Schema summarization on large-scale databases is a challenge. In a typical large database schema, a great proportion of the tables are closely connected through a few high degree tables. It is thus difficult to separa...
详细信息
Schema summarization on large-scale databases is a challenge. In a typical large database schema, a great proportion of the tables are closely connected through a few high degree tables. It is thus difficult to separate these tables into clusters that represent different topics. Moreover, as a schema can be very big, the schema summary needs to be structured into multiple levels, to further improve the usability. In this paper, we introduce a new schema summarization approach utilizing the techniques of community detection in social networks. Our approach contains three steps. First, we use a community detection algorithm to divide a database schema into subject groups, each representing a specific subject. Second, we cluster the subject groups into abstract domains to form a multi-level navigation structure. Third, we discover representative tables in each cluster to label the schema summary. We evaluate our approach on Freebase, a real world large-scale database. The results show that our approach can identify subject groups precisely. The generated abstract schema layers are very helpful for users to explore database.
A network of many sensors and a base station that are deployed over a region is *** sensor has a transmission range,an interference range and a carrier sensing range,which are r,αr and βr,*** this paper,we study the...
详细信息
A network of many sensors and a base station that are deployed over a region is *** sensor has a transmission range,an interference range and a carrier sensing range,which are r,αr and βr,*** this paper,we study the minimum latency conflict-aware many-to-one data aggregation scheduling problem:Given locations of sensors along with a base station,a subset of all sensors,and parameters r,α and β,to find a schedule in which the data of each sensor in the subset can be transmitted to the base station with no conflicts,such that the latency is *** designe an algorithm based on maximal independent sets,which has a latency bound of(a+19b)R + Δb-a + 5 time slots,where a and b are two constant integers relying on α and β,Δ is the maximum degree of network topology,and R is the trivial lower bound of *** Δ contributes to an additive factor instead of a multiplicative one,thus our algorithm is nearly a constant(a+19b)-ratio.
The low-altitude economy (LAE), as a new economic paradigm, plays an indispensable role in cargo transportation, healthcare, infrastructure inspection, and especially post-disaster communication. Specifically, unmanne...
详细信息
The low-altitude economy (LAE), as a new economic paradigm, plays an indispensable role in cargo transportation, healthcare, infrastructure inspection, and especially post-disaster communication. Specifically, unmanned aerial vehicles (UAVs), as one of the core technologies of the LAE, can be deployed to provide communication coverage, facilitate data collection, and relay data for trapped users, thereby significantly enhancing the efficiency of post-disaster response efforts. However, conventional UAV self-organizing networks exhibit low reliability in long-range cases due to their limited onboard energy and transmit ability. Therefore, in this paper, we design an efficient and robust UAV-swarm enabled collaborative self-organizing network to facilitate post-disaster communications. Specifically, a ground device transmits data to UAV swarms, which then use collaborative beamforming (CB) technique to form virtual antenna arrays and relay the data to a remote access point (AP) efficiently. Then, we formulate a rescue-oriented post-disaster transmission rate maximization optimization problem (RPTRMOP), aimed at maximizing the transmission rate of the whole network. Given the challenges of solving the formulated RPTRMOP by using traditional algorithms, we propose a two-stage optimization approach to address it. In the first stage, the optimal traffic routing and the theoretical upper bound on the transmission rate of the network are derived. In the second stage, we transform the formulated RPTRMOP into a variant named V-RPTRMOP based on the obtained optimal traffic routing, aimed at rendering the actual transmission rate closely approaches its theoretical upper bound by optimizing the excitation current weight and the placement of each participating UAV via a diffusion model-enabled particle swarm optimization (DM-PSO) algorithm. Simulation results show the effectiveness of the proposed two-stage optimization approach in improving the transmission rate of the construct
Partial label learning is a weakly supervised learning framework in which each instance is associated with multiple candidate labels,among which only one is the ground-truth *** paper proposes a unified formulation th...
详细信息
Partial label learning is a weakly supervised learning framework in which each instance is associated with multiple candidate labels,among which only one is the ground-truth *** paper proposes a unified formulation that employs proper label constraints for training models while simultaneously performing *** existing partial label learning approaches that only leverage similarities in the feature space without utilizing label constraints,our pseudo-labeling process leverages similarities and differences in the feature space using the same candidate label constraints and then disambiguates noise *** experiments on artificial and real-world partial label datasets show that our approach significantly outperforms state-of-the-art counterparts on classification prediction.
Local differential privacy(LDP),which is a technique that employs unbiased statistical estimations instead of real data,is usually adopted in data collection,as it can protect every user’s privacy and prevent the lea...
详细信息
Local differential privacy(LDP),which is a technique that employs unbiased statistical estimations instead of real data,is usually adopted in data collection,as it can protect every user’s privacy and prevent the leakage of sensitive *** segment pairs method(SPM),multiple-channel method(MCM)and prefix extending method(PEM)are three known LDP protocols for heavy hitter identification as well as the frequency oracle(FO)problem with large ***,the low scalability of these three LDP algorithms often limits their ***,communication and computation strongly affect their ***,excessive grouping or sharing of privacy budgets makes the results *** address the abovementioned problems,this study proposes independent channel(IC)and mixed independent channel(MIC),which are efficient LDP protocols for FO with a large *** design a flexible method for splitting a large domain to reduce the number of ***,we employ the false positive rate with interaction to obtain an accurate *** experiments demonstrate that IC outperforms all the existing solutions under the same privacy guarantee while MIC performs well under a small privacy budget with the lowest communication cost.
Deep learning has shown significant improvements on various machine learning tasks by introducing a wide spectrum of neural network ***,for these neural network models,it is necessary to label a tremendous amount of t...
详细信息
Deep learning has shown significant improvements on various machine learning tasks by introducing a wide spectrum of neural network ***,for these neural network models,it is necessary to label a tremendous amount of training data,which is prohibitively expensive in *** this paper,we propose OnLine Machine Learning(OLML)database which stores trained models and reuses these models in a new training task to achieve a better training effect with a small amount of training *** efficient model reuse algorithm AdaReuse is developed in the OLML ***,AdaReuse firstly estimates the reuse potential of trained models from domain relatedness and model quality,through which a group of trained models with high reuse potential for the training task could be selected ***,multi selected models will be trained iteratively to encourage diverse models,with which a better training effect could be achieved by *** evaluate AdaReuse on two types of natural language processing(NLP)tasks,and the results show AdaReuse could improve the training effect significantly compared with models training from scratch when the training data is *** on AdaReuse,we implement an OLML database prototype system which could accept a training task as an SQL-like query and automatically generate a training plan by selecting and reusing trained *** studies are conducted to illustrate the OLML database could properly store the trained models,and reuse the trained models efficiently in new training tasks.
Latent Dirichlet allocation(LDA)is a topic model widely used for discovering hidden semantics in massive text *** Gibbs sampling(CGS),as a widely-used algorithm for learning the parameters of LDA,has the risk of priva...
详细信息
Latent Dirichlet allocation(LDA)is a topic model widely used for discovering hidden semantics in massive text *** Gibbs sampling(CGS),as a widely-used algorithm for learning the parameters of LDA,has the risk of privacy ***,word count statistics and updates of latent topics in CGS,which are essential for parameter estimation,could be employed by adversaries to conduct effective membership inference attacks(MIAs).Till now,there are two kinds of methods exploited in CGS to defend against MIAs:adding noise to word count statistics and utilizing inherent *** two kinds of methods have their respective *** sampled from the Laplacian distribution sometimes produces negative word count statistics,which render terrible parameter estimation in *** inherent privacy could only provide weak guaranteed privacy when defending against *** is promising to propose an effective framework to obtain accurate parameter estimations with guaranteed differential *** key issue of obtaining accurate parameter estimations when introducing differential privacy in CGS is making good use of the privacy budget such that a precise noise scale is *** is the first time that R′enyi differential privacy(RDP)has been introduced into CGS and we propose RDP-LDA,an effective framework for analyzing the privacy loss of any differentially private ***-LDA could be used to derive a tighter upper bound of privacy loss than the overestimated results of existing differentially private CGS obtained byε-*** RDP-LDA,we propose a novel truncated-Gaussian mechanism that keeps word count statistics *** we propose distribution perturbation which could provide more rigorous guaranteed privacy than utilizing inherent *** validate that our proposed methods produce more accurate parameter estimation under the JS-divergence metric and obtain lower precision and recall when defending against MIAs.
The cross-domain knowledge diffusion from science to policy is a prevalent phenomenon that demands academic attention. To investigate the characteristics of cross-domain knowledge diffusion from science to policy, thi...
详细信息
The cross-domain knowledge diffusion from science to policy is a prevalent phenomenon that demands academic attention. To investigate the characteristics of cross-domain knowledge diffusion from science to policy, this study suggests using the citation of policies to scientific articles as a basis for quantifying the diffusion strength, breadth, and speed. The study reveals that the strength and breadth of cross-domain knowledge diffusion from scientific papers to policies conform to a power-law distribution, while the speed follows a logarithmic normal distribution. Moreover, the papers with the highest diffusion strength, breadth, and fastest diffusion speed are predominantly from world-renowned universities, scholars, and top journals. The papers with the highest diffusion strength and breadth are mostly from social sciences, especially economics, those with the fastest diffusion speed are mainly from medical and life sciences, followed by social sciences. The findings indicate that cross-domain knowledge diffusion from science to policy follows the Matthew effect, whereby individuals or institutions with high academic achievements are more likely to achieve successful cross-domain knowledge diffusion. Furthermore, papers in the field of economics tend to have the higher cross-domain knowledge diffusion strength and breadth, while those in medical and life sciences have the faster cross-domain knowledge diffusion speed. 86 Annual Meeting of the Association for Information Science & Technology | Oct. 27 – 31, 2023 | London, United Kingdom. Author(s) retain copyright, but ASIS&T receives an exclusive publication license.
Dear editor,This letter presents an unsupervised feature selection method based on machine *** selection is an important component of artificial intelligence,machine learning,which can effectively solve the curse of d...
详细信息
Dear editor,This letter presents an unsupervised feature selection method based on machine *** selection is an important component of artificial intelligence,machine learning,which can effectively solve the curse of dimensionality *** most of the labeled data is expensive to obtain.
Local differential privacy(LDP)approaches to collecting sensitive information for frequent itemset mining(FIM)can reliably guarantee *** current approaches to FIM under LDP add"padding and sampling"steps to ...
详细信息
Local differential privacy(LDP)approaches to collecting sensitive information for frequent itemset mining(FIM)can reliably guarantee *** current approaches to FIM under LDP add"padding and sampling"steps to obtain frequent itemsets and their frequencies because each user transaction represents a set of *** current state-of-the-art approach,namely set-value itemset mining(SVSM),must balance variance and bias to achieve accurate ***,an unbiased FIM approach with lower variance is highly *** narrow this gap,we propose an Item-Level LDP frequency oracle approach,named the Integrated-with-Hadamard-Transform-Based Frequency Oracle(IHFO).For the first time,Hadamard encoding is introduced to a set of values to encode all items into a fixed vector,and perturbation can be subsequently applied to the *** FIM approach,called optimized united itemset mining(O-UISM),is pro-posed to combine the padding-and-sampling-based frequency oracle(PSFO)and the IHFO into a framework for acquiring accurate frequent itemsets with their ***,we theoretically and experimentally demonstrate that O-UISM significantly outperforms the extant approaches in finding frequent itemsets and estimating their frequencies under the same privacy guarantee.
暂无评论