检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Kim, Jinuk El Halabi, Marwa Ji, Mingi Song, Hyun Oh Department of Computer Science and Engineering Seoul National University Korea Republic of Neural Processing Research Center Korea Republic of Samsung - SAIT AI Lab Montreal Canada Google United States

Recent works show that reducing the number of layers in a convolutional neural network can enhance efficiency while maintaining the performance of the network. Existing depth compression methods remove redundant non-linear activation functions and merge the consecutive convolution layers into a single layer. However, these methods suffer from a critical drawback;the kernel size of the merged layers becomes larger, significantly undermining the latency reduction gained from reducing the depth of the network. We show that this problem can be addressed by jointly pruning convolution layers and activation functions. To this end, we propose LayerMerge, a novel depth compression method that selects which activation layers and convolution layers to remove, to achieve a desired inference speedup while minimizing performance loss. Since the corresponding selection problem involves an exponential search space, we formulate a novel surrogate optimization problem and efficiently solve it via dynamic programming. Empirical results demonstrate that our method consistently outperforms existing depth compression and layer pruning methods on various network architectures, both on image classification and generation tasks. We release the code at https://***/snu-mllab/LayerMerge. Copyright 2024 by the author(s)

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

On Approximate Opacity of Stochastic Control Systems

引用

IEEE Transactions on Automatic Control 2024年第6期70卷 3846-3861页

作者： Liu, Siyuan Yin, Xiang Dimarogonas, Dimos V. Zamani, Majid Kth Royal Institute of Technology Division of Decision and Control Systems Stockholm Sweden Shanghai Jiao Tong University and Key Lab of System Control & Information Processing Ministry of Education Department of Automation Shanghai China University of Colorado Boulder Computer Science Department CO80309 United States Ludwig Maximilian University of Munich Computer Science Department Germany

This paper investigates an important class of information-flow security property called opacity for stochastic control systems. Opacity captures whether a system's secret behavior (a subset of the system's behavior that is considered to be critical) can be kept from outside observers. Existing works on opacity for control systems only provide a binary characterization of the system's security level by determining whether the system is opaque or not. In this work, we introduce a quantifiable measure of opacity that considers the likelihood of satisfying opacity for stochastic control systems modeled as general Markov decision processes (gMDPs). We also propose verification methods tailored to the new notions of opacity for finite gMDPs by using value iteration techniques. Then, a new notion called approximate opacity-preserving stochastic simulation relation is proposed, which captures the distance between two systems' behaviors in terms of preserving opacity. Based on this new system relation, we show that one can verify opacity for stochastic control systems using their abstractions (modeled as finite gMDPs). We also discuss how to construct such abstractions for a class of gMDPs under certain stability conditions. © 1963-2012 IEEE.

关键词： Stochastic control systems

来源：评论

学校读者我要写书评

暂无评论

DEER: Distribution Divergence-based Graph Contrast for Partial label Learning on Graphs

引用

IEEE Transactions on Multimedia 2024年 1-16页

作者： Gu, Yiyang Chen, Zihao Qin, Yifang Mao, Zhengyang Xiao, Zhiping Ju, Wei Chen, Chong Hua, Xian-Sheng Wang, Yifan Luo, Xiao Zhang, Ming School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University-Anker Embodied AI Lab Peking University Beijing China School of Mathematical Sciences Peking University Beijing China Department of Computer Science University of California Los Angeles USA Terminus Group Beijing China School of Information Technology & Management University of International Business and Economics Beijing China

Graph neural networks (GNNs) have emerged as powerful tools for graph classification tasks. However, contemporary graph classification methods are predominantly studied in fully supervised scenarios, while there could be label ambiguity and noise in real-world applications. In this work, we explore the weakly supervised problem of partial label learning on graphs, where each graph sample is assigned a collection of candidate labels. A novel method called Distribution Divergence-based Graph Contrast (DEER) is proposed to address this issue. At the heart of our DEER is to measure the divergence among the underlying semantic distributions in the hidden space and this metric enables the identification of accurate positive graph pairs for effective graph contrastive learning. Specifically, we generate graph representations of augmented graph views that retain semantics and can be regarded as samples from the underlying semantic distributions. We employ a non-parametric metric to measure distribution divergence, which is then combined with pseudo-labeling to generate unbiased and target-oriented graph pairs. Furthermore, we introduce a label-correction method to eliminate noisy candidate labels, updating target labels using posterior distributions in a soft manner. Comprehensive experiments on various benchmarks demonstrate the superiority of our DEER in different settings compared to a range of state-of-the-art baselines. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A prompt-based approach to adversarial example generation and robustness enhancement

引用

Frontiers of computer science 2024年第4期18卷 85-96页

作者： Yuting YANG Pei HUANG Juan CAO Jintao LI Yun LIN Feifei MA Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Computer Science Stanford UniversityCA 94305USA School of Computing National University of SingaporeSingapore 119077Singapore Laboratory of Parallel Software and Computational Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Recent years have seen the wide application of natural language processing(NLP)models in crucial areas such as finance,medical treatment,and news media,raising concerns about the model robustness and *** find that prompt paradigm can probe special robust defects of pre-trained language *** prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via *** results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym ***,we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization *** on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.

关键词： robustness adversarial example prompt learning pre-trained language model

来源：评论

学校读者我要写书评

暂无评论

Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasets

Diversity Over Size: On the Effect of Sample and Topic Sizes...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Schiller, Benjamin Daxenberger, Johannes Waldis, Andreas Gurevych, Iryna summetix GmbH Germany Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany Information Systems Research Lab Lucerne University of Applied Sciences and Arts Switzerland

ISBN: (纸本)9798891761643

Topic-Dependent Argument Mining (TDAM), that is extracting and classifying argument components for a specific topic from large document sources, is an inherently difficult task for machine learning models and humans alike, as large TDAM datasets are rare and recognition of argument components requires expert knowledge. The task becomes even more difficult if it also involves stance detection of retrieved arguments. In this work, we investigate the effect of TDAM dataset composition in few- and zero-shot settings. Our findings show that, while fine-tuning is mandatory to achieve acceptable model performance, using carefully composed training samples and reducing the training sample size by up to almost 90% can still yield 95% of the maximum performance. This gain is consistent across three TDAM tasks on three different datasets. We also publish a new dataset and code for future benchmarking. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Data collection of wireless sensor network based on trajectory optimization of laser-charged UAV

引用

High-Confidence Computing 2024年第2期4卷 116-128页

作者： Chuanwen Luo Jian Zhang Jin Qian Yi Hong Zhibo Chen Yunan Hou Xiujuan Zhang Yuqing Zhu School of Information Science and Technology Beijing Forestry UniversityBeijing 100083China Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing 100083China College of Information Engineering Taizhou UniversityTaizhou 225300China School of Computer Science Qufu Normal UniversityRizhao 276826China Research Center of Applied Mathematics and Machine Intelligence Zhejiang LabHangzhou 311121China Department of Computer Science California State UniversityCA 90032USA

Unmanned Aerial Vehicle(UAV)can be used as wireless aerial mobile base station for collecting data from sensors in UAV-based Wireless Sensor Networks(WSNs),which is crucial for providing seamless services and improving the performance in the next generation wireless ***,since the UAV are powered by batteries with limited energy capacity,the UAV cannot complete data collection tasks of all sensors without energy replenishment when a large number of sensors are deployed over large monitoring *** overcome this problem,we study the Real-time Data Collection with Lasercharging UAV(RDCL)problem,where the UAV is utilized to collect data from a specified WSN and is recharged using Laser Beam Directors(LBDs).This problem aims to collect all sensory data from the WSN and transport it to the base station by optimizing the flight trajectory of UAV such that realtime data performance is ensured It has been proven that the RDCL problem is *** address this,we initially focus on studying two sub-problems,the Trajectory Optimization of UAV for Data Collection(TODC)problem and the Charging Trajectory Optimization of UAV(CTO)problem,whose objectives are to find the optimal flight plans of UAV in the data collection areas and charging areas,*** we propose an approximation algorithm to solve each of them with the constant ***,we present an approximation algorithm that utilizes the solutions obtained from TODC and CTO problems to address the RDCL ***,the proposed algorithm is verified by extensive simulations.

关键词： Wireless sensor networks Laser-charged UAV Trajectory optimization Data collection

来源：评论

学校读者我要写书评

暂无评论

Incomplete intuitionistic fuzzy behavioral group decision-making based on multigranulation probabilistic rough sets and MULTIMOORA for water quality inspection

引用

Journal of Intelligent and Fuzzy Systems 2023年第3期44卷 4537-4556页

作者： Bai, Wenhui Zhang, Chao Zhai, Yanhui Sangaiah, Arun Kumar School of Computer and Information Technology Key Lab. of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Shanxi Taiyuan China International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

Water quality inspection (WQI) is one of the primary ways to ensure the safe utilization of water resources, and complicated data modeling, fusion and analysis play a significant role in seeking the resource with the best water quality. Nevertheless, the challenges of missing data, relatively large differences in decision results and bounded rationality owned by decision-makers (DMs) in terms of WQI still exist nowadays. Thus, from the aspect of stable and behavioral decision-making in multi-granularity incomplete intuitionistic fuzzy information systems (MG-IIFISs), the paper investigates a comprehensive multi-attribute group decision-making (MAGDM) approach for the application of WQI. First, the concept of MG-IIFISs is built by modeling MAGDM problems with intuitionistic fuzzy numbers (IFNs), then a new transformation scheme is constructed for transforming MG-IIFISs into multi-granularity intuitionistic fuzzy information systems (MG-IFISs) based on the similarity principle. Second, three types of multigranulation intuitionistic fuzzy probabilistic rough sets (MG IF PRSs) are developed by referring to the MULTIMOORA (Multi-Objective Optimization by Ratio Analysis plus the full MULTIplicative form) method. Afterwards, attribute weights are objectively calculated based on the best-worst method (BWM), and a new stable and behavioral MAGDM approach is constructed by means of the TODIM (an acronym in Portuguese for interactive multi-criteria decision-making) method. At last, a case study in the setting of WQI is conducted with the support of a UCI data set, and sensitivity analysis, comparative analysis and experimental analysis are investigated to display the validity of the proposed approach. In general, the proposed approach improves the stability of decision results via MULTIMOORA and BWM, and also fully considers the bounded rationality of DMs' psychological behaviors from the aspect of the TODIM method, which has certain advantages in the community of MAGDM studie

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

Nepali Encoder Transformers: An Analysis of Auto Encoding Transformer Language Models for Nepali Text Classification 1

Nepali Encoder Transformers: An Analysis of Auto Encoding Tr...

引用

1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages, SIGUL 2022

作者： Maskey, Utsav Bhatta, Manish Bhatta, Shiva Raj Dhungel, Sanket Bal, Bal Krishna Information and Language Processing Research Lab Department of Computer Science & Engineering Kathmandu University Dhulikhel Nepal

ISBN: (纸本)9791095546917

Language model pre-training has significantly impacted NLP and resulted in performance gains on many NLP-related tasks, but comparative study of different approaches on many low-resource languages seems to be missing. This paper attempts to investigate appropriate methods for pretraining a Transformer-based model for the Nepali language. We focus on the language-specific aspects that need to be considered for modeling. Although some language models have been trained for Nepali, the study is far from sufficient. We train three distinct Transformer-based masked language models for Nepali text sequences: distilbert-base (Sanh et al., 2019) for its efficiency and minuteness, deberta-base (P. He et al., 2020) for its capability of modeling the dependency of nearby token pairs and XLM-ROBERTa (Conneau et al., 2020) for its capabilities to handle multilingual downstream tasks. We evaluate and compare these models with other Transformer-based models on a downstream classification task with an aim to suggest an effective strategy for training low-resource language models and their fine-tuning. © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation 16th

QS-Craft: Learning to Quantize, Scrabble and Craft for Co...

引用

16th Asian Conference on computer Vision, ACCV 2022

作者： Hong, Yuxin Qian, Xuelin Luo, Simian Guo, Guodong Xue, Xiangyang Fu, Yanwei School of Data Science and MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China School of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Department of CSEE West Virginia University Morgantown United States

ISBN: (纸本)9783031263507

This paper studies the task of conditional Human Motion Animation (cHMA). Given a source image and a driving video, the model should animate the new frame sequence, in which the person in the source image should perform a similar motion as the pose sequence from the driving video. Despite the success of Generative Adversarial Network (GANs) methods in image and video synthesis, it is still very challenging to conduct cHMA due to the difficulty in efficiently utilizing the conditional guided information such as images or poses, and generating images of good visual quality. To this end, this paper proposes a novel model of learning to Quantize, Scrabble, and Craft (QS-Craft) for conditional human motion animation. The key novelties come from the newly introduced three key steps: quantize, scrabble and craft. Particularly, our QS-Craft employs transformer in its structure to utilize the attention architectures. The guided information is represented as a pose coordinate sequence extracted from the driving videos. Extensive experiments on human motion datasets validate the efficacy of our model. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing 38

Efficiently Learning Significant Fourier Feature Pairs for S...

引用

38th Conference on neural information processing Systems, NeurIPS 2024

作者： Ren, Yixin Xia, Yewei Zhang, Hao Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Department of Computer Science and Technology Tongji University Shanghai China SIAT Chinese Academy of Sciences Shenzhen China Machine Learning Department MBZUAI Abu Dhabi United Arab Emirates

We propose a novel method to efficiently learn significant Fourier feature pairs for maximizing the power of Hilbert-Schmidt Independence Criterion (HSIC) based independence tests. We first reinterpret HSIC in the frequency domain, which reveals its limited discriminative power due to the inability to adapt to specific frequency-domain features under the current inflexible configuration. To remedy this shortcoming, we introduce a module of learnable Fourier features, thereby developing a new criterion. We then derive a finite sample estimate of the test power by modeling the behavior of the criterion, thus formulating an optimization objective for significant Fourier feature pairs learning. We show that this optimization objective can be computed in linear time (with respect to the sample size n), which ensures fast independence tests. We also prove the convergence property of the optimization objective and establish the consistency of the independence tests. Extensive empirical evaluation on both synthetic and real datasets validates our method's superiority in effectiveness and efficiency, particularly in handling high-dimensional data and dealing with large-scale scenarios. © 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

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：