检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Tao, Shuchang Cao, Qi Shen, Huawei Huang, Junjie Wu, Yunfan Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Node injection attack on Graph Neural networks (GNNs) is an emerging and practical attack scenario that the attacker injects malicious nodes rather than modifying original nodes or edges to affect the performance of GNNs. However, existing node injection attacks ignore extremely limited scenarios, namely the injected nodes might be excessive such that they may be perceptible to the target GNN. In this paper, we focus on an extremely limited scenario of single node injection evasion attack, i.e., the attacker is only allowed to inject one single node during the test phase to hurt GNN’s performance. The discreteness of network structure and the coupling effect between network structure and node features bring great challenges to this extremely limited scenario. We first propose an optimization-based method to explore the performance upper bound of single node injection evasion attack. Experimental results show that 100%, 98.60%, and 94.98% nodes on three public datasets are successfully attacked even when only injecting one node with one edge, confirming the feasibility of single node injection evasion attack. However, such an optimization-based method needs to be re-optimized for each attack, which is computationally unbearable. To solve the dilemma, we further propose a Generalizable Node Injection Attack model, namely G-NIA, to improve the attack efficiency while ensuring the attack performance. Experiments are conducted across three well-known GNNs. Our proposed G-NIA significantly outperforms state-of-the-art baselines and is 500 times faster than the optimization-based method when inferring. Copyright © 2021, The Authors. 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

Learning discrete representations via constrained clustering for effective and efficient dense retrieval

arXiv

引用

arXiv 2021年

作者： Zhan, Jingtao Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Institute for Artificial Intelligence Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Dense Retrieval (DR) has achieved state-of-the-art first-stage ranking effectiveness. However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space. Therefore, we present RepCONC, a novel retrieval model that learns discrete Representations via CONstrained Clustering. RepCONC jointly trains dual-encoders and the Product Quantization (PQ) method to learn discrete document representations and enables fast approximate NNS with compact indexes. It models quantization as a constrained clustering process, which requires the document embeddings to be uniformly clustered around the quantization centroids and supports end-to-end optimization of the quantization method and dual-encoders. We theoretically demonstrate the importance of the uniform clustering constraint in RepCONC and derive an efficient approximate solution for constrained clustering by reducing it to an instance of the optimal transport problem. Besides constrained clustering, RepCONC further adopts a vector-based inverted file system (IVF) to support highly efficient vector search on CPUs. Extensive experiments on two popular ad-hoc retrieval benchmarks show that RepCONC achieves better ranking effectiveness than competitive vector quantization baselines under different compression ratio settings. It also substantially outperforms a wide range of existing retrieval models in terms of retrieval effectiveness, memory efficiency, and time efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Continuous Distributed Processing of Software Defined Radar

Continuous Distributed Processing of Software Defined Radar

引用

IEEE International Conference on Radar

作者： Bing Li Qiang Qiu Shiqi Gong Yongjun Liu Yu Lei CAS Key Lab of Network Data Science and Technology Chinese Academy of Sciences Institute of Computing Technology Beijing China State Key Laboratory of Internet of Things for Smart City University of Macau Macau China National Laboratory of Radar Signal Processing Xidian University Xi'an China Golaxy Data Technology Co. Ltd. Beijing China

ISBN: (纸本)9781665468893

Software-defined radar has been an active research field for more than ten years. However, the low performance and low scalability of the traditional processing techniques of SDR make it hard to deal with complex radar tasks. The stream processing engine is a software that supports low latency and high scalability distributed data processing. It is widely used in log, image, and video processing scenarios but rarely used in radar applications. This paper reviews processing software-defined radar data by using the stream processing engine, and we illustrate the differences between processing log data and radar data. Furthermore, we discuss some optimizations for stream processing engines to get better performance in the radar data processing.

关键词： Protocols Scalability Streaming media Radar imaging data processing Software Hardware

来源：评论

学校读者我要写书评

暂无评论

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information

arXiv

引用

arXiv 2024年

作者： Zhang, Mingkun Li, Jianing Chen, Wei Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Toward the Understanding of Deep Text Matching Models for Information Retrieval

arXiv

引用

arXiv 2021年

作者： Chen, Lijuan Lan, Yanyan Pang, Liang Guo, Jiafeng Cheng, Xueqi Sogou Inc. Beijing China Institute for AI Industry Research Tsinghua University Beijing China Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance improvements. However, most models are black boxes and it is hard to understand what happened in the matching process, due to the poor interpretability of deep learning. This paper aims at tackling this problem. The key idea is to test whether existing deep text matching methods satisfy some fundamental heuristics in information retrieval. Specifically, four heuristics are used in our study, i.e., term frequency constraint, term discrimination constraint, length normalization constraints, and TF-length constraint. Since deep matching models usually contain many parameters, it is difficult to conduct a theoretical study for these complicated functions. In this paper, We propose an empirical testing method. Specifically, We first construct some queries and documents to make them satisfy the assumption in a constraint, and then test to which extend a deep text matching model trained on the original dataset satisfy the corresponding constraint. Besides, a famous attribution based interpretation method, namely integrated gradient, is adopted to conduct detailed analysis and guide for feasible improvement. Experimental results on LETOR 4.0 and MS Marco show that all the investigated deep text matching methods, both representation and interaction based methods, satisfy the above constraints with high probabilities in statistics. We further extend these constraints to the semantic settings, which are shown to be better satisfied for all the deep text matching models. These empirical findings give clear understandings on why deep text matching models usually perform well in information retrieval. We believe the proposed evaluation methodology will be useful for testing future deep text matching models. © 2021, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Account matching across heterogeneous networks

Account matching across heterogeneous networks

引用

International Conference on Game Theory for networks, GameNets

作者： Qiang Liu Jingyuan Li Yuanzhuo Wang Guoliang Xing Yan Ren University of Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China

ISBN: (纸本)9781479979035

Due to the development of web services, many social network sites, as well as online shopping sites have been booming in the past decade, where it is a common phenomenon that people are likely to use multiple services at the same time. Discovering the correspondence between accounts of a same individual is a crucial prerequisite for many interesting cross network applications, such as improving the recommendation performance of the online shopping sites by using extra information from social network services. In this paper, we propose a gametheoretic method to identify correlation accounts of individuals between social network sites and online shopping sites with stable matching model, incorporating accounts profiles as well as historical behaviors. The results show that our method identifies up to 70% of correlation accounts between Facebook and eBay, one of the most popular social network sites and online shopping sites in the world, respectively.

关键词： Games Lead

来源：评论

学校读者我要写书评

暂无评论

Augmentation-aware self-supervision for data-efficient GAN training 23

Augmentation-aware self-supervision for data-efficient GAN t...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Liang Hou Qi Cao Yige Yuan Songtao Zhao Chongyang Ma Siyuan Pan Pengfei Wan Zhongyuan Wang Huawei Shen Xueqi Cheng CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences and Kuaishou Technology CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Kuaishou Technology CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic - harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs. Our code is available at https://***/liang-hou/augself-gan.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A simulator for swarm AUVs acoustic communication networking 11

A simulator for swarm AUVs acoustic communication networking

引用

11th ACM International Conference on Underwater networks and Systems, WUWNet 2016

作者： Li, Guannan Liu, Jun Wang, Xue Xu, Hongli Cui, Jun-Hong Shenyang Institute of Automation CAS University of Chinese Academy of Sciences No. 114 Nanta Street Shenhe District Shenyang China College of Computer Science and Technology Jilin University State Key Laboratory of Robotics Key Laboratory of System Control and Information Processing Ministry of Education of China Changchun China Shenyang Institute of Automation CAS Northeast University No. 114 Nanta Street Shenhe District Shenyang China Shenyang Institute of Automation CAS No. 114 Nanta Street Shenhe District Shenyang China College of Computer Science and Technology Jilin University Changchun China Underwater Sensor Network Lab. University of Connecticut StorrsCT06269 United States

ISBN: (纸本)9781450346375

This paper presents a simulator for swarm operations designed to verify algorithms for a swarm of autonomous underwater robots (AUVs), specifically for constructing an underwater communication network with AUVs carrying acoustic communication devices. This simulator consists of three nodes: a virtual vehicle node (VV), a virtual environment node (VE), and a visual showing node (VS). The modular design treats AUV models as a combination of virtual equipment. An expert acoustic communication simulator is embedded in this simulator, to simulate scenarios with dynamic acoustic communication nodes. The several simulations we have performed demonstrate that this simulator is easy to use and can be further improved.

关键词： Simulators

来源：评论

学校读者我要写书评

暂无评论

Self-supervised GANs with label augmentation 21

Self-supervised GANs with label augmentation

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Liang Hou Huawei Shen Qi Cao Xueqi Cheng Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

ISBN: (纸本)9781713845393

Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment. However, the separate self-supervised tasks in existing self-supervised GANs cause a goal inconsistent with generative modeling due to the fact that their self-supervised classifiers are agnostic to the generator distribution. To address this problem, we propose a novel self-supervised GAN that unifies the GAN task with the self-supervised task by augmenting the GAN labels (real or fake) via self-supervision of data transformation. Specifically, the original discriminator and self-supervised classifier are unified into a label-augmented discriminator that predicts the augmented labels to be aware of both the generator distribution and the data distribution under every transformation, and then provide the discrepancy between them to optimize the generator. Theoretically, we prove that the optimal generator could converge to replicate the real data distribution. Empirically, we show that the proposed method significantly outperforms previous self-supervised and data augmentation GANs on both generative modeling and representation learning across benchmark datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Populating knowledge base with collective entity mentions: A graph-based approach

Populating knowledge base with collective entity mentions: A...

引用

International Conference on Advances in Social network Analysis and Mining, ASONAM

作者： Hailun Lin Yantao Jia Yuanzhuo Wang Xiaolong Jin Xiaojing Li Xueqi Cheng University of Chinese Academy of Sciences Beijing P. R. China CAS Key Laboratory of Network Data Science and Technology Chinese Academy of Sciences Beijing P. R. China

Populating a knowledge base with new entity mentions extracted from unstructured text can help enhance its coverage and freshness. It naturally consists of two subtasks, namely, fine-grained entity classification and entity linking. Existing studies often focus on one of these two subtasks and they usually populate entity mentions in the same text by implicitly assuming that they are independent. However, these entity mentions are often semantically related to each other and it would be better to populate them into the knowledge base collectively. For solving these problems, in this paper we propose an interdependence graph based and unified collective inference approach, called CIIGA, to populating a knowledge base with collective entities, which can jointly determine the proper locations of all entity mentions in the same text by exploiting their interdependence relationships. Experimental results show that this approach can achieve significant accuracy improvement, as compared to the baseline approach, APOLLO, on the task of knowledge base population with multiple entities.

关键词： Knowledge based systems Sociology Statistics Semantics Encyclopedias Electronic publishing

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：