最新文献_第4页

MS-STFNN: A multi-scale spatio-temporal fusion neural network for fMRI-based depression diagnosis MS-STFNN：基于fmri的多尺度时空融合神经网络抑郁症诊断

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

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-02-09 DOI: 10.1016/j.neunet.2026.108685

Mengni Zhou , Miaofeng Wang , Rongkun Mi , Yan Niu , Xiaohong Cui , Ran Gao , Yuxi Li , Xin Wen , Jie Xiang

Major depressive disorder (MDD) is a common mental disorder. Current clinical diagnosis primarily relies on subjective scales, underscoring an urgent need to develop objective neuroimaging diagnostic methods. Brain network analysis and deep learning techniques based on functional magnetic resonance imaging (fMRI) have been proven effective in uncovering abnormal spatial patterns associated with depression. However, the temporal dynamics of brain activity are also equally critical for understanding the neural mechanisms of MDD. Despite this importance, existing studies still suffer from insufficient characterization of spatio-temporal information. This study proposes a novel multi-scale spatio-temporal fusion neural network (MS-STFNN) that captures multi-granularity spatial features of the brain from local to global levels, while incorporating dynamic functional connectivity (DFC) and raw fMRI sequences to characterize time-varying properties at multiple resolution levels. Finally, effective classification of different depression subtypes is achieved through multi-scale feature fusion (MSFF). The results show that the proposed model outperforms baseline models across multiple subtype classification tasks. Ablation study further demonstrates the effectiveness of multi-granularity spatial feature extraction, multi-resolution temporal representation, and the spatio-temporal fusion strategy. This study provides a reliable framework for the objective diagnosis of depression, addressing the limitations of traditional subjective assessments, while also offering new insights into the efficient utilization of spatio-temporal features in brain network analysis.

重度抑郁症（MDD）是一种常见的精神障碍。目前的临床诊断主要依赖于主观量表，强调迫切需要发展客观的神经影像学诊断方法。基于功能磁共振成像（fMRI）的脑网络分析和深度学习技术已被证明在发现与抑郁症相关的异常空间模式方面是有效的。然而，大脑活动的时间动态对于理解重度抑郁症的神经机制也同样重要。尽管如此，现有的研究仍然存在对时空信息表征不足的问题。本研究提出了一种新的多尺度时空融合神经网络（MS-STFNN），该网络可以捕获从局部到全局的多粒度大脑空间特征，同时结合动态功能连接（DFC）和原始fMRI序列来表征多分辨率水平下的时变特性。最后，通过多尺度特征融合（MSFF）实现不同抑郁亚型的有效分类。结果表明，该模型在多个子类型分类任务上优于基线模型。消融研究进一步验证了多粒度空间特征提取、多分辨率时间表示和时空融合策略的有效性。本研究为抑郁症的客观诊断提供了一个可靠的框架，解决了传统主观评估的局限性，同时也为有效利用脑网络分析中的时空特征提供了新的见解。

{"title":"MS-STFNN: A multi-scale spatio-temporal fusion neural network for fMRI-based depression diagnosis","authors":"Mengni Zhou , Miaofeng Wang , Rongkun Mi , Yan Niu , Xiaohong Cui , Ran Gao , Yuxi Li , Xin Wen , Jie Xiang","doi":"10.1016/j.neunet.2026.108685","DOIUrl":"10.1016/j.neunet.2026.108685","url":null,"abstract":"<div><div>Major depressive disorder (MDD) is a common mental disorder. Current clinical diagnosis primarily relies on subjective scales, underscoring an urgent need to develop objective neuroimaging diagnostic methods. Brain network analysis and deep learning techniques based on functional magnetic resonance imaging (fMRI) have been proven effective in uncovering abnormal spatial patterns associated with depression. However, the temporal dynamics of brain activity are also equally critical for understanding the neural mechanisms of MDD. Despite this importance, existing studies still suffer from insufficient characterization of spatio-temporal information. This study proposes a novel multi-scale spatio-temporal fusion neural network (MS-STFNN) that captures multi-granularity spatial features of the brain from local to global levels, while incorporating dynamic functional connectivity (DFC) and raw fMRI sequences to characterize time-varying properties at multiple resolution levels. Finally, effective classification of different depression subtypes is achieved through multi-scale feature fusion (MSFF). The results show that the proposed model outperforms baseline models across multiple subtype classification tasks. Ablation study further demonstrates the effectiveness of multi-granularity spatial feature extraction, multi-resolution temporal representation, and the spatio-temporal fusion strategy. This study provides a reliable framework for the objective diagnosis of depression, addressing the limitations of traditional subjective assessments, while also offering new insights into the efficient utilization of spatio-temporal features in brain network analysis.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108685"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174598","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

On the inherent robustness of one-stage object detection against out-of-distribution data 针对非分布数据的单阶段目标检测的固有鲁棒性

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

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-02-04 DOI: 10.1016/j.neunet.2026.108683

Aitor Martinez-Seras , Javier Del Ser , Aitzol Olivares-Rad , Alain Andres , Pablo Garcia-Bringas

Robustness is a fundamental aspect for developing safe and trustworthy models, particularly when they are deployed in the open world. In this work we analyze the inherent capability of one-stage object detectors to robustly operate in the presence of out-of-distribution (OoD) data. Specifically, we propose a novel detection algorithm for detecting unknown objects in image data, which leverages the features extracted by the model from each sample. Differently from other recent approaches in the literature, our proposal does not require retraining the object detector, thereby allowing for the use of pretrained models. Our proposed OoD detector exploits the application of supervised dimensionality reduction techniques to mitigate the effects of the curse of dimensionality on the features extracted by the model. Furthermore, it utilizes high-resolution feature maps to identify potential unknown objects in an unsupervised fashion. Our experiments analyze the Pareto trade-off between the performance detecting known and unknown objects resulting from different algorithmic configurations and inference confidence thresholds. We also compare the performance of our proposed algorithm to that of logits-based post-hoc OoD methods, as well as possible fusion strategies. Finally, we discuss on the competitiveness of all tested methods against state-of-the-art OoD approaches for object detection models over the recently published Unknown Object Detection benchmark. The obtained results verify that the performance of avant-garde post-hoc OoD detectors can be further improved when combined with our proposed algorithm.

健壮性是开发安全和可信模型的基本方面，特别是当它们部署在开放世界中时。在这项工作中，我们分析了一级目标检测器在存在非分布（OoD）数据的情况下鲁棒运行的固有能力。具体来说，我们提出了一种新的检测算法来检测图像数据中的未知物体，该算法利用模型从每个样本中提取的特征。与文献中其他最近的方法不同，我们的建议不需要重新训练目标检测器，从而允许使用预训练模型。我们提出的OoD检测器利用监督降维技术的应用来减轻维数诅咒对模型提取的特征的影响。此外，它利用高分辨率特征图以无监督的方式识别潜在的未知物体。我们的实验分析了不同算法配置和推断置信阈值导致的已知和未知对象检测性能之间的帕累托权衡。我们还将我们提出的算法的性能与基于逻辑学的事后OoD方法以及可能的融合策略进行了比较。最后，我们讨论了在最近发布的未知对象检测基准上，所有测试方法与最先进的对象检测模型的OoD方法的竞争力。实验结果表明，结合本文提出的算法，可以进一步提高前卫的事后OoD检测器的性能。

{"title":"On the inherent robustness of one-stage object detection against out-of-distribution data","authors":"Aitor Martinez-Seras , Javier Del Ser , Aitzol Olivares-Rad , Alain Andres , Pablo Garcia-Bringas","doi":"10.1016/j.neunet.2026.108683","DOIUrl":"10.1016/j.neunet.2026.108683","url":null,"abstract":"<div><div>Robustness is a fundamental aspect for developing safe and trustworthy models, particularly when they are deployed in the open world. In this work we analyze the inherent capability of one-stage object detectors to robustly operate in the presence of out-of-distribution (OoD) data. Specifically, we propose a novel detection algorithm for detecting unknown objects in image data, which leverages the features extracted by the model from each sample. Differently from other recent approaches in the literature, our proposal does not require retraining the object detector, thereby allowing for the use of pretrained models. Our proposed OoD detector exploits the application of supervised dimensionality reduction techniques to mitigate the effects of the curse of dimensionality on the features extracted by the model. Furthermore, it utilizes high-resolution feature maps to identify potential unknown objects in an unsupervised fashion. Our experiments analyze the Pareto trade-off between the performance detecting known and unknown objects resulting from different algorithmic configurations and inference confidence thresholds. We also compare the performance of our proposed algorithm to that of logits-based post-hoc OoD methods, as well as possible fusion strategies. Finally, we discuss on the competitiveness of all tested methods against state-of-the-art OoD approaches for object detection models over the recently published Unknown Object Detection benchmark. The obtained results verify that the performance of avant-garde post-hoc OoD detectors can be further improved when combined with our proposed algorithm.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108683"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174308","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

Exploring financial sentiment analysis via fine-tuning large language model and attributed graph neural network 通过微调大语言模型和属性图神经网络探索金融情绪分析。

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

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-01-22 DOI: 10.1016/j.neunet.2026.108620

Zongshen Mu , Yujie Wan , Yueting Zhuang , Jie Tan , Hong Cheng , Yueyang Wang

Financial sentiment analysis (FSA) refers to the task of classifying textual content into predefined sentiment categories to analyze their potential impacts on financial market fluctuations. However, directly applying these pre-trained LLMs to FSA still poses significant challenges. Existing approaches fail to align with domain-specific objectives and struggle to adapt to customized financial data schemas. Moreover, these LLMs predict the stock change primarily depending on its own information, failing to take into account cross-impact among relevant stocks. In this paper, we propose a novel framework that synergizes an LLM with a Graph Neural Network (GNN) to model stock price dynamics, leveraging stock sentiment signals extracted from financial news. Specifically, we employ the open-source Llama-3-8B model as the backbone, then enhance its sensitivity to financial sentiment patterns through supervised fine-tuning (SFT) and direct preference optimization (DPO) techniques. Leveraging the sentiment outputs from the fine-tuned LLM, we design a GNN to enhance stock representations and model cross-asset dependencies via two types of text-attributed graphs, which dynamically encode time-varying price correlations. Experiments on the Chinese A-share market demonstrate that financial sentiment significantly influences stock price variations. Our framework outperforms previous baselines and exhibits an average improvement of 50% in Sharpe ratio.

金融情绪分析（Financial sentiment analysis， FSA）是指将文本内容分类到预定义的情绪类别中，分析其对金融市场波动的潜在影响。然而，将这些预先训练的法学硕士直接应用于金融服务管理局仍然面临着重大挑战。现有的方法不能与特定于领域的目标保持一致，并且难以适应定制的财务数据模式。而且，这些llm预测股票变动主要依靠自身的信息，没有考虑相关股票之间的交叉影响。在本文中，我们提出了一个新的框架，将LLM与图神经网络（GNN）协同作用，利用从金融新闻中提取的股票情绪信号来模拟股票价格动态。具体而言，我们采用开源的lama-3- 8b模型作为主干，然后通过监督微调（SFT）和直接偏好优化（DPO）技术增强其对金融情绪模式的敏感性。利用微调LLM的情感输出，我们设计了一个GNN来增强股票表示，并通过两种类型的文本属性图来建模跨资产依赖关系，这两种类型的文本属性图动态编码时变价格相关性。对中国a股市场的实验表明，金融情绪显著影响股价波动。我们的框架优于以前的基准，夏普比率平均提高了50%。

{"title":"Exploring financial sentiment analysis via fine-tuning large language model and attributed graph neural network","authors":"Zongshen Mu , Yujie Wan , Yueting Zhuang , Jie Tan , Hong Cheng , Yueyang Wang","doi":"10.1016/j.neunet.2026.108620","DOIUrl":"10.1016/j.neunet.2026.108620","url":null,"abstract":"<div><div>Financial sentiment analysis (FSA) refers to the task of classifying textual content into predefined sentiment categories to analyze their potential impacts on financial market fluctuations. However, directly applying these pre-trained LLMs to FSA still poses significant challenges. Existing approaches fail to align with domain-specific objectives and struggle to adapt to customized financial data schemas. Moreover, these LLMs predict the stock change primarily depending on its own information, failing to take into account cross-impact among relevant stocks. In this paper, we propose a novel framework that synergizes an LLM with a Graph Neural Network (GNN) to model stock price dynamics, leveraging stock sentiment signals extracted from financial news. Specifically, we employ the open-source Llama-3-8B model as the backbone, then enhance its sensitivity to financial sentiment patterns through supervised fine-tuning (SFT) and direct preference optimization (DPO) techniques. Leveraging the sentiment outputs from the fine-tuned LLM, we design a GNN to enhance stock representations and model cross-asset dependencies via two types of text-attributed graphs, which dynamically encode time-varying price correlations. Experiments on the Chinese A-share market demonstrate that financial sentiment significantly influences stock price variations. Our framework outperforms previous baselines and exhibits an average improvement of 50% in Sharpe ratio.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108620"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146114716","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

Dynamic bidirectional data recomposition for efficient road garbage segmentation in semi-supervised learning 基于半监督学习的道路垃圾高效分割的动态双向数据重组。

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.2026.108655

Suheng Peng , Jiacai Liao , Libo Cao

Deep neural networks excel in road garbage segmentation but require costly pixel-level annotations. Balancing accuracy and annotation costs is a key bottleneck in urban garbage management. Semi-supervised learning (SSL) reduces the dependence on annotations by utilizing large amounts of unlabeled data. However, existing methods face a key challenge: under extreme annotation imbalance, the scarce labeled data often lacks diversity. This leads to repeated reuse during training, preventing full information exploitation and causing model performance stagnation. Specifically, we introduce the Dynamic Bidirectional Data Recomposition (DBDR) mechanism, which dynamically adjusts the bidirectional information interaction between labeled and unlabeled data to solve the problem of representation stagnation. Early training: The labeled data is integrated into the unlabeled data stream according to confidence levels, guiding the model to prioritize capturing and stabilizing basic semantic prototypes. Mid-training: A dynamic memory queue is constructed to quantify the evolution of model confidence states over time. We use dynamic thresholds and dual validation to trigger a reverse flow of knowledge from unlabeled to labeled supervision. This breaks local optima in the encoder and reshapes the semantic decision boundaries. DBDR can be integrated into any current mainstream SSL framework. On a real-world road garbage dataset, DBDR delivers a significant performance boost over all five state-of-the-art baseline models. Ablation experiments validate its key improvements in the segmentation of confusing targets (e.g., plastic, paper). This research provides an economically feasible solution for future smart city waste management technologies.

深度神经网络擅长道路垃圾分割，但需要昂贵的像素级标注。平衡准确性和标注成本是城市垃圾管理的关键瓶颈。半监督学习（SSL）通过利用大量未标记的数据来减少对注释的依赖。然而，现有方法面临着一个关键挑战：在标注极度不平衡的情况下，稀缺的标注数据往往缺乏多样性。这将导致训练期间的重复重用，从而阻止充分利用信息并导致模型性能停滞。具体来说，我们引入了动态双向数据重组（DBDR）机制，动态调整标记和未标记数据之间的双向信息交互，以解决表示停滞的问题。早期训练：根据置信度将标记的数据整合到未标记的数据流中，引导模型优先捕获和稳定基本语义原型。训练中期：构建一个动态记忆队列来量化模型置信状态随时间的演变。我们使用动态阈值和双重验证来触发从未标记监督到标记监督的反向知识流。这打破了编码器中的局部最优，并重塑了语义决策边界。DBDR可以集成到任何当前主流的SSL框架中。在现实世界的道路垃圾数据集上，DBDR比所有五个最先进的基线模型都提供了显着的性能提升。消融实验验证了其在分割混淆目标（如塑料、纸张）方面的关键改进。本研究为未来智慧城市废弃物管理技术提供了经济可行的解决方案。

{"title":"Dynamic bidirectional data recomposition for efficient road garbage segmentation in semi-supervised learning","authors":"Suheng Peng , Jiacai Liao , Libo Cao","doi":"10.1016/j.neunet.2026.108655","DOIUrl":"10.1016/j.neunet.2026.108655","url":null,"abstract":"<div><div>Deep neural networks excel in road garbage segmentation but require costly pixel-level annotations. Balancing accuracy and annotation costs is a key bottleneck in urban garbage management. Semi-supervised learning (SSL) reduces the dependence on annotations by utilizing large amounts of unlabeled data. However, existing methods face a key challenge: under extreme annotation imbalance, the scarce labeled data often lacks diversity. This leads to repeated reuse during training, preventing full information exploitation and causing model performance stagnation. Specifically, we introduce the Dynamic Bidirectional Data Recomposition (DBDR) mechanism, which dynamically adjusts the bidirectional information interaction between labeled and unlabeled data to solve the problem of representation stagnation. Early training: The labeled data is integrated into the unlabeled data stream according to confidence levels, guiding the model to prioritize capturing and stabilizing basic semantic prototypes. Mid-training: A dynamic memory queue is constructed to quantify the evolution of model confidence states over time. We use dynamic thresholds and dual validation to trigger a reverse flow of knowledge from unlabeled to labeled supervision. This breaks local optima in the encoder and reshapes the semantic decision boundaries. DBDR can be integrated into any current mainstream SSL framework. On a real-world road garbage dataset, DBDR delivers a significant performance boost over all five state-of-the-art baseline models. Ablation experiments validate its key improvements in the segmentation of confusing targets (e.g., plastic, paper). This research provides an economically feasible solution for future smart city waste management technologies.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108655"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146120838","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

HpMiX: A Disease ceRNA biomarker prediction framework driven by graph topology-constrained Mixup and hypergraph residual enhancement HpMiX：一个基于图拓扑约束混合和超图残差增强的疾病ceRNA生物标志物预测框架。

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.2026.108662

Xinfei Wang , Lan Huang , Yan Wang , Renchu Guan , Zhuhong You , Fengfeng Zhou , Yuqing Li , Yuan Fu

The competing endogenous RNA (ceRNA) regulatory network (CENA) plays a critical role in elucidating the molecular mechanisms of diseases. However, existing computational methods primarily focus on modeling local topological structures of biological networks, struggling to capture high-order regulatory relationships and global topological structures, thus limiting a deeper understanding of complex regulatory interactions.

To address this, we propose HpMiX, a Graph Topology-Constrained Mixup (GTCM) and hypergraph residual enhancement learning framework for the discovery of disease-related ceRNA biomarkers. This framework first constructs a CENA network encompassing multi-molecule associations, including miRNA, lncRNA, circRNA, and mRNA, and models higher-order regulatory relationships using K-hop hyperedges. Biologically meaningful initial features are then extracted from CENA via a multi-structure hypergraph weighted random walk method (MHWRW), integrating prior biological knowledge and regulatory information. Subsequently, graph topology-constrained Mixup and multi-head attention, combined with a residual hypergraph neural network, are employed to generate robust node embeddings with both local and global context, enabling the identification of potential disease-ceRNA biomarkers.

Prediction results across multiple disease biomarkers demonstrate that HpMiX significantly outperforms state-of-the-art methods, validating its effectiveness in biological regulatory network representation learning. Case studies further confirm that the framework can effectively identify differentially expressed ceRNAs in diseases, highlighting its potential as a tool for pre-screening high-probability disease biomarkers.

竞争内源性RNA （ceRNA）调控网络（CENA）在阐明疾病的分子机制中起着至关重要的作用。然而，现有的计算方法主要侧重于对生物网络的局部拓扑结构进行建模，难以捕捉高阶调控关系和全局拓扑结构，从而限制了对复杂调控相互作用的更深入理解。为了解决这个问题，我们提出了HpMiX，一个图拓扑约束混合（GTCM）和超图残差增强学习框架，用于发现与疾病相关的ceRNA生物标志物。该框架首先构建了一个包含多分子关联的CENA网络，包括miRNA、lncRNA、circRNA和mRNA，并使用K-hop超边缘模拟高阶调控关系。然后通过多结构超图加权随机漫步方法（MHWRW）从CENA中提取具有生物学意义的初始特征，整合先前的生物学知识和调控信息。随后，图拓扑约束的Mixup和多头注意，结合残差超图神经网络，用于生成具有局部和全局上下文的鲁棒节点嵌入，从而能够识别潜在的疾病- cerna生物标志物。多种疾病生物标志物的预测结果表明，HpMiX显著优于最先进的方法，验证了其在生物调节网络表示学习中的有效性。案例研究进一步证实，该框架可以有效识别疾病中差异表达的cerna，突出了其作为预筛选高概率疾病生物标志物工具的潜力。

{"title":"HpMiX: A Disease ceRNA biomarker prediction framework driven by graph topology-constrained Mixup and hypergraph residual enhancement","authors":"Xinfei Wang , Lan Huang , Yan Wang , Renchu Guan , Zhuhong You , Fengfeng Zhou , Yuqing Li , Yuan Fu","doi":"10.1016/j.neunet.2026.108662","DOIUrl":"10.1016/j.neunet.2026.108662","url":null,"abstract":"<div><div>The competing endogenous RNA (ceRNA) regulatory network (CENA) plays a critical role in elucidating the molecular mechanisms of diseases. However, existing computational methods primarily focus on modeling local topological structures of biological networks, struggling to capture high-order regulatory relationships and global topological structures, thus limiting a deeper understanding of complex regulatory interactions.</div><div>To address this, we propose HpMiX, a Graph Topology-Constrained Mixup (GTCM) and hypergraph residual enhancement learning framework for the discovery of disease-related ceRNA biomarkers. This framework first constructs a CENA network encompassing multi-molecule associations, including miRNA, lncRNA, circRNA, and mRNA, and models higher-order regulatory relationships using K-hop hyperedges. Biologically meaningful initial features are then extracted from CENA via a multi-structure hypergraph weighted random walk method (MHWRW), integrating prior biological knowledge and regulatory information. Subsequently, graph topology-constrained Mixup and multi-head attention, combined with a residual hypergraph neural network, are employed to generate robust node embeddings with both local and global context, enabling the identification of potential disease-ceRNA biomarkers.</div><div>Prediction results across multiple disease biomarkers demonstrate that HpMiX significantly outperforms state-of-the-art methods, validating its effectiveness in biological regulatory network representation learning. Case studies further confirm that the framework can effectively identify differentially expressed ceRNAs in diseases, highlighting its potential as a tool for pre-screening high-probability disease biomarkers.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108662"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146127083","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

Decomposition and transfer of individual Q-values for decision-making of multi-agent reinforcement learning with communication 基于沟通的多智能体强化学习决策中个体q值的分解与迁移。

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.2026.108678

Xiaopeng Xu, Yadong Zhao, Dong Wang

In partially observable multi-agent tasks, communication modules need to be trained to supplement information for decision-making, and decision-making modules need to be trained to analyze received information. This leads to their coupling during the process of multi-agent reinforcement learning. To alleviate the difficulty from the coupling, two transfer-based frameworks are proposed. The Simple Transfer Framework converts a difficult reinforcement learning into an easy one and a supervised learning. The Decomposition and Transfer Framework further decomposes this supervised learning into two simpler ones, based on the decomposition of communication-based individual Q-values. They are decomposed into local individual Q-values and their deviations. Based on this framework, the mutual information neural estimation is introduced to train message generators independently. The proposed frameworks are verified by training two communication-based architectures. They outperform direct reinforcement learning algorithms across various team sizes tested in the Drone Fight. The independent training method effectively facilitates the transfer of the deviations.

在部分可观察的多智能体任务中，需要训练通信模块来补充决策信息，需要训练决策模块来分析接收到的信息。这导致了它们在多智能体强化学习过程中的耦合。为了减轻这种耦合带来的困难，提出了两个基于传输的框架。简单迁移框架将困难的强化学习转化为简单的监督学习。基于基于通信的个体q值分解，分解和转移框架进一步将这种监督学习分解为两个更简单的框架。它们被分解为局部单个q值及其偏差。在此框架的基础上，引入互信息神经估计来独立训练消息生成器。通过训练两个基于通信的体系结构对所提出的框架进行了验证。它们在无人机战斗中测试的各种团队规模中都优于直接强化学习算法。独立训练的方法有效地促进了偏差的传递。

{"title":"Decomposition and transfer of individual Q-values for decision-making of multi-agent reinforcement learning with communication","authors":"Xiaopeng Xu, Yadong Zhao, Dong Wang","doi":"10.1016/j.neunet.2026.108678","DOIUrl":"10.1016/j.neunet.2026.108678","url":null,"abstract":"<div><div>In partially observable multi-agent tasks, communication modules need to be trained to supplement information for decision-making, and decision-making modules need to be trained to analyze received information. This leads to their coupling during the process of multi-agent reinforcement learning. To alleviate the difficulty from the coupling, two transfer-based frameworks are proposed. The Simple Transfer Framework converts a difficult reinforcement learning into an easy one and a supervised learning. The Decomposition and Transfer Framework further decomposes this supervised learning into two simpler ones, based on the decomposition of communication-based individual Q-values. They are decomposed into local individual Q-values and their deviations. Based on this framework, the mutual information neural estimation is introduced to train message generators independently. The proposed frameworks are verified by training two communication-based architectures. They outperform direct reinforcement learning algorithms across various team sizes tested in the Drone Fight. The independent training method effectively facilitates the transfer of the deviations.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108678"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146167535","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

C3Net: A cross-modal collaborative calibration of features for object detection using frames and events C3Net：使用帧和事件进行目标检测的跨模态特征协同校准

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.2026.108651

Yunhua Chen , Jinyu Zhong , Yihao Guo , Zequan Xie , Jinsheng Xiao , Pinghua Chen

Object detection by fusing RGB frames and event streams is challenging due to their inherent heterogeneity and significant statistical disparities, which often lead to suboptimal fusion in existing methods. To address this, we introduce C3Net, a novel framework built upon a paradigm shift from direct feature merging to Collaborative Calibration. First, we propose an Adaptive Balancing Time Surface (ABTS) to generate motion-robust event representations by mitigating spatial inconsistencies caused by varying object velocities. Second, the core Cross-Modal Feature Collaborative Calibration Module (CM-FCCM) performs mutual calibration of RGB and event features across channel and spatial dimensions, reducing modality discrepancies before fusion; the calibrated features are then fed back to the respective backbones for enriched feature learning. Finally, an Adaptive Channel Fusion Module (ACFM) dynamically integrates the modalities based on channel-wise confidence. Extensive experiments on PKU-DAVIS-SOD, DSEC-MOD, and PKU-DDD17-CAR datasets demonstrate that C3Net achieves state-of-the-art performance, showcasing its superior ability to leverage the complementary strengths of frames and events.

由于RGB帧和事件流具有固有的异质性和显著的统计差异，因此通过融合RGB帧和事件流进行目标检测具有挑战性，这往往导致现有方法的融合不理想。为了解决这个问题，我们引入了C3Net，这是一个建立在从直接特征合并到协同校准的范式转变之上的新框架。首先，我们提出了一种自适应平衡时间曲面（ABTS），通过减轻由物体速度变化引起的空间不一致性来生成运动鲁棒事件表示。其次，核心跨模态特征协同校准模块（CM-FCCM）跨通道和空间维度对RGB和事件特征进行相互校准，减少融合前的模态差异；然后将校正后的特征反馈到各自的主干进行丰富的特征学习。最后，提出了基于信道置信度的自适应信道融合模块（ACFM）。在PKU-DAVIS-SOD、DSEC-MOD和PKU-DDD17-CAR数据集上进行的大量实验表明，C3Net实现了最先进的性能，展示了其利用框架和事件互补优势的卓越能力。

{"title":"C3Net: A cross-modal collaborative calibration of features for object detection using frames and events","authors":"Yunhua Chen , Jinyu Zhong , Yihao Guo , Zequan Xie , Jinsheng Xiao , Pinghua Chen","doi":"10.1016/j.neunet.2026.108651","DOIUrl":"10.1016/j.neunet.2026.108651","url":null,"abstract":"<div><div>Object detection by fusing RGB frames and event streams is challenging due to their inherent heterogeneity and significant statistical disparities, which often lead to suboptimal fusion in existing methods. To address this, we introduce C3Net, a novel framework built upon a paradigm shift from direct feature merging to Collaborative Calibration. First, we propose an Adaptive Balancing Time Surface (ABTS) to generate motion-robust event representations by mitigating spatial inconsistencies caused by varying object velocities. Second, the core Cross-Modal Feature Collaborative Calibration Module (CM-FCCM) performs mutual calibration of RGB and event features across channel and spatial dimensions, reducing modality discrepancies before fusion; the calibrated features are then fed back to the respective backbones for enriched feature learning. Finally, an Adaptive Channel Fusion Module (ACFM) dynamically integrates the modalities based on channel-wise confidence. Extensive experiments on PKU-DAVIS-SOD, DSEC-MOD, and PKU-DDD17-CAR datasets demonstrate that C3Net achieves state-of-the-art performance, showcasing its superior ability to leverage the complementary strengths of frames and events.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108651"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174304","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

RIT-HetGE: A residue interaction type-aware heterogeneous graph-embedding model for predicting protein thermal stability RIT-HetGE：预测蛋白质热稳定性的残基相互作用类型感知异质图嵌入模型

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

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-02-09 DOI: 10.1016/j.neunet.2026.108707

Lingzhi Liu, Yingying Jiang, Yanbin Gu, Shiming Zhao, Yanrui Ding

Accurately predicting protein thermal stability is crucial for understanding protein function, guiding protein engineering, and advancing biomedical and industrial applications. Although research on protein thermal stability has advanced with structure-based representation learning, most existing methods embed protein structures as homogeneous graphs, which are unable to capture the intricate and heterogeneous characteristics of residue-residue interactions. To address this limitation, we propose a Residue Interaction Type-Aware Heterogeneous Graph Embedding model (RIT-HetGE) that utilizes intra-interaction-type-aware convolutions for local structure learning and employs an inter-interaction-type-aware attention mechanism to fuse interaction-specific features. Theoretical analysis based on Rademacher complexity provides generalization guarantees. Experiments on a large-scale protein structure dataset demonstrate that our model outperforms baseline models and aggregates diverse interaction types to enhance protein representation. RIT-HetGE also exhibits strong interpretability; the intra-interaction-type-aware layer enables identification of critical residues, whereas the inter-interaction-type-aware layer facilitates the detection of significant interaction types associated with protein thermal stability. These findings highlight the importance of integrating biologically meaningful heterogeneous interactions with protein structure encoding and offer a robust framework for protein thermal stability prediction.

准确预测蛋白质热稳定性对理解蛋白质功能、指导蛋白质工程、推进生物医学和工业应用至关重要。尽管基于结构表征学习的蛋白质热稳定性研究取得了进展，但现有的大多数方法将蛋白质结构嵌入为同质图，无法捕捉残基-残基相互作用的复杂和异质性特征。为了解决这一限制，我们提出了一种残余交互类型感知异构图嵌入模型（RIT-HetGE），该模型利用内部交互类型感知卷积进行局部结构学习，并采用内部交互类型感知注意机制融合特定于交互的特征。基于Rademacher复杂度的理论分析为泛化提供了保证。在大规模蛋白质结构数据集上的实验表明，我们的模型优于基线模型，并聚集了不同的相互作用类型来增强蛋白质的表示。RIT-HetGE还具有很强的可解释性；相互作用类型感知层能够识别关键残基，而相互作用类型感知层有助于检测与蛋白质热稳定性相关的重要相互作用类型。这些发现强调了将具有生物学意义的异质相互作用与蛋白质结构编码相结合的重要性，并为蛋白质热稳定性预测提供了一个强大的框架。

{"title":"RIT-HetGE: A residue interaction type-aware heterogeneous graph-embedding model for predicting protein thermal stability","authors":"Lingzhi Liu, Yingying Jiang, Yanbin Gu, Shiming Zhao, Yanrui Ding","doi":"10.1016/j.neunet.2026.108707","DOIUrl":"10.1016/j.neunet.2026.108707","url":null,"abstract":"<div><div>Accurately predicting protein thermal stability is crucial for understanding protein function, guiding protein engineering, and advancing biomedical and industrial applications. Although research on protein thermal stability has advanced with structure-based representation learning, most existing methods embed protein structures as homogeneous graphs, which are unable to capture the intricate and heterogeneous characteristics of residue-residue interactions. To address this limitation, we propose a Residue Interaction Type-Aware Heterogeneous Graph Embedding model (RIT-HetGE) that utilizes intra-interaction-type-aware convolutions for local structure learning and employs an inter-interaction-type-aware attention mechanism to fuse interaction-specific features. Theoretical analysis based on Rademacher complexity provides generalization guarantees. Experiments on a large-scale protein structure dataset demonstrate that our model outperforms baseline models and aggregates diverse interaction types to enhance protein representation. RIT-HetGE also exhibits strong interpretability; the intra-interaction-type-aware layer enables identification of critical residues, whereas the inter-interaction-type-aware layer facilitates the detection of significant interaction types associated with protein thermal stability. These findings highlight the importance of integrating biologically meaningful heterogeneous interactions with protein structure encoding and offer a robust framework for protein thermal stability prediction.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108707"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174305","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

AW-EL-PINNs: A multi-task learning physics-informed neural network for Euler-Lagrange systems in optimal control problems 最优控制问题中Euler-Lagrange系统的多任务学习物理信息神经网络

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

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-02-09 DOI: 10.1016/j.neunet.2026.108694

Chuandong Li, Runtian Zeng

This paper presents adaptive weighted Euler-Lagrange theorem combined physics-informed neural networks (AW-EL-PINNs) for solving Euler-Lagrange systems in optimal control problems. The framework systematically converts optimal control frameworks into two-point boundary value problems (TPBVPs) while establishing a multi-task learning paradigm through innovative integration of the Euler-Lagrange theorem with deep learning architecture. The adaptive loss weighting mechanism dynamically balances loss function components during training, decreasing tedious manual tuning of weighting the loss functions compared to the conventional physics-informed neural networks (PINNs). Based on five numerical examples, it is clear that AW-EL-PINNs achieve enhanced solution accuracy compared to baseline methods while maintaining stability throughout the optimization process. These results highlight the framework’s capability to improve precision and ensure stability in solving Euler-Lagrange systems in optimal control problems, offering potential strategies for problems under physical applications.

本文提出了自适应加权欧拉-拉格朗日定理结合物理信息神经网络（aw - el - pinn）来解决欧拉-拉格朗日系统的最优控制问题。该框架系统地将最优控制框架转化为两点边值问题（TPBVPs），同时通过创新地将欧拉-拉格朗日定理与深度学习架构相结合，建立了多任务学习范式。自适应损失加权机制在训练过程中动态平衡损失函数分量，与传统的物理信息神经网络（pinn）相比，减少了手动调整损失函数权重的繁琐工作。基于五个数值实例，很明显，与基线方法相比，aw - el - pinn在整个优化过程中保持稳定性的同时，获得了更高的解精度。这些结果突出了该框架在解决Euler-Lagrange系统最优控制问题时提高精度和确保稳定性的能力，为物理应用问题提供了潜在的策略。

引用次数: 0

Event-triggered decentralized adaptive critic learning control for interconnected systems with nonlinear inequality state constraints 具有非线性不等式状态约束的互联系统的事件触发分散自适应批评学习控制

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

Neural Networks

Pub Date : 2026-07-01 Epub Date: 2026-01-31 DOI: 10.1016/j.neunet.2026.108646

Wenqian Du , Mingduo Lin , Guoling Yuan , Bo Zhao

In this paper, an event-triggered decentralized adaptive critic learning (ACL) control method is proposed for interconnected systems with nonlinear inequality state constraints. First, by introducing a slack function, the nonlinear inequality state constraints of original isolated subsystem are transformed into equality forms, and then the original isolated subsystem is augmented to an unconstrained one. Then, by establishing a cost function with discount factors for each isolated subsystem, a local policy iteration-based decentralized control law is developed by solving the Hamilton–Jacobi–Bellman equation with the help of a local critic neural network (NN) for each isolated subsystem. Through developing a novel event-triggering mechanism for each isolated subsystem, the decentralized control policy is updated at the triggering instants only, which assists to save the computational and communication resources. Hereafter, the event-triggered decentralized control law of isolated subsystem is derived. Then, the overall optimal control for the entire interconnected system is derived by constituting an array of developed event-triggered decentralized control laws. Furthermore, the closed-loop nonlinear interconnected system and the weight estimation errors of local critic NNs are guaranteed to be uniformly ultimately bounded. Finally, the effectiveness of the proposed method is validated through two comparative simulation examples.

针对具有非线性不等式状态约束的互联系统，提出了一种事件触发的分散自适应批评学习（ACL）控制方法。首先，通过引入松弛函数，将原隔离子系统的非线性不等式状态约束转化为等式形式，然后将原隔离子系统扩充为无约束子系统。然后，通过建立每个孤立子系统的带有折扣因子的成本函数，利用局部批评神经网络（NN）求解Hamilton-Jacobi-Bellman方程，建立了基于局部策略迭代的分散控制律。通过为每个隔离子系统开发一种新的事件触发机制，使分散控制策略只在触发时刻更新，从而节省了计算资源和通信资源。在此基础上，推导了孤立子系统的事件触发分散控制律。然后，通过构建一系列成熟的事件触发分散控制律，推导出整个互联系统的整体最优控制。此外，还保证了闭环非线性互联系统和局部临界神经网络的权值估计误差最终一致有界。最后，通过两个对比仿真算例验证了所提方法的有效性。

{"title":"Event-triggered decentralized adaptive critic learning control for interconnected systems with nonlinear inequality state constraints","authors":"Wenqian Du , Mingduo Lin , Guoling Yuan , Bo Zhao","doi":"10.1016/j.neunet.2026.108646","DOIUrl":"10.1016/j.neunet.2026.108646","url":null,"abstract":"<div><div>In this paper, an event-triggered decentralized adaptive critic learning (ACL) control method is proposed for interconnected systems with nonlinear inequality state constraints. First, by introducing a slack function, the nonlinear inequality state constraints of original isolated subsystem are transformed into equality forms, and then the original isolated subsystem is augmented to an unconstrained one. Then, by establishing a cost function with discount factors for each isolated subsystem, a local policy iteration-based decentralized control law is developed by solving the Hamilton–Jacobi–Bellman equation with the help of a local critic neural network (NN) for each isolated subsystem. Through developing a novel event-triggering mechanism for each isolated subsystem, the decentralized control policy is updated at the triggering instants only, which assists to save the computational and communication resources. Hereafter, the event-triggered decentralized control law of isolated subsystem is derived. Then, the overall optimal control for the entire interconnected system is derived by constituting an array of developed event-triggered decentralized control laws. Furthermore, the closed-loop nonlinear interconnected system and the weight estimation errors of local critic NNs are guaranteed to be uniformly ultimately bounded. Finally, the effectiveness of the proposed method is validated through two comparative simulation examples.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108646"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174716","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