检索结果-内蒙古大学图书馆

Iterative context-aware graph inference for visual dialog

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Guo, Dan Wang, Hui Zhang, Hanwang Zha, Zheng-Jun Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Nanyang Technological University University of Science and Technology of China

Visual dialog is a challenging task that requires the comprehension of the semantic dependencies among implicit visual and textual contexts. This task can refer to the relation inference in a graphical model with sparse contexts and unknown graph structure (relation descriptor), and how to model the underlying context-aware relation inference is critical. To this end, we propose a novel Context-Aware Graph (CAG) neural network. Each node in the graph corresponds to a joint semantic feature, including both object-based (visual) and history-related (textual) context representations. The graph structure (relations in dialog) is iteratively updated using an adaptive top-K message passing mechanism. Specifically, in every message passing step, each node selects the most K relevant nodes, and only receives messages from them. Then, after the update, we impose graph attention on all the nodes to get the final graph embedding and infer the answer. In CAG, each node has dynamic relations in the graph (different related K neighbor nodes), and only the most relevant nodes are attributive to the context-aware relational graph inference. Experimental results on VisDial v0.9 and v1.0 datasets show that CAG outperforms comparative methods. Visualization results further validate the interpretability of our method. Copyright © 2020, The Authors. All rights reserved.

关键词： Message passing

Balanced Tree Partitioning with Succinct Logic

学校读者我要写书评

暂无评论

Balanced Tree Partitioning with Succinct Logic

IEEE International Conference on Big knowledge (ICBK)

作者： Xindong Wu Shaojing Sheng Peng Zhou Key Laboratory of Knowledge Engineering with Big Data (Heifei Unversity of Technology) Ministry of Education Heifei China School of Compuster Science and Technology Anhui University Heifei China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

As a widely used data structure, graphs are good at characterizing data with internal associations, such as social and biological data. Tree structured data are special and are widely used in many real-world applications, such as organizational structure analysis and genealogical knowledge graph reasoning. For example, in kinship knowledge graph analysis, when a genealogical tree is particularly large (more than 25 levels and 45,000 nodes), it is a great challenge to partition this large tree into a specified number of subtrees with succinct logic and a balanced number of nodes. Therefore, in this paper, we propose the TPA (tree partitioning algorithm) algorithm to achieve a balanced and succinct logic partition of large-scale tree structured data. TPA first extracts all related nodes from a massive graph database and then constructs the convergent subgraph into a complete tree with a specified root node. Specifically, several virtual nodes are supplemented for generation-skipping connected nodes to achieve correct node numbering and partitioning. Finally, a graph partitioning algorithm is executed on the complete tree to obtain a specified number of subtrees with succinct logic and balanced node scales. Experiments conducted on four real-world datasets verify the effectiveness of our TPA algorithm.

关键词： Partitioning algorithms data visualization Convergence data analysis Distributed databases Big data

Towards efficient local causal structure learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Shuai Wang, Hao Yu, Kui Cao, Fuyuan Wu, Xindong The School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China The School of Computer and Information Technology Shanxi University Taiyuan030006 China The Key Laboratory of Knowledge Engineering With Big Data Ministry of Education Hefei University of Technology Hefei230601 China Mininglamp Academy of Sciences Mininglamp Technology Beijing100102 China

Local causal structure learning aims to discover and distinguish direct causes (parents) and direct effects (children) of a variable of interest from data. While emerging successes have been made, existing methods need to search a large space to distinguish direct causes from direct effects of a target variable T. To tackle this issue, we propose a novel Efficient Local Causal Structure learning algorithm, named ELCS. Specifically, we first propose the concept of N-structures, then design an efficient Markov Blanket (MB) discovery subroutine to integrate MB learning with N-structures to learn the MB of T and simultaneously distinguish direct causes from direct effects of T. With the proposed MB subroutine, ELCS starts from the target variable, sequentially finds MBs of variables connected to the target variable and simultaneously constructs local causal structures over MBs until the direct causes and direct effects of the target variable have been distinguished. Using eight Bayesian networks the extensive experiments have validated that ELCS achieves better accuracy and efficiency than the state-of-the-art algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Bayesian networks

iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Fei Xu, Jianian Chen, Jiabin Chen, Li Shang, Ruitao Zhou, Zhi Liu, Fangming The Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Computing and Informatics University of Louisiana at Lafayette 301 East Lewis Street LafayetteLA70504 United States The Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Sun Yat-sen University 132 E. Waihuan Road Guangzhou510006 China The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes increasingly compelling. However, GPU sharing inevitably brings severe performance interference among co-located inference workloads, as motivated by an empirical measurement study of DNN inference on EC2 GPU instances. While existing works on guaranteeing inference performance service level objectives (SLOs) focus on either temporal sharing of GPUs or reactive GPU resource scaling and inference migration techniques, how to proactively mitigate such severe performance interference has received comparatively little attention. In this paper, we propose iGniter, an interference-aware GPU resource provisioning framework for cost-efficiently achieving predictable DNN inference in the cloud. iGniter is comprised of two key components: (1) a lightweight DNN inference performance model, which leverages the system and workload metrics that are practically accessible to capture the performance interference;(2) A cost-efficient GPU resource provisioning strategy that jointly optimizes the GPU resource allocation and adaptive batching based on our inference performance model, with the aim of achieving predictable performance of DNN inference workloads. We implement a prototype of iGniter based on the NVIDIA Triton inference server hosted on EC2 GPU instances. Extensive prototype experiments on four representative DNN models and datasets demonstrate that iGniter can guarantee the performance SLOs of DNN inference workloads with practically acceptable runtime overhead, while saving the monetary cost by up to 25% in comparison to the state-of-the-art GPU resource provisioning strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Iterative Context-Aware Graph Inference for Visual Dialog

学校读者我要写书评

暂无评论

Iterative Context-Aware Graph Inference for Visual Dialog

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Dan Guo Hui Wang Hanwang Zhang Zheng-Jun Zha Meng Wang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Nanyang Technological University University of Science and Technology of China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

关键词： Visualization History Task analysis Semantics Message passing Neural networks Cognition

Combining Global and Sequential Patterns for Multivariate Time Series Forecasting

学校读者我要写书评

暂无评论

Combining Global and Sequential Patterns for Multivariate Ti...

IEEE International Conference on Big data

作者： Zhaoxi Li Jun He Hongyan Liu Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China School of Information Renmin University of China Beijing China School of Economics and Management Tsinghua g University Beijing China

ISBN: (数字)9781728162515

ISBN: (纸本)9781728162522

Multivariate time series forecasting is very important for many applications. Many studies have been conducted for accurate and interpretable prediction methods. However, existing methods either cannot take both times series and covariates into consideration, lacking of interpretability, or ignore global trends across multivariate time series. In this paper, we aim to solve these issues. To this end, we propose a new model named TEDGE for accurate and interpretable time series prediction. In this model, we extract global trends hidden across multivariate times series to improve prediction accuracy. Meanwhile, we utilize a deep recurrent model with attention mechanism to find long-and short-term sequential patterns hidden in individual time series with interpretability. We conduct experiments on several datasets to evaluate the proposed models performance. Results demonstrate the superior performance of our proposed model.

关键词： Conferences Time series analysis Predictive models Big data Market research data models Forecasting

DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Jiayi Wu, Wen Shi, Liye Ji, Yu Hu, Wenxin Chen, Xi Zheng, Wei He, Liang School of Computer Science and Technology East China Normal University Shanghai200062 China Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention School of Psychology and Cognitive Science East China Normal University Shanghai200062 China School of Data Science and Engineering East China Normal University Shanghai200062 China Information Technology Services East China Normal University Shanghai200062 China

Sequential recommendations have made great strides in accurately predicting the future behavior of users. However, seeking accuracy alone may bring side effects such as unfair and overspecialized recommendation results. In this work, we focus on the calibrated recommendations for sequential recommendation, which is connected to both fairness and diversity. On the one hand, it aims to provide fairer recommendations whose preference distributions are consistent with users' historical behaviors. On the other hand, it can improve the diversity of recommendations to a certain degree. But existing methods for calibration have mainly relied on the post-processing on the candidate lists, which require more computation time in generating recommendations. In addition, they fail to establish the relationship between accuracy and calibration, leading to the limitation of accuracy. To handle these problems, we propose an end-to-end framework to provide both accurate and calibrated recommendations for sequential recommendation. We design an objective function to calibrate the interests between recommendation lists and historical behaviors. We also provide distribution modification approaches to improve the diversity and mitigate the effect of imbalanced interests. In addition, we design a decoupled-aggregated model to improve the recommendation. The framework assigns two objectives to two individual sequence encoders, and aggregates the outputs by extracting useful information. Experiments on benchmark datasets validate the effectiveness of our proposed model. Copyright © 2022, The Authors. All rights reserved.

关键词： Calibration

Robust optical frequency transfer in a noisy urban fiber network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Xiang Hu, Liang Deng, Xue Zang, Qi Liu, Jie Wang, Dongjie Liu, Tao Dong, Ruifang Zhang, Shougang National Time Service Center Chinese Academy of Sciences Xi’an710600 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Time and Frequency Standards Chinese Academy of Sciences Xi’an710600 China State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Institute for Advanced Communication and Data Science Shanghai Key Laboratory of Navigation and Location-Based Services Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China

Optical fibers have been recognized as one of the most promising host material for high phase coherence optical frequency transfer over thousands of kilometers. In the pioneering work, the active phase noise cancellation (ANC) technique has been widely used for suppressing the fiber phase noise introduced by the environmental perturbations, in which an ideal phase detector with high resolution and unlimited detection range is needed to extract the fiber phase noise, in particular for noisy fiber links. We demonstrate the passive phase noise cancellation (PNC) technique without the need of phase detector could be preferable for noisy fiber links. To avoid the effect of the radio frequency (RF) from the time base at the local site in the conventional active or passive phase noise cancellation techniques, here we introduce a fiber-pigtailed acousto-optic modulator (AOM) with two diffraction order outputs (0 and +1 order) with properly allocating the AOM-driving frequencies allowing to cancel the time base effect. Using this technique, we demonstrate transfer of coherent light through a 260 km noisy urban fiber link. The results show the effect of the RF reference can be successfully removed. After being passively compensated, we demonstrate a fractional frequency instability of 4.9 × 10−14 at the integration time of 1 s and scales down to 10−20 level at 10,000 s in terms of modified Allan deviation over the 260 km noisy urban fiber link. The frequency uncertainty of the retrieved light after transferring through this noise-compensated fiber link relative to that of the input light achieves (0.41 ± 4.7) × 10−18. The proposed technique opens a way to a broad distribution of an ultrastable frequency reference with high coherence without any effects coming from the RF reference and enables a wide range of applications beyond metrology over fiber networks. © 2021, CC BY.

关键词： Natural frequencies

Contrastive Learning for Robust Android Malware Familial Classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China University of Texas at Dallas Dallas United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. © 2021, CC0.

关键词： Android (operating system)