检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Memristive computing and Applications, ICMCA 2023

作者： Liu, Aidi Yu, Wenyue Huang, Lili Guo, Jian Lei, Tengfei Zhao, Hui School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Computer and Information Engineering Qilu Institute of Technology China Collaborative Innovation Center of Memristive Computing Application School of Computer and Information Engineering Qilu Institute of Technology China School of Information Science and Engineering University of Jinan Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan China

ISBN: (纸本)9798350316230

This article mainly conducts a series of research on the synchronization control of Cohen-Grossberg neural networks. Firstly, a memristive Cohen-Grossberg neural network model with time-varying delay was constructed, and an equivalent system was obtained by combining inverse function theory, differential inclusion, and set-valued mapping. Secondly, a new predefined-time stability theorem was proposed, and sufficient conditions were obtained to ensure that the drive-response system achieves predefined-time synchronization by designing appropriate control strategy. The simulation results show that the stability time of the error system can be adjusted by the user, verifying the correctness and of the theory. © 2023 IEEE.

关键词： Neural network models

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

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

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

ISBN: (纸本)9798350337488

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. © 2023 IEEE.

关键词： deep learning embedding information retrieval peptide mass spectra tandem mass spectrometry

来源：评论

学校读者我要写书评

暂无评论

Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning 38

Leveraging Catastrophic Forgetting to Develop Safe Diffusion...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Pan, Jiadong Gao, Hongcheng Wu, Zongyu Hu, Taihang Su, Li Huang, Qingming Li, Liang Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China University of Chinese Academy of Sciences China The Pennsylvania State University United States Nankai University China

Diffusion models (DMs) have demonstrated remarkable proficiency in producing images based on textual prompts. Numerous methods have been proposed to ensure these models generate safe images. Early methods attempt to incorporate safety filters into models to mitigate the risk of generating harmful images but such external filters do not inherently detoxify the model and can be easily bypassed. Hence, model unlearning and data cleaning are the most essential methods for maintaining the safety of models, given their impact on model parameters. However, malicious fine-tuning can still make models prone to generating harmful or undesirable images even with these methods. Inspired by the phenomenon of catastrophic forgetting, we propose a training policy using contrastive learning to increase the latent space distance between clean and harmful data distribution, thereby protecting models from being fine-tuned to generate harmful images due to forgetting. The experimental results demonstrate that our methods not only maintain clean image generation capabilities before malicious fine-tuning but also effectively prevent DMs from producing harmful images after malicious fine-tuning. Our method can also be combined with other safety methods to maintain their safety against malicious fine-tuning further. WARNING: This paper contains offensive images generated by models. © 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

Optimized Service Function Deployment in Edge computing Networks Using Deep Reinforcement Learning 7

Optimized Service Function Deployment in Edge Computing Netw...

引用

7th International Conference on Algorithms, computing and Artificial Intelligence, ACAI 2024

作者： Huo, Liuwei Zhu, Bowen Zhao, Dongcheng Institute of intelligent computing University of Electronic Science and Technology of China Chengdu China School of Communication and Information Engineering University of Electronic Science and Technology of China Chengdu China Tianfu Jiangxi Laboratory Chengdu China

ISBN: (纸本)9798331529314

The deployment of service function chains (SFCs) in integrated edge computing networks presents significant challenges, including optimizing resource utilization, minimizing latency, and reducing energy consumption. These challenges arise from the dynamic nature of workloads, varying network conditions, and complex service function dependencies. Conventional optimization approaches often struggle to handle these complexities, as they depend on static models and assumptions that may not apply in practical situations. This paper introduces an innovative solution using deep reinforcement learning (DRL) to overcome these limitations. By modeling the deployment problem as a Markov decision process, we utilize the DRL's capability to learn optimal policies through iterative trial and error interactions with the environment. Our method adaptively adjusts service function placement in real time, accounting for workload variability, service dependencies, and network conditions. Comprehensive simulations demonstrate that our proposed approach achieves significant improvements in terms of latency reduction, resource utilization, and energy consumption compared to conventional methods, and can provide a new solution for SFC deployment. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Conditional selection with CNN augmented transformer for multimodal affective analysis

引用

CAAI Transactions on Intelligence technology 2024年第4期9卷 917-931页

作者： Jianwen Wang Shiping Wang Shunxin Xiao Renjie Lin Mianxiong Dong Wenzhong Guo College of Computer and Data Science Fuzhou UniversityFuzhouChina College of Computer and Cyber Security Fujian Normal UniversityFuzhouChina Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhouChina Digital Fujian Institute of Big Data Security Technology Fujian Normal UniversityFuzhouChina Department of Sciences and Informatics Muroran Institute of TechnologyMuroranJapan

Attention mechanism has been a successful method for multimodal affective analysis in recent years. Despite the advances, several significant challenges remain in fusing language and its nonverbal context information. One is to generate sparse attention coefficients associated with acoustic and visual modalities, which helps locate critical emotional se-mantics. The other is fusing complementary cross‐modal representation to construct optimal salient feature combinations of multiple modalities. A Conditional Transformer Fusion Network is proposed to handle these problems. Firstly, the authors equip the transformer module with CNN layers to enhance the detection of subtle signal patterns in nonverbal sequences. Secondly, sentiment words are utilised as context conditions to guide the computation of cross‐modal attention. As a result, the located nonverbal fea-tures are not only salient but also complementary to sentiment words directly. Experi-mental results show that the authors’ method achieves state‐of‐the‐art performance on several multimodal affective analysis datasets.

关键词： affective computing data fusion information fusion multimodal approaches

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration 38

Speculative Decoding with CTC-based Draft Model for LLM Infe...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 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

REVISITING GRAPH ADVERSARIAL ATTACK AND DEFENSE FROM A DATA DISTRIBUTION PERSPECTIVE 11

REVISITING GRAPH ADVERSARIAL ATTACK AND DEFENSE FROM A DATA ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Li, Kuan Liu, Yang Ao, Xiang He, Qing Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China

Recent studies have shown that structural perturbations are significantly effective in degrading the accuracy of Graph Neural Networks (GNNs) in the semi-supervised node classification (SSNC) task. However, the reasons for the destructive nature of gradient-based methods have not been explored in-depth. In this work, we discover an interesting phenomenon: the adversarial edges are not uniformly distributed on the graph, and a majority of perturbations are generated around the training nodes in poisoning attacks. Combined with this phenomenon, we provide an explanation for the effectiveness of the gradient-based attack method from a data distribution perspective and revisit both poisoning attack and evasion attack in SSNC. From this new perspective, we empirically and theoretically discuss some other attack tendencies. Based on the analysis, we provide nine practical tips on both attack and defense and meanwhile leverage them to improve existing attack and defense methods. Moreover, we design a fast attack method and a self-training defense method, which outperform the state-of-the-art methods and can effectively scale to large graphs like ogbn-arxiv. We validate our claims through extensive experiments on four benchmark datasets. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

The Effect of Data Transformation Techniques on Machine Learning Performance: A Case Study on Student Dropout Prediction 5

The Effect of Data Transformation Techniques on Machine Lear...

引用

5th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2024

作者： Liew, Yeong Chuan Lim, Khai Yin Lim, Ting Yee Tan, Choo Jun Chai, Koh Kiong Deng, Xinjie Tunku Abdul Rahman University of Management and Technology Faculty of Computing and Information Technology Penang Malaysia NEUON AI Sdn Bhd Sarawak Malaysia Institute for Intelligent Systems Research and Innovation Deakin University Geelong Australia

ISBN: (纸本)9798350355925

This study investigates the effects of data transformation techniques on the performance of various machine learning classification models. Specifically, the standard scaler (or Z-score) and min-max scaler techniques coupled with several machine learning and statistical algorithms, including K-Nearest Neighbors, Naive Bayes, Support Vector Machine, and Logistic Regression (LR), are examined systematically. Based on a set of student performance data from an institution, application of the resulting model to predicting student dropout rate is demonstrated. The empirical results indicate that LR with a standard scaler yields the highest AUC (area under the receiver operating characteristic curve) score of 89.95%. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Latency optimization for task offloading in Space-Terrestrial collaborative networks based on deep reinforcement learning

Latency optimization for task offloading in Space-Terrestria...

引用

2024 International Conference on Smart Transportation and City Engineering, STCE 2024

作者： Song, Chuanlong Zhao, Yuxuan He, Jian School of Communication and Information Engineering Shanghai University Shanghai China Shanghai Aerospace Electronic Technology Institute Key Laboratory of Intelligent Computing for Spatial Heterogeneous Network Shanghai China

ISBN: (纸本)9781510690585

Satellite networks, as a crucial component of space communication systems, effectively mitigate the limitations of terrestrial communication networks in edge computing, such as insufficient ground station coverage and susceptibility to natural disasters. Therefore, this paper introduces satellite networks into the context of terrestrial edge computing, constructing a space-terrestrial collaborative network edge computing framework and investigating the latency issues in task offloading. Due to factors such as long communication distances in space-terrestrial networks, limited onboard resources, and rapid relative positional changes between nodes, system latency may increase. This study models the problem as a Markov Decision Process (MDP) with the objective of minimizing system latency. A Deep Deterministic Policy Gradient (DDPG) reinforcement learning algorithm is proposed for the space-terrestrial collaborative network edge computing scenario. Experimental results demonstrate that, compared to local task processing and the Deep Q-Network (DQN) algorithm, the proposed algorithm reduces the overall system overhead by an average of 28.12% and 13.29%, respectively, while also exhibiting better stability and convergence. © 2025 SPIE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

A Semantic Overlay on Blockchain for Supporting Traceability in Cross-border Logistics 2

A Semantic Overlay on Blockchain for Supporting Traceability...

引用

2nd IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2022

作者： Sun, Xiaoping Institute of Computing Technology Chinese Academy of Sciences Key Lab of Intelligent Information Processing Beijing China

ISBN: (纸本)9781665492270

Traceability is important for maintaining quality of logistics transactions and improving logistics efficiency. Implementing traceability for cross-border logistics is facing challenges when it lacks global centralized logistics information management services. Blockchain techniques enable a decentralized cross-border logistics management by publishing logistics transaction on blockchain transactions to support privacy protection and traceability. Logistics transactions involves complex interactions among participants. How to publish those interactions on a blockchain platform is a challenge. We propose a semantic overlay model that publishes a logistics transaction as a semantic link on a blockchain platform for supporting traceability. A semantic link schema model is designed and published on the blockchain platform to validate semantics links for ensuring the correctness of logistics transaction execution. The proposed semantic overlay on blockchain supports further extension of semantic computing in decentralized applications. © 2022 IEEE.

关键词： Blockchain

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：