Bee-Chung Chen, Lei Chen, R. Ramakrishnan, D. Musicant
In this paper, we introduce a new class of data mining problems called learning from aggregate views. In contrast to the traditional problem of learning from a single table of training examples, the new goal is to learn from multiple aggregate views of the underlying data, without access to the un-aggregated data. We motivate this new problem, present a general problem framework, develop learning methods for RFA (Restriction-Free Aggregate) views defined using COUNT, SUM, AVG and STDEV, and offer theoretical and experimental results that characterize the proposed methods.
{"title":"Learning from Aggregate Views","authors":"Bee-Chung Chen, Lei Chen, R. Ramakrishnan, D. Musicant","doi":"10.1109/ICDE.2006.86","DOIUrl":"https://doi.org/10.1109/ICDE.2006.86","url":null,"abstract":"In this paper, we introduce a new class of data mining problems called learning from aggregate views. In contrast to the traditional problem of learning from a single table of training examples, the new goal is to learn from multiple aggregate views of the underlying data, without access to the un-aggregated data. We motivate this new problem, present a general problem framework, develop learning methods for RFA (Restriction-Free Aggregate) views defined using COUNT, SUM, AVG and STDEV, and offer theoretical and experimental results that characterize the proposed methods.","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"492 1","pages":"3-3"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76724219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Continuous spatio-temporal queries have recently received increasing attention due to the abundance of location-aware applications. This paper addresses the Continuous Reverse Nearest Neighbor (CRNN) Query. Given a set of objects O and a query set Q, the CRNN query monitors the exact reverse nearest neighbors of each query point, under the model that both the objects and the query points may move unpredictably. Existing methods for the reverse nearest neighbor (RNN) query either are static or assume a priori knowledge of the trajectory information, and thus do not apply. Related recent work on continuous range query and continuous nearest neighbor query relies on the fact that a simple monitoring region exists. Due to the unique features of the RNN problem, it is non-trivial to even define a monitoring region for the CRNN query. This paper defines the monitoring region for the CRNN query, discusses how to perform initial computation, and then focuses on incremental CRNN monitoring upon updates. The monitoring region according to one query point consists of two types of regions. We argue that the two types should be handled separately. In continuous monitoring, two optimization techniques are proposed. Experimental results prove that our proposed approach is both efficient and scalable.
{"title":"Continuous Reverse Nearest Neighbor Monitoring","authors":"Tian Xia, Donghui Zhang","doi":"10.1109/ICDE.2006.43","DOIUrl":"https://doi.org/10.1109/ICDE.2006.43","url":null,"abstract":"Continuous spatio-temporal queries have recently received increasing attention due to the abundance of location-aware applications. This paper addresses the Continuous Reverse Nearest Neighbor (CRNN) Query. Given a set of objects O and a query set Q, the CRNN query monitors the exact reverse nearest neighbors of each query point, under the model that both the objects and the query points may move unpredictably. Existing methods for the reverse nearest neighbor (RNN) query either are static or assume a priori knowledge of the trajectory information, and thus do not apply. Related recent work on continuous range query and continuous nearest neighbor query relies on the fact that a simple monitoring region exists. Due to the unique features of the RNN problem, it is non-trivial to even define a monitoring region for the CRNN query. This paper defines the monitoring region for the CRNN query, discusses how to perform initial computation, and then focuses on incremental CRNN monitoring upon updates. The monitoring region according to one query point consists of two types of regions. We argue that the two types should be handled separately. In continuous monitoring, two optimization techniques are proposed. Experimental results prove that our proposed approach is both efficient and scalable.","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"5 1","pages":"77-77"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76392151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In multimedia retrieval, a query is typically interactively refined towards the ‘optimal’ answers by exploiting user feedback. However, in existing work, in each iteration, the refined query is re-evaluated. This is not only inefficient but fails to exploit the answers that may be common between iterations. In this paper, we introduce a new approach called SaveRF (Save random accesses in Relevance Feedback) for iterative relevance feedback search. SaveRF predicts the potential candidates for the next iteration and maintains this small set for efficient sequential scan. By doing so, repeated candidate accesses can be saved, hence reducing the number of random accesses. In addition, efficient scan on the overlap before the search starts also tightens the search space with smaller pruning radius. We implemented SaveRF and our experimental study on real life data sets show that it can reduce the I/O cost significantly.
在多媒体检索中，通过利用用户反馈，查询通常被交互式地细化为“最佳”答案。然而，在现有的工作中，在每次迭代中，精炼的查询都会被重新评估。这不仅效率低下，而且无法利用迭代之间可能常见的答案。本文提出了一种新的相关反馈迭代搜索方法SaveRF (Save random access In Relevance Feedback)。SaveRF预测下一次迭代的潜在候选项，并维护这个小集合以进行有效的顺序扫描。这样做可以节省重复的候选访问，从而减少随机访问的数量。此外，在搜索开始前对重叠部分进行高效扫描，以更小的剪枝半径收紧了搜索空间。我们实现了SaveRF，我们对现实生活数据集的实验研究表明，它可以显着降低I/O成本。
{"title":"SaveRF: Towards Efficient Relevance Feedback Search","authors":"Heng Tao Shen, B. Ooi, K. Tan","doi":"10.1109/ICDE.2006.132","DOIUrl":"https://doi.org/10.1109/ICDE.2006.132","url":null,"abstract":"In multimedia retrieval, a query is typically interactively refined towards the ‘optimal’ answers by exploiting user feedback. However, in existing work, in each iteration, the refined query is re-evaluated. This is not only inefficient but fails to exploit the answers that may be common between iterations. In this paper, we introduce a new approach called SaveRF (Save random accesses in Relevance Feedback) for iterative relevance feedback search. SaveRF predicts the potential candidates for the next iteration and maintains this small set for efficient sequential scan. By doing so, repeated candidate accesses can be saved, hence reducing the number of random accesses. In addition, efficient scan on the overlap before the search starts also tightens the search space with smaller pruning radius. We implemented SaveRF and our experimental study on real life data sets show that it can reduce the I/O cost significantly.","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"151 1","pages":"110-110"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76739217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many of the data sources used in stream query processing are known to exhibit bursty behavior. We focus here on passive network monitoring, an application in which the data rates typically exhibit a large peak-to-average ratio. Provisioning a stream query processor to handle peak rates in such a setting can be prohibitively expensive. In this paper, we propose to solve this problem by provisioning the query processor for typical data rates instead of much higher peak data rates. To enable this strategy, we present mechanisms and policies for managing the tradeoffs between the latency and accuracy of query results when bursts exceed the steady-state capacity of the query processor. We describe the current status of our implementation and present experimental results on a testbed network monitoring application to demonstrate the utility of our approach
{"title":"Declarative Network Monitoring with an Underprovisioned Query Processor","authors":"Frederick Reiss, J. Hellerstein","doi":"10.1109/ICDE.2006.46","DOIUrl":"https://doi.org/10.1109/ICDE.2006.46","url":null,"abstract":"Many of the data sources used in stream query processing are known to exhibit bursty behavior. We focus here on passive network monitoring, an application in which the data rates typically exhibit a large peak-to-average ratio. Provisioning a stream query processor to handle peak rates in such a setting can be prohibitively expensive. In this paper, we propose to solve this problem by provisioning the query processor for typical data rates instead of much higher peak data rates. To enable this strategy, we present mechanisms and policies for managing the tradeoffs between the latency and accuracy of query results when bursts exceed the steady-state capacity of the query processor. We describe the current status of our implementation and present experimental results on a testbed network monitoring application to demonstrate the utility of our approach","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"744 1","pages":"56-56"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76879152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sriram Mohan, Jonathan Klinginsmith, Arijit Sengupta, Yuqing Wu
We present ACXESS (Access Control for XML with Enhanced Security Specifications), a system for specifying and enforcing enhanced security constraints on XML via virtual "security views" and query rewrites. ACXESS is the first system that bears the capability to specify and enforce complicated security policies on both subtrees and structural relationships.
{"title":"ACXESS - Access Control for XML with Enhanced Security Specifications","authors":"Sriram Mohan, Jonathan Klinginsmith, Arijit Sengupta, Yuqing Wu","doi":"10.1109/ICDE.2006.12","DOIUrl":"https://doi.org/10.1109/ICDE.2006.12","url":null,"abstract":"We present ACXESS (Access Control for XML with Enhanced Security Specifications), a system for specifying and enforcing enhanced security constraints on XML via virtual \"security views\" and query rewrites. ACXESS is the first system that bears the capability to specify and enforce complicated security policies on both subtrees and structural relationships.","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"23 1","pages":"171-171"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79696932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K-Anonymity has been proposed as a mechanism for protecting privacy in microdata publishing, and numerous recoding "models" have been considered for achieving ��anonymity. This paper proposes a new multidimensional model, which provides an additional degree of flexibility not seen in previous (single-dimensional) approaches. Often this flexibility leads to higher-quality anonymizations, as measured both by general-purpose metrics and more specific notions of query answerability. Optimal multidimensional anonymization is NP-hard (like previous optimal ��-anonymity problems). However, we introduce a simple greedy approximation algorithm, and experimental results show that this greedy algorithm frequently leads to more desirable anonymizations than exhaustive optimal algorithms for two single-dimensional models.
k -匿名被认为是微数据发布中保护隐私的一种机制，许多重新编码“模型”被认为可以实现“匿名”。本文提出了一种新的多维模型，它提供了以前(单维)方法所没有的额外的灵活性。这种灵活性通常会导致更高质量的匿名化，这可以通过通用指标和更具体的查询可回答性概念来衡量。最优多维匿名化是np困难的(就像之前的最优匿名问题一样)。然而，我们引入了一种简单的贪婪近似算法，实验结果表明，对于两个单维模型，这种贪婪算法通常比穷举最优算法产生更理想的匿名化。
{"title":"Mondrian Multidimensional K-Anonymity","authors":"K. LeFevre, D. DeWitt, R. Ramakrishnan","doi":"10.1109/ICDE.2006.101","DOIUrl":"https://doi.org/10.1109/ICDE.2006.101","url":null,"abstract":"K-Anonymity has been proposed as a mechanism for protecting privacy in microdata publishing, and numerous recoding \"models\" have been considered for achieving ��anonymity. This paper proposes a new multidimensional model, which provides an additional degree of flexibility not seen in previous (single-dimensional) approaches. Often this flexibility leads to higher-quality anonymizations, as measured both by general-purpose metrics and more specific notions of query answerability. Optimal multidimensional anonymization is NP-hard (like previous optimal ��-anonymity problems). However, we introduce a simple greedy approximation algorithm, and experimental results show that this greedy algorithm frequently leads to more desirable anonymizations than exhaustive optimal algorithms for two single-dimensional models.","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"1 1","pages":"25-25"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82839072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The problem of frequently updating multi-dimensional indexes arises in many location-dependent applications. While the R-tree and its variants are one of the dominant choices for indexing multi-dimensional objects, the R-tree exhibits inferior performance in the presence of frequent updates. In this paper, we present an R-tree variant, termed the RUM-tree (stands for R-tree with Update Memo) that minimizes the cost of object updates. The RUM-tree processes updates in a memo-based approach that avoids disk accesses for purging old entries during an update process. Therefore, the cost of an update operation in the RUM-tree reduces to the cost of only an insert operation. The removal of old object entries is carried out by a garbage cleaner inside the RUM-tree. In this paper, we present the details of the RUM-tree and study its properties. Theoretical analysis and experimental evaluation demonstrate that the RUMtree outperforms other R-tree variants by up to a factor of eight in scenarios with frequent updates.
{"title":"R-trees with Update Memos","authors":"Xiaopeng Xiong, Walid G. Aref","doi":"10.1109/ICDE.2006.125","DOIUrl":"https://doi.org/10.1109/ICDE.2006.125","url":null,"abstract":"The problem of frequently updating multi-dimensional indexes arises in many location-dependent applications. While the R-tree and its variants are one of the dominant choices for indexing multi-dimensional objects, the R-tree exhibits inferior performance in the presence of frequent updates. In this paper, we present an R-tree variant, termed the RUM-tree (stands for R-tree with Update Memo) that minimizes the cost of object updates. The RUM-tree processes updates in a memo-based approach that avoids disk accesses for purging old entries during an update process. Therefore, the cost of an update operation in the RUM-tree reduces to the cost of only an insert operation. The removal of old object entries is carried out by a garbage cleaner inside the RUM-tree. In this paper, we present the details of the RUM-tree and study its properties. Theoretical analysis and experimental evaluation demonstrate that the RUMtree outperforms other R-tree variants by up to a factor of eight in scenarios with frequent updates.","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"65 1","pages":"22-22"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85127798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An individual’s location-visit pattern, or trail, can be leveraged to link sensitive data back to identity. We propose a secure multiparty computation protocol that enables locations to provably prevent such linkages. The protocol incorporates a controllable parameter specifying the minimum number of identities a sensitive piece of data must be linkable to via its trail.
{"title":"Composition and Disclosure of Unlinkable Distributed Databases","authors":"B. Malin, L. Sweeney","doi":"10.1109/ICDE.2006.41","DOIUrl":"https://doi.org/10.1109/ICDE.2006.41","url":null,"abstract":"An individual’s location-visit pattern, or trail, can be leveraged to link sensitive data back to identity. We propose a secure multiparty computation protocol that enables locations to provably prevent such linkages. The protocol incorporates a controllable parameter specifying the minimum number of identities a sensitive piece of data must be linkable to via its trail.","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"25 1","pages":"118-118"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84029051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Todays abundance of storage coupled with digital technologies in virtually any scientific or commercial application such as medical and biological imaging or music archives deal with tremendous quantities of images, videos or audio files stored in large multimedia databases. For content-based data mining and retrieval purposes suitable similarity models are crucial. The Earth Mover’s Distance was introduced in Computer Vision to better approach human perceptual similarities. Its computation, however, is too complex for usage in interactive multimedia database scenarios. In order to enable efficient query processing in large databases, we propose an index-supported multistep algorithm. We therefore develop new lower bounding approximation techniques for the Earth Mover’s Distance which satisfy high quality criteria including completeness (no false drops), index-suitability and fast computation. We demonstrate the efficiency of our approach in extensive experiments on large image databases
{"title":"Approximation Techniques for Indexing the Earth Mover’s Distance in Multimedia Databases","authors":"I. Assent, Andrea Wenning, T. Seidl","doi":"10.1109/ICDE.2006.25","DOIUrl":"https://doi.org/10.1109/ICDE.2006.25","url":null,"abstract":"Todays abundance of storage coupled with digital technologies in virtually any scientific or commercial application such as medical and biological imaging or music archives deal with tremendous quantities of images, videos or audio files stored in large multimedia databases. For content-based data mining and retrieval purposes suitable similarity models are crucial. The Earth Mover’s Distance was introduced in Computer Vision to better approach human perceptual similarities. Its computation, however, is too complex for usage in interactive multimedia database scenarios. In order to enable efficient query processing in large databases, we propose an index-supported multistep algorithm. We therefore develop new lower bounding approximation techniques for the Earth Mover’s Distance which satisfy high quality criteria including completeness (no false drops), index-suitability and fast computation. We demonstrate the efficiency of our approach in extensive experiments on large image databases","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"91 1","pages":"11-11"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83790023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
It is well recognized that data cubing often produces huge outputs. Two popular efforts devoted to this problem are (1) iceberg cube, where only significant cells are kept, and (2) closed cube, where a group of cells which preserve roll-up/drill-down semantics are losslessly compressed to one cell. Due to its usability and importance, efficient computation of closed cubes still warrants a thorough study. In this paper, we propose a new measure, called closedness, for efficient closed data cubing. We show that closedness is an algebraic measure and can be computed efficiently and incrementally. Based on closedness measure, we develop an an aggregation-based approach, called C-Cubing (i.e., Closed-Cubing), and integrate it into two successful iceberg cubing algorithms: MM-Cubing and Star-Cubing. Our performance study shows that C-Cubing runs almost one order of magnitude faster than the previous approaches. We further study how the performance of the alternative algorithms of C-Cubing varies w.r.t the properties of the data sets.
{"title":"C-Cubing: Efficient Computation of Closed Cubes by Aggregation-Based Checking","authors":"Dong Xin, Zheng Shao, Jiawei Han, Hongyan Liu","doi":"10.1109/ICDE.2006.31","DOIUrl":"https://doi.org/10.1109/ICDE.2006.31","url":null,"abstract":"It is well recognized that data cubing often produces huge outputs. Two popular efforts devoted to this problem are (1) iceberg cube, where only significant cells are kept, and (2) closed cube, where a group of cells which preserve roll-up/drill-down semantics are losslessly compressed to one cell. Due to its usability and importance, efficient computation of closed cubes still warrants a thorough study. In this paper, we propose a new measure, called closedness, for efficient closed data cubing. We show that closedness is an algebraic measure and can be computed efficiently and incrementally. Based on closedness measure, we develop an an aggregation-based approach, called C-Cubing (i.e., Closed-Cubing), and integrate it into two successful iceberg cubing algorithms: MM-Cubing and Star-Cubing. Our performance study shows that C-Cubing runs almost one order of magnitude faster than the previous approaches. We further study how the performance of the alternative algorithms of C-Cubing varies w.r.t the properties of the data sets.","PeriodicalId":6819,"journal":{"name":"22nd International Conference on Data Engineering (ICDE'06)","volume":"93 1","pages":"4-4"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83886403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：