检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Jiang, Huanwen Wang, Xinyao Han, Guosheng Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan Xiangtan411105 China

In the real world, most of the time series generated from complex systems are nonlinear. To effectively study its fractal properties, in this work, we first generalize the adaptive fractal analysis (AFA) to the adaptive multifractal cross-correlation analysis (AMFCCA), which can be used to study the multifractal cross-correlation between two time series. Considering the complexity of time series from complex systems, we extend AMFCCA to the case of multivariate time series, namely multivariate adaptive multifractal cross-correlation analysis (MV-AMFCCA). In order to detect the multifractality on different time scales, we propose multiscale adaptive multifractal cross-correlation analysis of multivariate time series (MMV-AMFCCA). By the numerical simulation on synthetic multivariate processes, our method shows the theoretical validity. Furthermore, we applied these methods to the multifractal analysis of three pollutants in urban and suburban areas in Beijing. After removing the seasonal trend, we find that the urban and suburban systems both have multifractality, especially the multifractality of the urban system are more evident than the suburban systems, the degree of multifractality in spring and winter stronger than that in summer and autumn. Therefore, our methods are suitable for systems with multiple outputs and provide more comprehensive methods for characterizing autocorrelation and cross-correlation in multivariate time series. © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Perturbation Synergy Attack for Person Re-identification 38

Cross-Modality Perturbation Synergy Attack for Person Re-ide...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Gong, Yunpeng Zhong, Zhun Qu, Yansong Luo, Zhiming Ji, Rongrong Jiang, Min School of Informatics Xiamen University China School of Computer Science and Information Engineering Hefei University of Technology China The Department of Artificial Intelligence Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Key Laboratory of Digital Protection and Intelligent Processing of Intangible CulturalHeritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University Fujian Xiamen361005 China

In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images. However, the safety of cross-modality scenarios, which are more commonly encountered in practical applications involving images captured by infrared cameras, has not received adequate attention. The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities. For instance, infrared images are typically grayscale, unlike visible images that contain color information. Existing attack methods have primarily focused on the characteristics of the visible image modality, overlooking the features of other modalities and the variations in data distribution among different modalities. This oversight can potentially undermine the effectiveness of these methods in image retrieval across diverse modalities. This study represents the first exploration into the security of cross-modality ReID models and proposes a universal perturbation attack specifically designed for cross-modality ReID. This attack optimizes perturbations by leveraging gradients from diverse modality data, thereby disrupting the discriminator and reinforcing the differences between modalities. We conducted experiments on three widely used cross-modality datasets, namely RegDB, SYSU, and LLCM. The results not only demonstrate the effectiveness of our method but also provide insights for future improvements in the robustness of cross-modality ReID systems. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond MLE: convex learning for text generation 23

Beyond MLE: convex learning for text generation

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Chenze Shao Zhengrui Ma Min Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences School of Future Science and Engineering Soochow University

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at https://***/ictnlp/Convex-Learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learned Fingerprint Embedding for Large-Scale Peptide Mass Spectra Retrieval

Learned Fingerprint Embedding for Large-Scale Peptide Mass S...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yongshuai Wang Xiaojun Cai Defeng Li Shiwei Sun Cheng Chen Xuefeng Cui School of Computer Science and Technology Shandong University Qingdao China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Tandem mass spectrometry (MS/MS) is a widely used technique for protein identification, post-translational modifications, immunotherapy, and other applications. As the amount of MS/MS spectra data increases, new computational methods are needed to efficiently search through these databases. This study introduces MS2VEC, a novel fingerprint embedding model designed to facilitate large-scale retrieval of peptide mass spectra. MS2VEC captures the relationships between distant peaks and incorporates position-aware fingerprint features from all peaks. To do this, dilated convolutions are used to capture remote relationships, and a novel position-aware multi-head attention pooling mechanism is used to abstract fingerprint features. The results demonstrate that MS2VEC achieves a top-1 retrieval accuracy of 0.810, outperforming existing methods by 5.1%. Interestingly, the precursor charge is not essential for the retrieval task, as the spectra itself contains enough information to accurately predict the charge. Additionally, the results suggest that weight-balanced fragment ions and water losses are important contributors to fingerprint features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Knowledge Representation Method for Fake News Detection

A Multimodal Knowledge Representation Method for Fake News D...

引用

Computer, Control and Robotics (ICCCR), International Conference on

作者： Fanhao Zeng Jiaxin Yao Yijie Xu Yanhua Liu Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Engineering Research Center of Big Data Intelligence Ministry of Education (Fuzhou University) Fuzhou China

ISBN: (数字)9798350373141

ISBN: (纸本)9798350373158

To address the key challenge encountered in fake news detection, i.e., multimodal data is difficult to be effectively semantically represented due to its intrinsic heterogeneity, this paper proposes a multimodal knowledge representation method for fake news detection. First, visual feature extraction is performed for fake news image data, the relevant images are sliced into multiple blocks, and then visual modal features are obtained by linear projection layer mapping. This simplifies the feature extraction process and reduces the computational cost, which helps to improve the fake news recognition performance. Second, to meet the actual fake news detection needs, a long text representation method based on topic words is investigated for the text data in fake news. Finally, the multimodal representation of the same fake news data is optimized by establishing a connection between two different modalities, visual and text, and inputting it into a BiLSTM-Attention based network to achieve the fusion of multimodal features. The experiment selects the same fake news data of EANN model and uses four classical classification methods to verify the effect of knowledge representation and compare it with the fusion model ViLT which is not optimized for long text. The experiment proves that the accuracy rate of fake news detection using the multimodal representation proposed in this paper is improved by 7.4% compared to the EANN model, and by 9.3% compared to the ViLT representation.

关键词： Digital control Visualization Accuracy Knowledge representation Machine learning Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Token-level Feedback for Controllable Text Generation

arXiv

引用

arXiv 2024年

作者： Li, Wendi Wei, Wei Xu, Kaihe Xie, Wenfeng Chen, Dangyang Cheng, Yu Cognitive Computing and Intelligent Information Processing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology China China Ping An Property & Casualty Insurance company of China China The Chinese University of Hong Kong Hong Kong

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most existing methods suffer from overfitting issues (finetuning-based methods) or semantic collapse (post-processing methods). However, current RL methods are generally guided by coarse-grained (sentence/paragraph-level) feedback, which may lead to suboptimal performance owing to semantic twists or progressions within sentences. To tackle that, we propose a novel reinforcement learning algorithm named TOLE which formulates TOken-LEvel rewards for controllable text generation, and employs a "first-quantize-then-noise" paradigm to enhance the robustness of the RL algorithm. Furthermore, TOLE can be flexibly extended to multiple constraints with little computational expense. Experimental results show that our algorithm can achieve superior performance on both single-attribute and multi-attribute control tasks. We have released our codes at https://***/WindyLee0822/CTG. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Strategy Bus Deviation-Driven Layer Assignment Algorithm

Multi-Strategy Bus Deviation-Driven Layer Assignment Algorit...

引用

Electronics Design Automation (ISEDA), International Symposium of

作者： Yantao Yu Zepeng Li Jiarui Chen Xing Huang Genggeng Liu Ning Xu College of Computer and Data Science Fuzhou University Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China School of Computer Science Northwestern Polytechnical University Xian China School of Information Engineering Wuhan University of Technology Wuhan China

ISBN: (数字)9798350352030

ISBN: (纸本)9798350352047

In modern very large-scale integration (VLSI) design, the solution quality of the bus routing is a crucial factor that determines the timing and power of circuit, and finally affects the performance and yield of chips. Taking bus deviation as the main optimization objective, an effective multi-strategy bus deviation-driven layer assignment algorithm is proposed to solve the timing-matching problem of bus routing. First, a net priority determination method that integrates multiple features is presented to determine the layer assignment order, thus obtaining a routing sequence which can weigh the wirelength and bus deviation well. Second, an effective single net layer assignment algorithm is proposed to assign each net based on dynamic programming, thus reducing the number of vias. Third, a layer shifting strategy based on the bus lookup table is designed to effectively balance total wirelength and bus deviation by sacrificing a certain number of vias. Experimental results, compared to existing work, show that the proposed algorithm can achieve significant optimization on the bus deviation and total wirelength, and finally obtain the best results in terms of the bus deviation, which is the most important optimization objective for bus routing.

关键词： Design automation Heuristic algorithms Very large scale integration Routing Timing Pins Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Computation Offloading Algorithm Based on Deep Reinforcement Learning and Multi-Task Dependency for Edge computing 25th

Computation Offloading Algorithm Based on Deep Reinforcemen...

引用

25th International Computer Symposium on New Trends in Computer Technologies and Applications, ICS 2022

作者： Lin, Tengxiang Lin, Cheng-Kuan Chen, Zhen Cheng, Hongju College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Department of Computer Science National Yang Ming Chiao Tung University Hsinchu300 Taiwan

ISBN: (纸本)9789811995811

Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, significantly reducing service latency. In this paper, we aim to divide the task into several sub-tasks through its inherent interrelation, guided by the idea of high concurrency for synchronization, and then offload sub-tasks to other edge servers so that they can be processed to minimize the cost. Furthermore, we propose a DRL-based Multi-Task Dependency Offloading Algorithm (MTDOA) to solve challenges caused by dependencies between sub-tasks and dynamic working scenes. Firstly, we model the Markov decision process as the task offloading decision. Then, we use the graph attention network to extract the dependency information of different tasks and combine Long Short-term Memory (LSTM) with Deep Q Network (DQN) to deal with time-dependent problems. Finally, simulation experiments demonstrate that the proposed algorithm boasts good convergence ability and is superior to several other baseline algorithms, proving this algorithm’s effectiveness and reliability. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Modality Deep Network for Extreme Learned Image Compression

arXiv

引用

arXiv 2023年

作者： Jiang, Xuhao Tan, Weimin Tan, Tian Yan, Bo Shen, Liquan School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China School of Communication Shanghai University Shanghai China

Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years, but suffer from blur and severe semantics loss at extremely low bitrates. To address this issue, we propose a multimodal machine learning method for text-guided image compression, in which the semantic information of text is used as prior information to guide image compression for better compression performance. We fully study the role of text description in different components of the codec, and demonstrate its effectiveness. In addition, we adopt the image-text attention module and image-request complement module to better fuse image and text features, and propose an improved multimodal semantic-consistent loss to produce semantically complete reconstructions. Extensive experiments, including a user study, prove that our method can obtain visually pleasing results at extremely low bitrates, and achieves a comparable or even better performance than state-of-the-art methods, even though these methods are at 2× to 4× bitrates of ours. Copyright © 2023, The Authors. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Learning Open-Vocabulary Semantic Segmentation Models From Natural Language Supervision

Learning Open-Vocabulary Semantic Segmentation Models From N...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jilan Xu Junlin Hou Yuejie Zhang Rui Feng Yi Wang Yu Qiao Weidi Xie Shanghai Key Lab of Intelligent Information Processing School of Computer Science Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai AI Laboratory CMIC Shanghai Jiao Tong University

This paper considers the problem of open-vocabulary semantic segmentation (OVS), that aims to segment objects of arbitrary classes beyond a pre-defined, closed-set categories. The main contributions are as follows: First, we propose a transformer-based model for OVS, termed as OVSegmentor, which only exploits web-crawled imagetext pairs for pre-training without using any mask annotations. OVSegmentor assembles the image pixels into a set of learnable group tokens via a slotattention based binding module, then aligns the group tokens to corresponding caption embeddings. Second, we propose two proxy tasks for training, namely masked entity completion and cross-image mask consistency. The former aims to infer all masked entities in the caption given group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities. The latter enforces consistent mask predictions between images that contain shared entities, encouraging the model to learn visual invariance. Third, we construct CC4M dataset for pre-training by filtering CC12M with frequently appeared entities, which significantly improves training efficiency. Fourth, we perform zero-shot transfer on four benchmark datasets, PASCAL VOC, PASCAL Context, COCO Object, and ADE20K. OVSegmentor achieves superior results over state-of-the-art approaches on PASCAL VOC using only 3% data (4M vs 134M) for pre-training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：