Neural Networks最新文献

Dominant preference decoupling and guided perturbed preference injection for cross-domain sequence recommendation 跨域序列推荐的显性偏好解耦和定向扰动偏好注入

IF 6.3 1区计算机科学

Neural Networks Pub Date : 2025-07-27 DOI: 10.1016/j.neunet.2025.107906

Xiuze Li , Zhenhua Huang , Changdong Wang , Yunwen Chen

{"title":"Dominant preference decoupling and guided perturbed preference injection for cross-domain sequence recommendation","authors":"Xiuze Li , Zhenhua Huang , Changdong Wang , Yunwen Chen","doi":"10.1016/j.neunet.2025.107906","DOIUrl":"10.1016/j.neunet.2025.107906","url":null,"abstract":"<div><div>Cross-domain sequential recommendation jointly models cross- and intra-domain interaction sequences to extract relevant information to predict future interactions across domains. Nevertheless, current mainstream methods overlook the intra-domain dominant preference and the impact of perturbed preference on prediction outcomes. Hence, this paper proposes the Dominant Preference Decoupling and Guided Perturbed Preference Injection for Cross-Domain Sequence Recommendation (DP-CSR) model to address the aforementioned issues. The core idea is to preserve the intra-domain dominant preference while extracting perturbed preference information from cross-domain sequences to predict user interactions. Specifically, DP-CSR captures diverse intra-domain dominant preferences through multi-channel hypergraph learning and then integrates them using an attention mechanism. After that, it constructs serialized perturbed preference by jointly modeling intra and cross-domain sequences using sequence encoders. Furthermore, a gating mechanism dynamically injects critical cross-domain perturbed preference information into the intra-domain perturbed preference. This strategy enhances the model’s prediction adaptability by combining three preference types and avoiding information redundancy. Furthermore, a contrastive learning-based preference decoupling optimization objective enhances the preference decoupling and fine alignment of the cross-domain perturbed preferences with the intra-domain perturbed ones. Extensive experiments on six real-world benchmark datasets demonstrate remarkable and consistent improvements of the proposed DP-CSR over the state-of-the-art methods.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107906"},"PeriodicalIF":6.3,"publicationDate":"2025-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721599","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

Temporal structure-preserving transformer for industrial load forecasting 用于工业负荷预测的时间结构保持变压器

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-07-23 DOI: 10.1016/j.neunet.2025.107887

Senzhen Wu , Zhijin Wang , Xiufeng Liu , Yuan Zhao , Yue Hu , Yaohui Huang

{"title":"Temporal structure-preserving transformer for industrial load forecasting","authors":"Senzhen Wu , Zhijin Wang , Xiufeng Liu , Yuan Zhao , Yue Hu , Yaohui Huang","doi":"10.1016/j.neunet.2025.107887","DOIUrl":"10.1016/j.neunet.2025.107887","url":null,"abstract":"<div><div>Accurate power load forecasting in industrial parks is crucial for optimizing energy management and operational efficiency. Existing models struggle with industrial load series’ complex, multi-target nature and the need to integrate diverse exogenous variables. This paper introduces the Temporal Structure-Preserving Transformer (TSPT), a novel architecture that addresses these challenges by decomposing multi-target series into univariate series, enabling parallel processing and integrating exogenous data. The TSPT model incorporates the Gated Feature Fusion (GFF), which learns to capture multiscale temporal patterns from each target sequence and exogenous factors by preserving the temporal structure of the series. This parallel processing and the structure-preserving transformations allow TSPT to effectively integrate domain-specific knowledge, such as weather, production, and efficiency data, enhancing its forecasting performance. Comprehensive experiments on a real-world industrial park dataset demonstrate TSPT’s superiority over state-of-the-art methods in handling complex, multi-target forecasting tasks with integrated exogenous variables. The proposed approach offers a pathway for scalable and accurate load forecasting in industrial settings, improving energy management and operational decision-making.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107887"},"PeriodicalIF":6.0,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704467","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

Enhancing adversarial transferability via transformation inference 通过转换推理增强对抗可转移性

IF 6.3 1区计算机科学

Neural Networks Pub Date : 2025-07-23 DOI: 10.1016/j.neunet.2025.107896

Jiaxin Hu , Jie Lin , Xiangyuan Yang , Hanlin Zhang , Peng Zhao

{"title":"Enhancing adversarial transferability via transformation inference","authors":"Jiaxin Hu , Jie Lin , Xiangyuan Yang , Hanlin Zhang , Peng Zhao","doi":"10.1016/j.neunet.2025.107896","DOIUrl":"10.1016/j.neunet.2025.107896","url":null,"abstract":"<div><div>The transferability of adversarial examples has become a crucial issue in black-box attacks. Input transformation techniques have shown considerable promise in enhancing transferability, but existing methods are often limited by their empirical nature, neglecting the wide spectrum of potential transformations. This may limit the transferability of adversarial examples. To address this issue, we propose a novel transformation variational inference attack(TVIA) to improve the diversity of transformations, which leverages variational inference (VI) to explore a broader set of input transformations, thus enriching the diversity of adversarial examples and enhancing their transferability across models. Unlike traditional empirical approaches, our method employs the variational inference of a Variational Autoencoder (VAE) model to explore potential transformations in the latent space, significantly expanding the range of image variations. We further enhance diversity by modifying the VAE’s sampling process, enabling the generation of more diverse adversarial examples. To stabilize the gradient direction during the attack process, we fuse transformed images with the original image and apply random noise. The experiment results on Cifar10, Cifar100, ImageNet datasets show that the average attack success rates (ASRs) of the adversarial examples generated by our TVIA surpass all existing attack methods. Specially, the ASR reaches 95.80 % when transferred from Inc-v3 to Inc-v4, demonstrating that our TVIA can effectively enhance the transferability of adversarial examples.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107896"},"PeriodicalIF":6.3,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721597","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

Exclusive style removal for cross domain novel class discovery 跨领域新颖类发现的专属风格移除

IF 6.3 1区计算机科学

Neural Networks Pub Date : 2025-07-23 DOI: 10.1016/j.neunet.2025.107902

Yicheng Wang , Feng Liu , Junmin Liu , Kai Sun

{"title":"Exclusive style removal for cross domain novel class discovery","authors":"Yicheng Wang , Feng Liu , Junmin Liu , Kai Sun","doi":"10.1016/j.neunet.2025.107902","DOIUrl":"10.1016/j.neunet.2025.107902","url":null,"abstract":"<div><div>As a promising field in open-world learning, <em>Novel Class Discovery</em> (NCD) is usually a task to cluster unseen novel classes in an unlabeled set based on the prior knowledge of labeled data within the same domain. However, the performance of existing NCD methods could be severely compromised when novel classes are sampled from a different distribution with the labeled ones. In this paper, we explore and establish the solvability of NCD with cross domain setting under the necessary condition that the style information needs to be removed. Based on the theoretical analysis, we introduce an exclusive style removal module for extracting style information that is distinctive from the baseline features, thereby facilitating inference. Moreover, this module is easy to integrate with other NCD methods, acting as a plug-in to improve performance on novel classes with different distributions compared to the labeled set. Additionally, recognizing the non-negligible influence of different backbones and pre-training strategies on the performance of the NCD methods, we build a fair benchmark for future NCD research. Extensive experiments on three common datasets demonstrate the effectiveness of our proposed style removal strategy.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107902"},"PeriodicalIF":6.3,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721600","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 with temporal and variable dependency-aware transformer for stock trading optimization 基于时间和变量依赖感知变压器的股票交易优化强化学习

IF 6.3 1区计算机科学

Neural Networks Pub Date : 2025-07-23 DOI: 10.1016/j.neunet.2025.107905

Yifan Li , Xu Dong , Zhuang Wu , Jing Gao , Tianqi Zhang , Lina Yu

{"title":"Reinforcement learning with temporal and variable dependency-aware transformer for stock trading optimization","authors":"Yifan Li , Xu Dong , Zhuang Wu , Jing Gao , Tianqi Zhang , Lina Yu","doi":"10.1016/j.neunet.2025.107905","DOIUrl":"10.1016/j.neunet.2025.107905","url":null,"abstract":"<div><div>Stock trading optimization aims to optimize portfolios in dynamic market environments, which plays a crucial role in practical financial decision-making. With the rise of Transformer in recent years, some researchers have combined Transformer with Reinforcement Learning (RL) to improve their ability to represent potential patterns in market data. However, existing methods mainly focus on capturing temporal dependencies, failing to effectively model the interactions among multiple variables, limiting sufficient decision-making information for policy learning in RL. To this end, this paper proposes a RL model that integrates a Temporal and Variable Dependency-aware Transformer to learn diverse dependency relationships in market data. Firstly, a short-term prediction module and a long-term prediction module are designed to explore potential dependencies in the market data with a short-term horizon and a long-term horizon, respectively. The core of both the short-term prediction module and the long-term prediction module is the Temporal and Variable Dependency-aware Transformer, which is implemented in two stages. Specifically, the first stage captures temporal relationships along the temporal dimension, and the second stage captures multivariate correlations across the variable dimension. Meanwhile, a relation representation module is proposed to further capture correlations of different stock assets within a market. Finally, a policy decision module is introduced to effectively fuse different representations from the preceding modules into a unified space, enabling RL to learn flexible policies with comprehensive decision-making information. The experimental results clearly demonstrate the superior performance of the proposed method, which achieves the highest Sharpe ratio of 1.48 and portfolio return of 2.65, outperforming state-of-the-art methods on three challenging datasets of CSI-300, S&P-100, and NASDAQ-100.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107905"},"PeriodicalIF":6.3,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720783","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

Corrigendum to “Hierarchical Feature-guided Prototypical Network for Few-shot Knowledge Graph Completion” [Neural Networks Volume 191, November 2025, 107702/NN_107702] “分层特征引导的原型网络用于少量知识图补全”的勘误表[神经网络卷191，十一月2025,107702/NN_107702]

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-07-22 DOI: 10.1016/j.neunet.2025.107886

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

引用次数: 0

GSAformer: Group sparse attention transformer for functional brain network analysis GSAformer：用于脑功能网络分析的组稀疏注意力转换器

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-07-22 DOI: 10.1016/j.neunet.2025.107891

Lina Zhou , Xiao Jiang , Mengxue Pang , Jinshan Zhang , Shuai Zhang , Chris Nugent , Lishan Qiao

{"title":"GSAformer: Group sparse attention transformer for functional brain network analysis","authors":"Lina Zhou , Xiao Jiang , Mengxue Pang , Jinshan Zhang , Shuai Zhang , Chris Nugent , Lishan Qiao","doi":"10.1016/j.neunet.2025.107891","DOIUrl":"10.1016/j.neunet.2025.107891","url":null,"abstract":"<div><div>Functional brain network (FBN) analysis based on fMRI has proven effective for neurological/mental disorder classification. Traditional methods usually separate the FBN construction from the subsequent classification tasks, resulting in a suboptimal solution. Recently, transformers, known for their attention mechanisms, have shown strong performance in various tasks, including brain disorder classification. However, existing methods treat subjects independently, limiting the capture of their shared patterns. To address these issues, we propose GSAformer, a group sparse attention-based model for brain disorder diagnosis. Specifically, we first construct brain connectivity matrices for subjects using Pearson’s correlation, and then incorporate group sparse prior into the transformer to explicitly model inter-subject relationships. Group sparsity is applied across attention matrices to reduce parameters, improve the generalization, and enhance the interpretability. A maximum mean discrepancy (MMD) constraint is also introduced to ensure consistency between the learned attention matrices and the group sparse brain networks. Our framework integrates population-level prior knowledge, and supports end-to-end adaptive learning, while maintaining computational complexity on par with the standard Transformer and demonstrating enhanced capability in capturing group sparse topological structures among population. We evaluate the GSAformer on three public datasets for brain disorder classification. The classification performance of the proposed method is improved by 3.8%, 4.1% and 14.7% on the three datasets, respectively, compared with the standard Transformer.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107891"},"PeriodicalIF":6.0,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704465","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

Neuro-dynamic programming-based event-triggered fault tolerant control for nonlinear systems with multiple faults 基于神经动态规划的多故障非线性系统容错控制

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-07-20 DOI: 10.1016/j.neunet.2025.107885

Haowei Lin , Weifeng Su , Runlin Huang , Bo Zhao , Jing Zhao , Wentao Fan

{"title":"Neuro-dynamic programming-based event-triggered fault tolerant control for nonlinear systems with multiple faults","authors":"Haowei Lin , Weifeng Su , Runlin Huang , Bo Zhao , Jing Zhao , Wentao Fan","doi":"10.1016/j.neunet.2025.107885","DOIUrl":"10.1016/j.neunet.2025.107885","url":null,"abstract":"<div><div>Existing neuro-dynamic programming (NDP)-based fault-tolerant control (FTC) methods typically focus exclusively on actuator faults while neglecting sensor faults, and their online implementation is constrained by the strict persistence of excitation (PE) condition and the initial admissible control. This paper presents an online FTC scheme for uncertain nonlinear systems characterized by multiple faults. By integrating two neural networks (NNs) within a neuro-observer, the proposed approach simultaneously reconstructs accurate system states and estimates both actuator and sensor faults. Based on the neuro-observer, a critic NN is built to derive the event-triggered control (ETC) policy indirectly. Then, the NDP-based event-triggered FTC strategy is derived by combining the NDP-based ETC and the actuator fault compensator with significantly reducing computational resource consumption. Meanwhile, an additional stabilizing term and the experience replay technique are introduced to relax the stringent PE and initial control conditions, which enables the online application of our proposed control scheme. The observer errors, fault estimation errors, and the closed-loop system are all shown to be uniformly ultimate boundedness by employing Lyapunov’s direct method. Finally, a simulation example is provided to validate the proposed method.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107885"},"PeriodicalIF":6.0,"publicationDate":"2025-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704464","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

DMCA-Net: Dual-branch multi-granularity hierarchical contrast and cross-attention network for cervical abnormal cell detection DMCA-Net：用于宫颈异常细胞检测的双分支多粒度分层对比和交叉注意网络

IF 6.3 1区计算机科学

Neural Networks Pub Date : 2025-07-20 DOI: 10.1016/j.neunet.2025.107890

Zhiping Wang , Peng Yao , Shuwei Shen , Pengfei Shao , Wei Ren , Liang Zeng , Mingzhai Sun , Ronald X. Xu

{"title":"DMCA-Net: Dual-branch multi-granularity hierarchical contrast and cross-attention network for cervical abnormal cell detection","authors":"Zhiping Wang , Peng Yao , Shuwei Shen , Pengfei Shao , Wei Ren , Liang Zeng , Mingzhai Sun , Ronald X. Xu","doi":"10.1016/j.neunet.2025.107890","DOIUrl":"10.1016/j.neunet.2025.107890","url":null,"abstract":"<div><div>Accurate detection of abnormal cells is essential for early screening and precise diagnosis of cervical cancer. Despite the recent advances in deep learning-based methods for cervical cancer detection, their broad clinical applications are hindered by several technical challenges. On the one hand, gradually evolved abnormal cells are visually similar to normal cells. On the other hand, single cells and cell clusters exhibit significant appearance variations, overlooking those between normal and abnormal cells. In order to overcome these challenges, we propose a novel dual-branch multi-granularity hierarchical contrast and cross attention network, called DMCA-Net. Specifically, DMCA-Net utilizes dual branches to detect abnormal and normal cells, respectively. Meanwhile, an inter-cell pair-wise cross-attention (IPCA) is utilized to improve feature embedding learning. The IPCA regularizes the attention learning of abnormal cell features by treating normal cell features as distractors. In addition, DMCA-Net also adopts a multi-granularity hierarchical contrastive learning (MHCL) to enhance the classification ability. Our study indicates that MHCL alleviates the interference of intra-class appearance variations in cervical cell, effectively pulls apart the inter-class distance between different classes of cervical cells at different granularities. Extensive experiments on two publicly available datasets demonstrate that our DMCA-Net outperforms existing methods, achieving state-of-the-art (SOTA) results. Code and additional annotation data are available at <span><span>https://github.com/zhihuaji/DMCA-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107890"},"PeriodicalIF":6.3,"publicationDate":"2025-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721598","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

LeanKAN: a parameter-lean Kolmogorov-Arnold network layer with improved memory efficiency and convergence behavior LeanKAN：一个参数精益的Kolmogorov-Arnold网络层，具有改进的内存效率和收敛行为

IF 6.3 1区计算机科学

Neural Networks Pub Date : 2025-07-19 DOI: 10.1016/j.neunet.2025.107883

Benjamin C. Koenig, Suyong Kim, Sili Deng

{"title":"LeanKAN: a parameter-lean Kolmogorov-Arnold network layer with improved memory efficiency and convergence behavior","authors":"Benjamin C. Koenig, Suyong Kim, Sili Deng","doi":"10.1016/j.neunet.2025.107883","DOIUrl":"10.1016/j.neunet.2025.107883","url":null,"abstract":"<div><div>The recently proposed Kolmogorov-Arnold network (KAN) is a promising alternative to multi-layer perceptrons (MLPs) for data-driven modeling. While original KAN layers were only capable of representing the addition operator, the recently-proposed MultKAN layer combines addition and multiplication subnodes in an effort to improve representation performance. Here, we find that MultKAN layers suffer from a few key drawbacks including limited applicability in output layers, bulky parameterizations with extraneous activations, and the inclusion of complex hyperparameters. To address these issues, we propose LeanKANs, a direct and modular replacement for MultKAN and traditional AddKAN layers. LeanKANs address these three drawbacks of MultKAN through general applicability as output layers, significantly reduced parameter counts for a given network structure, and a smaller set of hyperparameters. As a one-to-one layer replacement for standard AddKAN and MultKAN layers, LeanKAN is able to provide these benefits to traditional KAN learning problems as well as augmented KAN structures in which it serves as the backbone, such as KAN Ordinary Differential Equations (KAN-ODEs) or Deep Operator KANs (DeepOKAN). We demonstrate LeanKAN’s simplicity and efficiency in a series of demonstrations carried out across a standard KAN toy problem as well as ordinary and partial differential equations learned via KAN-ODEs, where we find that its sparser parameterization and compact structure serve to increase its expressivity and learning capability, leading it to outperform similar and even much larger MultKANs in various tasks.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"192 ","pages":"Article 107883"},"PeriodicalIF":6.3,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720782","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