检索结果-内蒙古大学图书馆

Adversarial Immunization for Certifiable Robustness on Graphs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tao, Shuchang Shen, Huawei Cao, Qi Hou, Liang Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Despite achieving strong performance in semi-supervised node classification task, graph neural networks (GNNs) are vulnerable to adversarial attacks, similar to other deep learning models. Existing researches focus on developing either robust GNN models or attack detection methods against adversarial attacks on graphs. However, little research attention is paid to the potential and practice of immunization to adversarial attacks on graphs. In this paper, we propose and formulate the graph adversarial immunization problem, i.e., vaccinating an affordable fraction of node pairs, connected or unconnected, to improve the certifiable robustness of graph against any admissible adversarial attack. We further propose an effective algorithm, called AdvImmune, which optimizes with meta-gradient in a discrete way to circumvent the computationally expensive combinatorial optimization when solving the adversarial immunization problem. Experiments are conducted on two citation networks and one social network. Experimental results demonstrate that the proposed AdvImmune method remarkably improves the ratio of robust nodes by 12%, 42%, 65%, with an affordable immune budget of only 5% edges. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

A linguistic study on relevance modeling in information retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fan, Yixing Guo, Jiafeng Ma, Xinyu Zhang, Ruqing Lan, Yanyan Cheng, Xueqi University of 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

Relevance plays a central role in information retrieval (IR), which has received extensive studies starting from the 20th century. The definition and the modeling of relevance has always been critical challenges in both information science and computer science research areas. Along with the debate and exploration on relevance, IR has already become a core task in many real-world applications, such as Web search engines, question answering systems, conversational bots, and so on. While relevance acts as a unified concept in all these retrieval tasks, the inherent definitions are quite different due to the heterogeneity of these tasks. This raises a question to us: Do these different forms of relevance really lead to different modeling focuses? To answer this question, in this work, we conduct an empirical study on relevance modeling in three representative IR tasks, i.e., document retrieval, answer retrieval, and response retrieval. Specifically, we attempt to study the following two questions: 1) Does relevance modeling in these tasks really show differences in terms of natural language understanding (NLU)? We employ 16 linguistic tasks to probe a unified retrieval model over these three retrieval tasks to answer this question. 2) If there do exist differences, how can we leverage the findings to enhance the relevance modeling? We proposed three intervention methods to investigate how to leverage different modeling focuses of relevance to improve these IR tasks. We believe the way we study the problem as well as our findings would be beneficial to the IR community. © 2021, CC BY.

关键词： Information retrieval

Locally smoothed neural networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Pang, Liang Lan, Yanyan Xu, Jun Guo, Jiafeng Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Convolutional Neural networks (CNN) and the locally connected layer are limited in capturing the importance and relations of different local receptive fields, which are often crucial for tasks such as face verification, visual question answering, and word sequence prediction. To tackle the issue, we propose a novel locally smoothed neural network (LSNN) in this paper. The main idea is to represent the weight matrix of the locally connected layer as the product of the kernel and the smoother, where the kernel is shared over different local receptive fields, and the smoother is for determining the importance and relations of different local receptive fields. Specifically, a multi-variate Gaussian function is utilized to generate the smoother, for modeling the location relations among different local receptive fields. Furthermore, the content information can also be leveraged by setting the mean and precision of the Gaussian function according to the content. Experiments on some variant of MNIST clearly show our advantages over CNN and locally connected layer. Copyright © 2017, The Authors. All rights reserved.

关键词： Convolution

The Impact of Heterogeneous Spreading Abilities of network Ties on Information Spreading

学校读者我要写书评

暂无评论

The Impact of Heterogeneous Spreading Abilities of Network T...

International Conference on Computer and Information technology (CIT)

作者： Chengeng Ou Xiaolong Jin Yuanzhuo Wang Wei Chen Xueqi Cheng University of 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

Understanding the dynamics of information spreading over social networks has been of great interest for a long time. It has been convincingly demonstrated that the topology of a network can significantly affect information spreading over it. Information spreading is often compared on small-world networks and random networks. In this paper, we find that the heterogeneity of spreading abilities of network ties can lead to completely different spreading results over small-world and random networks. In more detail, the more heterogeneous the spreading abilities of network ties, the lower the efficiency of information spreading over small-world networks. Moreover, such heterogeneity not only slows down the spreading pace, but also lengthens the life span of the information spread over small-world networks. On the contrary, if the spreading abilities of network ties are similar or equal, small-world networks are much better than random networks for information spreading.

关键词： Mathematical model Computational modeling Social network services network topology Computers Topology Silicon

FedMatch: Federated learning over heterogeneous question answering data

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Jiangui Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Question Answering (QA), a popular and promising technique for intelligent information access, faces a dilemma about data as most other AI techniques. On one hand, modern QA methods rely on deep learning models which are typically data-hungry. Therefore, it is expected to collect and fuse all the available QA datasets together in a common site for developing a powerful QA model. On the other hand, real-world QA datasets are typically distributed in the form of isolated islands belonging to different parties. Due to the increasing awareness of privacy security, it is almost impossible to integrate the data scattered around, or the cost is prohibited. A possible solution to this dilemma is a new approach known as federated learning, which is a privacy-preserving machine learning technique over distributed datasets. In this work, we propose to adopt federated learning for QA with the special concern on the statistical heterogeneity of the QA data. Here the heterogeneity refers to the fact that annotated QA data are typically with non-identical and independent distribution (non-IID) and unbalanced sizes in practice. Traditional federated learning methods may sacrifice the accuracy of individual models under the heterogeneous situation. To tackle this problem, we propose a novel Federated Matching framework for QA, named FedMatch, with a backbone-patch architecture. The shared backbone is to distill the common knowledge of all the participants while the private patch is a compact and efficient module to retain the domain information for each participant. To facilitate the evaluation, we build a benchmark collection based on several QA datasets from different domains to simulate the heterogeneous situation in practice. Empirical studies demonstrate that our model can achieve significant improvements against the baselines over all the datasets. © 2021, CC BY-NC-ND.

关键词： Deep learning

Focus on the Stability of Large Systems: Toward Automatic Prediction and Analysis of Vulnerability Threat Intelligence

学校读者我要写书评

暂无评论

Focus on the Stability of Large Systems: Toward Automatic Pr...

IEEE International Conference on data science in Cyberspace (DSC)

作者： Shiwen Song Qiong Wu Xin Zheng Peng Wang Yuchen Dou Zhongwen Li Lidong Zhai Institute of Information Engineering Chinese Academy of Sciences BeiJing China Bag Data Academy Zhongke Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665418164

With the increase in the number of users and business volume, the business systems of Internet companies are becoming more and more complex, resulting in a surge in the number of alarms. A large number of dirty alarms add a huge workload to security operations, which indirectly pose a large number of threats to business systems. At present, most systems use the method of accessing third-party Threat Intelligence to assist operators to realize automatic handling of alarms. However, this method has lagging and accuracy problems, making this work always difficult to meet the requirements of fast and accurate. This article proposes a new method for gathering vulnerability Threat Intelligence, which can obtain vulnerability information in advance of security announcements issued by security vendors. By analyzing the vulnerability disclosure process, this method obtains vulnerability information from the original source submitted by open source mail group, of developers. We used NLP technology and XGBoost model to automatically analyze the vulnerability information, and finally generate FINTEL. The experimental result shows that this method has an accuracy of 93%, and can obtain vulnerability information 10h to 7 days before security vendors release. The scope of application covers all open source code repositories and some closed source repositories.

关键词： Machine learning algorithms Scalability Prediction methods Stability analysis Security Surges Research and development

B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ma, Xinyu Guo, Jiafeng Zhang, Ruqing Fan, Yixing Li, Yingyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Pre-training and fine-tuning have achieved remarkable success in many downstream natural language processing (NLP) tasks. Recently, pre-training methods tailored for information retrieval (IR) have also been explored, and the latest success is the PROP method which has reached new SOTA on a variety of ad-hoc retrieval benchmarks. The basic idea of PROP is to construct the representative words prediction (ROP) task for pre-training inspired by the query likelihood model. Despite its exciting performance, the effectiveness of PROP might be bounded by the classical unigram language model adopted in the ROP task construction process. To tackle this problem, we propose a bootstrapped pre-training method (namely B-PROP) based on BERT for ad-hoc retrieval. The key idea is to use the powerful contextual language model BERT to replace the classical unigram language model for the ROP task construction, and re-train BERT itself towards the tailored objective for IR. Specifically, we introduce a novel contrastive method, inspired by the divergence-from-randomness idea, to leverage BERT's self-attention mechanism to sample representative words from the document. By further fine-tuning on downstream ad-hoc retrieval tasks, our method achieves significant improvements over PROP and other baselines, and further pushes forward the SOTA on a variety of ad-hoc retrieval tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Natural language processing systems

MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cui, Wanqing Bi, Keping Guo, Jiafeng Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Since commonsense information has been recorded significantly less frequently than its existence, language models pre-trained by text generation have difficulty to learn sufficient commonsense knowledge. Several studies have leveraged text retrieval to augment the models' commonsense ability. Unlike text, images capture commonsense information inherently but little effort has been paid to effectively utilize them. In this work, we propose a novel Multi-mOdal REtrieval (MORE) augmentation framework, to leverage both text and images to enhance the commonsense ability of language models. Extensive experiments on the Common-Gen task have demonstrated the efficacy of MORE based on the pre-trained models of both single and multiple modalities. © 2024, CC BY-NC-SA.

关键词： Computational linguistics

Multi-View Graph Embedding Learning for Image Co-Segmentation and Co-Localization

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video technology 2024年第6期34卷 4942-4956页

作者： Huang, Aiping Li, Lijian Zhang, Le Niu, Yuzhen Zhao, Tiesong Lin, Chia-Wen Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou350108 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering The Fujian Science and Technology Innovation Laboratory for Optoelectronic Information Fuzhou350108 China Institute of Communications Engineering National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Image co-segmentation and co-localization exploit inter-image information to identify and extract foreground objects with a batch mode. However, they remain challenging when confronted with large object variations or complex backgrounds. This paper proposes a multi-view graph embedding (MV-Gem) learning scheme which integrates diversity, robustness and discernibility of object features to alleviate this phenomenon. To encourage the diversity, the deep co-information containing both low-layer general representations and high-layer semantic information is generated to form a multi-view feature pool for comprehensive co-object description. To enhance the robustness, a multi-view adaptive weighted learning is formulated to fuse the deep co-information for feature complementation. To ensure the discernibility, the graph embedding and sparse constraint are embedded into the fusion formulation for feature selection. The former aims to inherit important structures from multiple views, and the latter further selects important features to restrain irrelevant backgrounds. With these techniques, MV-Gem gradually recovers all co-objects through optimization iterations. Extensive experimental results on real-world datasets demonstrate that MV-Gem is capable of locating and delineating co-objects in an image group. © 1991-2012 IEEE.

关键词： Semantics