Neural Networks最新文献_第4页

Prototypes as Anchors: Tackling Unseen Noise for online continual learning 原型作为锚：处理在线持续学习中看不见的噪音

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-19 DOI: 10.1016/j.neunet.2025.107634

Shao-Yuan Li , Yu-Xiang Zheng , Sheng-Jun Huang , Songcan Chen , Kangkan Wang

{"title":"Prototypes as Anchors: Tackling Unseen Noise for online continual learning","authors":"Shao-Yuan Li , Yu-Xiang Zheng , Sheng-Jun Huang , Songcan Chen , Kangkan Wang","doi":"10.1016/j.neunet.2025.107634","DOIUrl":"10.1016/j.neunet.2025.107634","url":null,"abstract":"<div><div>In the context of online class-incremental continual learning (CIL), adapting to label noise becomes paramount for model success in evolving domains. While some continual learning (CL) methods have begun to address noisy data streams, most assume that the noise strictly belongs to closed-set noise—i.e., they follow the assumption that noise in the current task originates classes within the same task. This assumption is clearly unrealistic in real-world scenarios. In this paper, we first formulate and analyze the concepts of <em>closed-set</em> and <em>open-set</em> noise, showing that both types can introduce <em>unseen classes</em> for the current training classifier. Then, to effectively handle noisy labels and unknown classes, we present an innovative replay-based method Prototypes as Anchors (PAA), which learns representative and discriminative prototypes for each class, and conducts a similarity-based denoising schema in the representation space to distinguish and eliminate the negative impact of unseen classes. By implementing a dual-classifier architecture, PAA conducts consistency checks between the classifiers to ensure robustness. Extensive experimental results on diverse datasets demonstrate a significant improvement in model performance and robustness compared to existing approaches, offering a promising avenue for continual learning in dynamic, real-world environments.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"190 ","pages":"Article 107634"},"PeriodicalIF":6.0,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144329869","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

DTGBA: A stronger graph backdoor attack with dual triggers DTGBA：一个更强的图形后门攻击与双触发器

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-18 DOI: 10.1016/j.neunet.2025.107726

Ding Li , Hui Xia , Xin Li , Rui Zhang , Mingda Ma

{"title":"DTGBA: A stronger graph backdoor attack with dual triggers","authors":"Ding Li , Hui Xia , Xin Li , Rui Zhang , Mingda Ma","doi":"10.1016/j.neunet.2025.107726","DOIUrl":"10.1016/j.neunet.2025.107726","url":null,"abstract":"<div><div>Graph backdoor attacks can significantly degrade the performance of graph neural networks (GNNs). Specifically, during the training phase, graph backdoor attacks inject triggers and target class labels into poisoned nodes to create a backdoored GNN. During the testing phase, triggers are added to target nodes, causing them to be misclassified as the target class. However, existing graph backdoor attacks lack sufficient imperceptibility and can be easily resisted by random edge dropping-based defense, limiting their effectiveness. To address these issues, we propose Dual Triggers Graph Backdoor Attack (DTGBA). Initially, we deploy an imperceptible injected trigger generator and multiple discriminators, driving the imperceptibility of the injected triggers through adversarial game between them. Additionally, we introduce a feature mask learner to extract the high-impact and low-impact feature dimensions of the target class’s nodes, and then create feature-based triggers by modifying the key feature dimensions of poisoned/target nodes, ensuring that the backdoor implantation can still be effective even if the injected triggers are removed by random edge dropping. Finally, we conduct extensive experiments to demonstrate that DTGBA achieves superior performance. Our code is available at <span><span>https://github.com/SnowStone-DingLi/DTGBA-main</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"190 ","pages":"Article 107726"},"PeriodicalIF":6.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144366789","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

PolarFusion: A multi-modal fusion algorithm for 3D object detection based on polar coordinates. PolarFusion：一种基于极坐标的三维目标检测多模态融合算法。

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-18 DOI: 10.1016/j.neunet.2025.107704

Peicheng Shi, Runshuai Ge, Xinlong Dong, Chadia Chakir, Taonian Liang, Aixi Yang

{"title":"PolarFusion: A multi-modal fusion algorithm for 3D object detection based on polar coordinates.","authors":"Peicheng Shi, Runshuai Ge, Xinlong Dong, Chadia Chakir, Taonian Liang, Aixi Yang","doi":"10.1016/j.neunet.2025.107704","DOIUrl":"https://doi.org/10.1016/j.neunet.2025.107704","url":null,"abstract":"<p><p>Existing 3D object detection algorithms that fuse multi-modal sensor information typically operate in Cartesian coordinates, which can lead to asymmetrical feature information and uneven attention across multiple views. To address this, we propose PolarFusion, the first multi-modal fusion BEV object detection algorithm based on polar coordinates. We designed three specialized modules for this approach: the Polar Region Candidates Generation Module, the Polar Region Query Generation Module, and the Polar Region Information Fusion Module. In the Polar Region Candidates Generation Module, we use a region proposal-based segmentation method to remove irrelevant areas from images, enhancing PolarFusion's information processing efficiency. These segmented image regions are then integrated into the point cloud segmentation task, addressing feature misalignment during fusion. The Polar Region Query Generation Module leverages prior information to generate high-quality target queries, reducing the time spent learning from initialization. For the Polar Region Information Fusion Module, PolarFusion employs a simple yet efficient self-attention to merge internal information from images and point clouds. This captures long-range dependencies in image texture information while preserving the precise positional data from point clouds, enabling more accurate BEV object detection. We conducted extensive experiments on challenging BEV object detection datasets. Both qualitative and quantitative results demonstrate that PolarFusion achieves an NDS of 76.1% and mAP of 74.5% on the nuScenes test set, significantly outperforming Cartesian-based methods. This advancement enhances the environmental perception capabilities of autonomous vehicles and contributes to the development of future intelligent transportation systems. The code will be released at https://github.com/RunshuaiGe/PolarFusion.git.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"190 ","pages":"107704"},"PeriodicalIF":6.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499002","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

Neural-network-based event-triggered adaptive secure fault-tolerant containment control for nonlinear multi-agent systems under denial-of-service attacks 拒绝服务攻击下非线性多智能体系统基于神经网络的事件触发自适应安全容错控制

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-18 DOI: 10.1016/j.neunet.2025.107725

Xiangjun Wu , Shuo Ding , Ning Zhao , Huanqing Wang , Ben Niu

{"title":"Neural-network-based event-triggered adaptive secure fault-tolerant containment control for nonlinear multi-agent systems under denial-of-service attacks","authors":"Xiangjun Wu , Shuo Ding , Ning Zhao , Huanqing Wang , Ben Niu","doi":"10.1016/j.neunet.2025.107725","DOIUrl":"10.1016/j.neunet.2025.107725","url":null,"abstract":"<div><div>Under the framework of backstepping theory, dealing with the non-differentiable problem of virtual control signals caused by sensor output triggering is difficult. Meanwhile, it is of great practical significance to consider problems of output triggering, multiple faults, and denial-of-service (DoS) attacks in nonlinear multi-agent systems (MASs). This paper studies a neural-network-based event-triggered adaptive secure fault-tolerant containment control problem for nonlinear MASs under multiple faults and DoS attacks. Under sensor output triggering, only intermittent output signals are used to construct a switched neural network estimator to guarantee that estimated states are first-order derivable. Meanwhile, virtual control laws are constructed using estimated states to ensure first-order differentiable, and dynamic filtering technology is adopted to avoid the repeated differentiation of virtual control laws. It is shown that the designed secure fault-tolerant containment controller can compensate for faults and DoS attacks, and each follower can converge to a dynamic convex hull spanned by multiple leaders. Practical simulation results are given to verify the effectiveness of the proposed control method.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"191 ","pages":"Article 107725"},"PeriodicalIF":6.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144471027","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

Hierarchical feature-guided prototypical network for few-shot knowledge graph completion 基于分层特征引导的知识图补全原型网络

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-18 DOI: 10.1016/j.neunet.2025.107702

Yuling Li , Kui Yu , Fei Yang , Chunfeng Shen , Ji Chang , Zerui Li , Kang Liu

{"title":"Hierarchical feature-guided prototypical network for few-shot knowledge graph completion","authors":"Yuling Li , Kui Yu , Fei Yang , Chunfeng Shen , Ji Chang , Zerui Li , Kang Liu","doi":"10.1016/j.neunet.2025.107702","DOIUrl":"10.1016/j.neunet.2025.107702","url":null,"abstract":"<div><div>Few-shot knowledge graph completion (FKGC) aims to predict missing triples for unseen relations by observing several associated reference entity pairs. Current methods address this task by learning relation prototypes from the direct neighborhoods of corresponding reference pairs and then computing the feature similarity between the relation prototype and query triples. However, exploiting only direct neighborhoods of entities may lose some representative entity features, leading to unreliable relation prototypes. Moreover, existing methods usually assume that all feature dimensions of entities contribute equally to calculating feature similarity, ignoring the different roles of entity features in dealing with different task relations. To solve these issues, we propose a novel hierarchical feature-guided prototypical network (HPNet) for few-shot knowledge graph completion. HPNet consists of two main components: a hierarchical neighbor encoder to capture more abundant entity features by simultaneously incorporating direct and distant neighborhood information, and a feature-guided prototype learner to compare query triples with relation prototypes along task-relevant feature dimensions by considering different importance of entity features. In this way, our model is able to generate more reliable prototypes and make comparisons in a more effective manner. Extensive comparisons to related works demonstrate the superiority of the proposed HPNet.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"191 ","pages":"Article 107702"},"PeriodicalIF":6.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144471037","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

TD-HCN: A trend-driven hypergraph convolutional network for stock return prediction 基于趋势驱动的超图卷积网络的股票收益预测

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-18 DOI: 10.1016/j.neunet.2025.107729

Lexin Fang , Tianlong Zhao , Junlei Yu , Qiang Guo , Xuemei Li , Caiming Zhang

{"title":"TD-HCN: A trend-driven hypergraph convolutional network for stock return prediction","authors":"Lexin Fang , Tianlong Zhao , Junlei Yu , Qiang Guo , Xuemei Li , Caiming Zhang","doi":"10.1016/j.neunet.2025.107729","DOIUrl":"10.1016/j.neunet.2025.107729","url":null,"abstract":"<div><div>Stock data analysis has become one of the most challenging tasks in time series data analysis due to its dynamism, complexity, and nonlinearity. Recently, relational graphs have become popular for describing certain important relationships in data, particularly by mapping indirect and direct relationships between stocks into non-Euclidean spaces. Existing graph-based methods mainly capture simple pairwise and static relationships between stocks, so they cannot effectively identify higher-order relationships and characterize the dynamic trends of stock relationships. This limitation restricts the performance of stock return prediction models. A variety of stock data types reveal complex relationships among stocks, such as stock prices, industry links, and wiki relationships. This paper proposes a novel <strong>T</strong>rend-<strong>D</strong>riven <strong>H</strong>ypergraph <strong>C</strong>onvolutional <strong>N</strong>etwork (<strong>TD-HCN</strong>) that integrates these data types in order to predict stock rankings through a cooperative learning method of local dynamic and global static relationships across temporal dimensions. To be concrete, we employ a Prior-constrained Relational Learning (PCRL) model that leverages explicit prior knowledge to guide the discovery of latent high-order relationships among stocks. In order to comprehensively capture and utilize dynamic trends in relationships among stocks, a Disentanglement Representation Learning (DRL) mechanism is developed to enhance the key trend features through the disentanglement operation and dual attention module. Extensive experiments on NASDAQ and NYSE datasets show that TD-HCN consistently outperforms the state-of-the-art methods by a considerable margin in terms of returns. It is also effective and robust in learning the dynamic relationships among stocks and capturing key changes in trends within those relationships.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"190 ","pages":"Article 107729"},"PeriodicalIF":6.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144338374","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

Degradation-Guided cross-consistent deep unfolding network for video restoration under diverse weathers 退化引导交叉一致深度展开网络在不同天气条件下的视频恢复

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-16 DOI: 10.1016/j.neunet.2025.107700

Yuanshuo Cheng , Mingwen Shao , Yecong Wan , Yuanjian Qiao , Wangmeng Zuo , Deyu Meng

{"title":"Degradation-Guided cross-consistent deep unfolding network for video restoration under diverse weathers","authors":"Yuanshuo Cheng , Mingwen Shao , Yecong Wan , Yuanjian Qiao , Wangmeng Zuo , Deyu Meng","doi":"10.1016/j.neunet.2025.107700","DOIUrl":"10.1016/j.neunet.2025.107700","url":null,"abstract":"<div><div>Existing video restoration (VR) methods have made promising progress in improving the quality of videos degraded by adverse weather. However, these approaches only restore videos with one specific type of degradation and ignore the diversity of degradations in the real world, which limits their application in realistic scenes with diverse adverse weathers. To address the aforementioned issue, in this paper, we propose a Cross-consistent Deep Unfolding Network (CDUN) to adaptively restore frames corrupted by different degradations via the guidance of degradation features. Specifically, the proposed CDUN incorporates (1) a flexible iterative optimization framework, capable of restoring frames corrupted by arbitrary degradations according to the corresponding degradation features given in advance. To enable the framework to eliminate diverse degradations, we devise (2) a Sequence-wise Adaptive Degradation Estimator (SADE) to estimate degradation features for the corrupted video. By orchestrating these two cascading procedures, the proposed CDUN is capable of an end-to-end restoration of videos under the diverse-degradation scene. In addition, we propose a window-based inter-frame fusion strategy to utilize information from more adjacent frames. This strategy involves progressive stacking of temporal windows in multiple iterations, effectively enlarging the temporal receptive field and enabling each frame’s restoration to leverage information from distant frames. This work establishes the first explicit model for diverse-degraded videos and is one of the earliest studies of video restoration in the diverse-degradation scene. Extensive experiments indicate that our method achieves state-of-the-art.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"191 ","pages":"Article 107700"},"PeriodicalIF":6.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144489827","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

Counterfactual value decomposition for cooperative multi-agent reinforcement learning 协同多智能体强化学习的反事实值分解

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-16 DOI: 10.1016/j.neunet.2025.107692

Kai Liu , Tianxian Zhang , Xiangliang Xu , Yuyang Zhao

{"title":"Counterfactual value decomposition for cooperative multi-agent reinforcement learning","authors":"Kai Liu , Tianxian Zhang , Xiangliang Xu , Yuyang Zhao","doi":"10.1016/j.neunet.2025.107692","DOIUrl":"10.1016/j.neunet.2025.107692","url":null,"abstract":"<div><div>Value decomposition has become a central focus in Multi-Agent Reinforcement Learning (MARL) in recent years. The key challenge lies in the construction and updating of the factored value function (FVF). Traditional methods rely on FVFs with restricted representational capacity, rendering them inadequate for tasks with non-monotonic payoffs. Recent approaches address this limitation by designing FVF update mechanisms that enable applicability to non-monotonic scenarios. However, these methods typically depend on the true optimal joint action value to guide FVF updates. Since the true optimal joint action is computationally infeasible in practice, these methods approximate it using the greedy joint action and update the FVF with the corresponding greedy joint action value. We observe that although the greedy joint action may be close to the true optimal joint action, its associated greedy joint action value can be substantially biased relative to the true optimal joint action value. This makes the approximation unreliable and can lead to incorrect update directions for the FVF, hindering the learning process. To overcome this limitation, we propose Comix, a novel off-policy MARL method based on a Sandwich Value Decomposition Framework. Comix constrains and guides FVF updates using both upper and lower bounds. Specifically, it leverages orthogonal best responses to construct the upper bound, thus overcoming the drawbacks introduced by the optimal approximation. Furthermore, an attention mechanism is incorporated to ensure that the upper bound can be computed with linear time complexity and high accuracy. Theoretical analyses show that Comix satisfies the IGM. Experiments on the asymmetric One-Step Matrix Game, discrete Predator-Prey, and StarCraft Multi-Agent Challenge show that Comix achieves higher learning efficiency and outperforms several state-of-the-art methods.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"190 ","pages":"Article 107692"},"PeriodicalIF":6.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144306934","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

BRSR-OpGAN: Blind radar signal restoration using operational generative adversarial network BRSR-OpGAN：基于作战生成对抗网络的雷达信号盲恢复

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-16 DOI: 10.1016/j.neunet.2025.107709

Muhammad Uzair Zahid , Serkan Kiranyaz , Alper Yildirim , Moncef Gabbouj

{"title":"BRSR-OpGAN: Blind radar signal restoration using operational generative adversarial network","authors":"Muhammad Uzair Zahid , Serkan Kiranyaz , Alper Yildirim , Moncef Gabbouj","doi":"10.1016/j.neunet.2025.107709","DOIUrl":"10.1016/j.neunet.2025.107709","url":null,"abstract":"<div><div>Many studies on radar signal restoration in the literature focus on isolated restoration problems, such as denoising over a certain type of noise, while ignoring other types of artifacts. Additionally, these approaches usually assume a noisy environment with a limited set of fixed signal-to-noise ratio (SNR) levels. However, real-world radar signals are often corrupted by a blend of artifacts, including but not limited to unwanted echo, sensor noise, intentional jamming, and interference, each of which can vary in type, severity, and duration. This study introduces Blind Radar Signal Restoration using an Operational Generative Adversarial Network (BRSR-OpGAN), which uses a dual domain loss in the temporal and spectral domains. This approach is designed to improve the quality of radar signals, regardless of the diversity and intensity of the corruption. The BRSR-OpGAN utilizes 1D Operational GANs, which use a generative neuron model specifically optimized for blind restoration of corrupted radar signals. This approach leverages GANs’ flexibility to adapt dynamically to a wide range of artifact characteristics. The proposed approach has been extensively evaluated using a well-established baseline and a newly curated extended dataset called the Blind Radar Signal Restoration (BRSR) dataset. This dataset was designed to simulate real-world conditions and includes a variety of artifacts, each varying in severity. The evaluation shows an average SNR improvement over 15.1 dB and 14.3 dB for the baseline and BRSR datasets, respectively. Finally, the proposed approach can be applied in real-time, even on resource-constrained platforms. This pilot study demonstrates the effectiveness of blind radar restoration in time-domain for real-world radar signals, achieving exceptional performance across various SNR values and artifact types. The BRSR-OpGAN method exhibits robust and computationally efficient restoration of real-world radar signals, significantly outperforming existing methods.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"190 ","pages":"Article 107709"},"PeriodicalIF":6.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144320858","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

Bridging the gap between ratings and true user opinions with dynamic review alignment for personalized recommendation 通过动态评论对齐个性化推荐，弥合评级和真实用户意见之间的差距

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-06-16 DOI: 10.1016/j.neunet.2025.107706

Xinyu Liu , Jinxia Guo , Qirui Hao , Hongliang Wang , Zhongjing Yu , Qinli Yang , Junming Shao

{"title":"Bridging the gap between ratings and true user opinions with dynamic review alignment for personalized recommendation","authors":"Xinyu Liu , Jinxia Guo , Qirui Hao , Hongliang Wang , Zhongjing Yu , Qinli Yang , Junming Shao","doi":"10.1016/j.neunet.2025.107706","DOIUrl":"10.1016/j.neunet.2025.107706","url":null,"abstract":"<div><div>Personalized recommender systems strive to deliver timely, accurate suggestions that reflect a user’s current interests, yet they face challenges in aligning ratings with users’ true thoughts and adapting to dynamic user behaviors under sparse user–item interactions. Ratings or implicit data often fail to reflect nuanced opinions, as users may assign high ratings despite expressing dissatisfaction in their reviews. Moreover, existing models struggle to adapt to temporal changes in user behaviors while handling the inherent noise and sparsity of real-world data. In this paper, we propose a dynamic multi-scale review alignment (DMRA) graph-based recommendation model to tackle these challenges. By incorporating multi-scale review extraction techniques, DMRA aligns textual insights with user–item interactions to uncover nuanced user opinions and mitigate rating biases. A sentiment-aware graph propagates semantic and sentiment information, while a memory-augmented module dynamically stores and updates user preferences in micro-cluster manner, balancing short-term and long-term interests. Furthermore, DMRA employs a contrastive learning mechanism to filter noise and inconsistencies in both ratings and reviews, ensuring robust recommendation. Extensive experiments on real-world datasets indicate that DMRA outperforms baselines, and has the capacity to promptly capture granular user preferences and item features and adapt to temporal dynamics, offering accurate and reliable personalized recommendations.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"191 ","pages":"Article 107706"},"PeriodicalIF":6.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144510734","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