检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 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

Beatgan: Anomalous rhythm detection using adversarially generated time series 28

Beatgan: Anomalous rhythm detection using adversarially gene...

引用

28th International Joint Conference on Artificial Intelligence, IJCAI 2019

作者： Zhou, Bin Liu, Shenghua Hooi, Bryan Cheng, Xueqi Ye, Jing Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science National University of Singapore Singapore Department of Anesthesiology Nanfang Hospital Southern Medical University China CAS Key Laboratory of Network Data Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9780999241141

Given a large-scale rhythmic time series containing mostly normal data segments (or 'beats'), can we learn how to detect anomalous beats in an effective yet efficient way? For example, how can we detect anomalous beats from electrocardiogram (ECG) readings? Existing approaches either require excessively high amounts of labeled and balanced data for classification, or rely on less regularized reconstructions, resulting in lower accuracy in anomaly detection. Therefore, we propose BeatGAN, an unsupervised anomaly detection algorithm for time series data. BeatGAN outputs explainable results to pinpoint the anomalous time ticks of an input beat, by comparing them to adversarially generated beats. Its robustness is guaranteed by its regularization of reconstruction error using an adversarial generation approach, as well as data augmentation using time series warping. Experiments show that BeatGAN accurately and efficiently detects anomalous beats in ECG time series, and routes doctors' attention to anomalous time ticks, achieving accuracy of nearly 0.95 AUC, and very fast inference (2.6 ms per beat). In addition, we show that BeatGAN accurately detects unusual motions from multivariate motion-capture time series data, illustrating its generality. © 2019 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

What makes a successful rebuttal in computer science conferences?: A perspective on social interaction

What makes a successful rebuttal in computer science confere...

引用

作者： Huang, Junjie Huang, Win-bin Bu, Yi Cao, Qi Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Information Management Peking University Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

With an exponential increase in submissionsto top-tier Computer science (CS) conferences, more and more conferences have introduced a rebuttal stage to the conference peer review process. The rebuttal stage can be modeled as social interactions between authors and reviewers. A successful rebuttal often results in an increased review score after the rebuttal stage. In this paper, we conduct an empirical study to determine the factors contributing to a successful rebuttal using over 3000 papers and 13,000 reviews from ICLR2022, one of the most prestigious computer science conferences. First, we observe a significant difference in review scores before and after the rebuttal stage, which is crucial for paper acceptance. Furthermore, we investigate factors from the reviewer's perspective using signed social network analysis. A notable finding is the increase in balanced network structure after the rebuttal stage. Subsequently, we evaluate several quantifiable author rebuttal strategies and their effects on review scores. These strategies can help authors in improving their review scores. Finally, we used machine learning models to predict rebuttal success and validated the impact of potential factors analyzed in this paper. Our experiments demonstrate that the utilization of all features proposed in this study can aid in predicting the success of the rebuttal. In summary, this work presents a study on the impact factors of successful rebuttals from both reviewers’ and authors’ perspectives and lays the foundation for analyzing rebuttals with social network analysis. © 2023 Elsevier Ltd

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective

arXiv

引用

arXiv 2024年

作者： Wen, Yuchen Bi, Keping Chen, Wei Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety ICT CAS Beijing China CAS Key Lab of Network Data Science and Technology ICT CAS Beijing China University of Chinese Academy of Sciences Beijing China

As large language models (LLMs) become an important way of information access, there have been increasing concerns that LLMs may intensify the spread of unethical content, including implicit bias that hurts certain populations without explicit harmful words. In this paper, we conduct a rigorous evaluation of LLMs’ implicit bias towards certain demographics by attacking them from a psychometric perspective to elicit agreements to biased viewpoints. Inspired by psychometric principles in cognitive and social psychology, we propose three attack approaches, i.e., Disguise, Deception, and Teaching. Incorporating the corresponding attack instructions, we built two benchmarks: (1) a bilingual dataset with biased statements covering four bias types (2.7K instances) for extensive comparative analysis, and (2) BUMBLE, a larger benchmark spanning nine common bias types (12.7K instances) for comprehensive evaluation. Extensive evaluation of popular commercial and open-source LLMs shows that our methods can elicit LLMs’ inner bias more effectively than competitive baselines. Our attack methodology and benchmarks offer an effective means of assessing the ethical risks of LLMs, driving progress toward greater accountability in their development. * © 2024, CC BY-NC-SA.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Robot and its living space:A roadmap for robot development based on the view of living space

引用

Digital Communications and networks 2021年第4期7卷 505-517页

作者： Xiaofeng Cai Huansheng Ning Sahraoui Dhelim Rongjuan Zhou Tao Zhang Yang Xu Yueliang Wan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing 100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing 100083China School of Foreign Studies University of Science and Technology Beijing Beijing 100083China Key Lab of Information Network Security Ministry of Public SecurityChina Run Technologies Co. LidBeijing China

Robot’s living space Human-robot relationship Robot humanization Hybrid intelligence Human-robot integrated society Robots,as the creation of humans,became an irreplaceable component in human *** the advancement of technologies,robots have become more and more intelligent and have been widely used in many fields,such as disease diagnosis,customer services,healthcare for the older people,and so *** robots made our lives much more convenient than ever before,they also brought many potential risks and challenges in technology,security,and *** better understand the development of robots,we proposed a concept of a robot’s living space and analyzed the role of robots in our *** this paper,we focus on setting a theoretical framework of the robot’s living space to further understand the human-robot *** research in this paper contains three central ***,we interpret the concept of the robot’s living space and the functions of each ***,we analyze and summarize the relative technologies which support robots living well in each ***,we provide advice and improvement measures based on a discussion of potential problems caused by the developments of *** the trend of robots humanization and human-robot society integration,we should seriously consider how to collaborate with intelligent robots to achieve hybrid *** build a harmonious human-robot integrated society,studying the robot’s living space and its relationship with humans is the prerequisite and roadmap.

关键词： Robot's living space Human-robot relationship Robot humanization Hybrid intelligence Human-robot integrated society

来源：评论

学校读者我要写书评

暂无评论

An application of insurance mechanism in risk management for energy internet

引用

High technology Letters 2018年第2期24卷 196-202页

作者： Yang Yunxue Zhang Qin Zhang Libo CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 P. R. China College of Economics and Management Nanjing University of Aeronautics and Astronautics Nanjing 210016 P. R. China Business College Yantai Nanshan University Yantai 265713 P. R. China

As a completely new residential distribution infrastructure,energy internet facilitates transactions of equipment,energy and services. However,there is security risk under all the *** paper proposes an electricity pricing model based on insurance from the perspective of maximizing the benefits of Energy Internet service providers by using the principal-agent theory. The consumer prepays the provider insurance premiums and signs a contract. The provider sets electricity price according to the premiums and therefore provides differentiated electric services for the consumer. Loss suffered by the consumer due to the power failure is compensated by the provider according to the contract. The equivalent model is presented and a necessary condition of the optimal strategy is obtained on the basis of Pontryagin's maximum principle. At last,a numerical example is presented,which illustrates the effectiveness of the proposed model.

关键词： energy internet insurance risk management optimal control fuzzy theory

来源：评论

学校读者我要写书评

暂无评论

GCN-ALP: Addressing Matching Collisions in Anchor Link Prediction

GCN-ALP: Addressing Matching Collisions in Anchor Link Predi...

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Hao Gao Yongqing Wang Shanshan Lyu Huawei Shen Xueqi Cheng CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

Nowadays online users prefer to join multiple social media for the purpose of socialized online service. The problem anchor link prediction is formalized to link user data with the common ground on user profile, content and network structure across social networks. Most of the traditional works concentrated on learning matching function with explicit or implicit features on observed user data. However, the low quality of observed user data confuses the judgment on anchor links, resulting in the matching collision problem in practice. In this paper, we explore local structure consistency and then construct a matching graph in order to circumvent matching collisions. Furthermore, we propose graph convolution networks with mini-batch strategy, efficiently solving anchor link prediction on matching graph. The experimental results on three real application scenarios show the great potentials of our proposed method in both prediction accuracy and efficiency. In addition, the visualization of learned embeddings provides us a qualitative way to understand the inference of anchor links on the matching graph.

关键词： Convolution Feature extraction Flickr Couplings Computer architecture Trajectory

来源：评论

学校读者我要写书评

暂无评论

GCN-ALP: Addressing matching collisions in anchor link prediction

arXiv

引用

arXiv 2021年

作者： Gao, Hao Wang, Yongqing Lyu, Shanshan Shen, Huawei Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Make It Possible: Multilingual Sentiment Analysis without Much Prior Knowledge

Make It Possible: Multilingual Sentiment Analysis without Mu...

引用

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Zheng Lin Xiaolong Jin Xueke Xu Yuanzhuo Wang Songbo Tan Xueqi Cheng CAS Key Laboratory on Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781479941421

Sentiment analysis is a hard problem, while multilingual sentiment analysis is even harder due to the different expression styles in different languages. Although many methods for multilingual sentiment analysis have been developed in the open literature, most of them suffer from two major problems. The first is their excessive dependence on external tools or resources (e.g., Machine translation systems or bilingual dictionaries), which may not be readily obtained, especially for minority languages, The second is conflictive sentiments, i.e., The sentiment polarity of some parts of a text is inconsistent with its overall sentiment polarity. It is observed that in a product or service review there usually exist a few sentences which play a more important role in determining its sentiment polarity, as compared to others. Therefore, differentiating key sentences from trivial ones may be helpful to improve sentiment analysis. Inspired by this observation in this paper we propose a novel framework to estimate the sentiment polarity of reviews by virtue of opinion lexica and key sentences automatically extracted from unlabelled data. This framework cannot only overcome the problem of excessive dependence on external resources, but also is able to capture the overall sentiment polarity of reviews. Experimental results on realistic review datasets demonstrate that the proposed framework is effective and competitive with the representative baselines.

关键词： Sentiment analysis Dictionaries data mining Training Algorithm design and analysis Google Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improved Far-field Speaker Recognition Method Based Geometry Acoustic Simulation and SpecAugment

Improved Far-field Speaker Recognition Method Based Geometry...

引用

2021 International Conference on Intelligent Computing, Automation and Applications, ICAA 2021

作者： Lian, Yingzi Pang, Jing Inner Mongolia University of Technology College of Science Hohhot China Inner Mongolia Key Lab. of Statistical Analysis Theory for Life Data and Neural Network Modeling Inner Mongolia University of Technology Hohhot China

ISBN: (纸本)9781665437301

Deep learning method has made a great breakthrough in the field of speaker recognition. However, the performance of deep learning method based neural network often degrade in far-field speaker recognition task, with respect to the near-field. One of the indispensable factors is that deep learning performance has a great impact on the quality and diversity of data. Utterance in far-field scenario always mixed with variant reverberation and noise which could interfere the prediction of model. In this paper, we proposed a novel method comprised of geometry acoustic simulation (GAS) and SpecAugment, which makes the performance of deep learning method on far-field speaker recognition task more stable and excellent. Based on near-field speech dataset, by means of physical simulation, far-field speech with different types and characters can be generated to provide as many scenes as possible for speaker recognition. Simultaneously, the SpecAugment method has been applied to enhance the diversity of utterance data on mel-spectrogram. Then, ResNet34 and AM-Softmax Loss were used as the most commonly used methods for feature extraction and model training. Our proposed method has been trained on Voxceleb1 and V oxceleb2 dataset, and test on Vox celeb original test set. Evaluations show that our proposed method has 46% and 40% of EER and minDCF relatively improvement on far-field speaker recognition task. © 2021 IEEE.

关键词： Deep learning

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：