Given a table T in a database and a question Q in natural language, the table question answering (TQA) task aims to return an accurate answer to Q based on the content of T. Recent state-of-the-art solutions leverage large language models (LLMs) to obtain high-quality answers. However, most rely on proprietary, large-scale LLMs with costly API access, posing a significant financial barrier. This paper instead focuses on TQA with smaller, open-weight LLMs that can run on a desktop or laptop. This setting is challenging, as such LLMs typically have weaker capabilities than large proprietary models, leading to substantial performance degradation with existing methods. We observe that a key reason for this degradation is that prior approaches often require the LLM to solve a highly sophisticated task using long, complex prompts, which exceed the capabilities of small open-weight LLMs. Motivated by this observation, we present Orchestra, a multi-agent approach that unlocks the potential of accessible LLMs for high-quality, cost-effective TQA. Orchestra coordinates a group of LLM agents, each responsible for a relatively simple task, through a structured, layered workflow to solve complex TQA problems -- akin to an orchestra. By reducing the prompt complexity faced by each agent, Orchestra significantly improves output reliability. We implement Orchestra on top of AgentScope, an open-source multi-agent framework, and evaluate it on multiple TQA benchmarks using a wide range of open-weight LLMs. Experimental results show that Orchestra achieves strong performance even with small- to medium-sized models. For example, with Qwen2.5-14B, Orchestra reaches 72.1% accuracy on WikiTQ, approaching the best prior result of 75.3% achieved with GPT-4; with larger Qwen, Llama, or DeepSeek models, Orchestra outperforms all prior methods and establishes new state-of-the-art results across all benchmarks.

Analysis of distributed data typically requires the collaboration of the data owners, as well as privacy protection. This paper focuses on the scenario where the database is vertically partitioned onto the data owners (referred to as vertical federated learning or VFL), e.g., an e-commerce platform and an online payment service collaborate to build a model to predict user behavior. To avoid revealing their private data during model fitting, the data owners commonly participate in a cryptographic protocol such as secure multiparty computation. However, the resulting model may still leak sensitive information under sophisticated data extraction attacks. A rigorous solution to this issue is to compute the model with differential privacy (DP), which provides strong and well-accepted privacy guarantees. Enforcing DP on VFL turns out to be highly challenging, and there does not yet exist an effective solution that avoids reliance on any trusted party. Consequently, practitioners are left with rather basic approaches for ensuring DP, e.g., each data owner perturbs her local data with additive noises, leading to suboptimal model utility. Can we achieve privacy-utility trade-offs for VFL with DP comparable to the centralized setting, without trusting any party? In this paper, we make a significant step towards providing a positive answer to this question. We focus on a subset of the data analysis and machine learning tasks-the class of tasks where the sensitive information to release can be expressed as a polynomial function of the input. Following the distributed DP framework that does not require any trusted party, we propose a generic mechanism to solve this class of problems, called the Skellam Quantization Mechanism (SQM). We formally prove the privacy guarantee of our solution, and show that it is able to match the privacy-utility trade-offs in the centralized setting. We then instantiate SQM on two classical tasks, principal component analysis and logistic regression. Extensive experiments on real-world datasets confirm the strong performance of SQM.

Graph Convolutional Networks (GCNs) are a popular machine learning model with a wide range of applications in graph analytics, including healthcare, transportation, and finance. However, a GCN trained without privacy protection measures may memorize private interpersonal relationships in the training data through its model parameters. This poses a substantial risk of compromising privacy through link attacks, potentially leading to violations of privacy regulations such as GDPR. To defend against such attacks, a promising approach is to train the GCN with differential privacy (DP), a rigorous framework that provides strong privacy protection by injecting random noise into the training process. However, training a GCN under DP is a highly challenging task. Existing solutions either perturb the graph topology or inject randomness into the graph convolution operations, or overestimate the amount of noise required, resulting in severe distortions of the network's message aggregation and, thus, poor model utility. Motivated by this, we propose GCON, a novel and effective solution for training GCNs with edge differential privacy. GCON leverages the classic idea of perturbing the objective function to satisfy DP and maintains an unaltered graph convolution process. Our rigorous theoretical analysis offers tight, closed-form bounds on the sensitivity of the graph convolution results and quantifies the impact of an edge modification on the trained model parameters. Extensive experiments using multiple benchmark datasets across diverse settings demonstrate the consistent superiority of GCON over existing solutions, as well as its resilience to link inference attacks.

Releasing relational databases while preserving privacy is an important research problem with numerous applications. A canonical approach is to generate synthetic data under differential privacy (DP), which provides a strong, rigorous privacy guarantee. The problem is particularly challenging when the data involve not only entities (e.g., represented by records in tables) but also relationships (represented by foreign-key references), since if we generate random records for each entity independently, the resulting synthetic data usually fail to exhibit realistic relationships. The current state of the art, PrivLava, addresses this issue by generating random join key attributes through a sophisticated expectation-maximization (EM) algorithm. This method, however, is rather costly in terms of privacy budget consumption, due to the numerous EM iterations needed to retain high data utility. Consequently, the privacy cost of PrivLava can be prohibitive for some real-world scenarios. We observe that the utility of the synthetic data is inherently sensitive to the join keys: changing the primary key of a record t, for example, causes t to join with a completely different set of partner records, which may lead to a significant distribution shift of the join result. Consequently, join keys need to be kept highly accurate, meaning that enforcing DP on them inevitably incurs a high privacy cost. In this paper, we explore a different direction: synthesizing a flattened relation and subsequently decomposing it down to base relations, which eliminates the need to generate join keys. Realizing this idea is challenging, since naively flattening a relational schema leads to a rather high-dimensional table, which is hard to synthesize accurately with differential privacy. We present a sophisticated PrivPetal approach that addresses the above issues via a novel concept: permutation relation , which is constructed as a surrogate to synthesize the flattened relation, avoiding the generation of a high-dimensional relation directly. The synthesis is done using a refined Markov random field mechanism, backed by fine-grained privacy analysis. Extensive experiments using multiple real datasets and the TPC-H benchmark demonstrate that PrivPetal significantly outperforms existing methods in terms of aggregate query accuracy on the synthetic data.

Differentiable architecture search plays a prominent role in Neural Architecture Search (NAS) and exhibits preferable efficiency than traditional heuristic NAS methods, including those based on evolutionary algorithms (EA) and reinforcement learning (RL). However, differentiable NAS methods encounter challenges when dealing with non-differentiable objectives like energy efficiency, resource constraints, and other non-differentiable metrics, especially under multi-objective search scenarios. While the multi-objective NAS research addresses these challenges, the individual training required for each candidate architecture demands significant computational resources. To bridge this gap, this work combines the efficiency of the differentiable NAS with metrics compatibility in multi-objective NAS. The architectures are discretely sampled by the architecture parameter α within the differentiable NAS framework, and α are directly optimised by the policy gradient algorithm. This approach eliminates the need for a sampling controller to be learned and enables the encompassment of non-differentiable metrics. We provide an efficient NAS framework that can be readily customized to address real-world multi-objective NAS (MNAS) scenarios, encompassing factors such as resource limitations and platform specialization. Notably, compared with other multi-objective NAS methods, our NAS framework effectively decreases the computational burden (accounting for just 1/6 of the NSGA-Net). This search framework is also compatible with the other efficiency and performance improvement strategies under the differentiable NAS framework.

Given a group size m and a sensitive dataset D , group privacy (GP) releases information about D (e.g., weights of a neural network trained on D) with the guarantee that the adversary cannot infer with high confidence whether the underlying data is D or a neighboring dataset D ′ that differs from D by m records. GP generalizes the well-established notion of differential privacy (DP) for protecting individuals' privacy; in particular, when m = 1, GP reduces to DP. Compared to DP, GP is capable of protecting the sensitive aggregate information of a group of up to m individuals, e.g., the average annual income among members of a yacht club. Despite its longstanding presence in the research literature and its promising applications, GP is often treated as an afterthought, with most approaches first developing a differential privacy (DP) mechanism and then using a generic conversion to adapt it for GP, treating the DP solution as a black box. As we point out in the paper, this methodology is suboptimal when the underlying DP solution involves subsampling, e.g., in the classic DP-SGD method for training deep learning models. In this case, the DP-to-GP conversion is overly pessimistic in its analysis, leading to high error and low utility in the published results under GP. Motivated by this, we propose a novel analysis framework that provides tight privacy accounting for subsampled GP mechanisms. Instead of converting a black-box DP mechanism to GP, our solution carefully analyzes and utilizes the inherent randomness in subsampled mechanisms, leading to a substantially improved bound on the privacy loss with respect to GP. The proposed solution applies to a wide variety of foundational mechanisms with subsampling. Extensive experiments with real datasets demonstrate that compared to the baseline convert-from-blackbox-DP approach, our GP mechanisms achieve noise reductions of over an order of magnitude in several practical settings, including deep neural network training.

Local differential privacy ( LDP ) is a strong privacy standard that has been adopted by popular software systems, including Chrome, iOS, MacOS, and Windows. The main idea is that each individual perturbs their own data locally, and only submits the resulting noisy version to a data aggregator. Although much effort has been devoted to computing various types of aggregates and building machine learning applications under LDP, research on fundamental perturbation mechanisms has not achieved significant improvement in recent years. Towards a more refined result utility, existing works in the literature mainly focus on improving the worst-case guarantee. However, this approach does not necessarily promise a better average performance given the fact that the data in practice obey a certain distribution, which is not known beforehand. In this paper, we propose the advanced adaptive additive ( AAA ) mechanism, which is a distribution-aware approach that addresses the average utility and tackles the classical mean estimation problem. AAA is carried out in a two-step approach: first, as the global data distribution is not available beforehand, the data aggregator selects a random subset of individuals to compute a (noisy) quantized data descriptor; then, in the second step, the data aggregator collects data from the remaining individuals, which are perturbed in a distribution-aware fashion. The perturbation involved in the latter step is obtained by solving an optimization problem, which is formulated with the data descriptor obtained in the former step and the desired properties of task-determined utilities. We provide rigorous privacy proofs and utility analyses, as well as extensive experiments comparing AAA with state-of-the-art mechanisms. The evaluation results demonstrate that the AAA mechanism consistently outperforms existing solutions with a clear margin in terms of result utility, on a wide range of privacy constraints and real-world and synthetic datasets.

A bipartite graph is a graph that consists of two disjoint sets of vertices and only edges between vertices from different vertex sets. In this paper, we study the counting problems of two common types of em motifs in bipartite graphs: (i) butterflies (2x2 bicliques) and (ii) bi-triangles (length-6 cycles). Unlike most of the existing algorithms that aim to obtain exact counts, our goal is to obtain precise enough estimations of these counts in bipartite graphs, as such estimations are already sufficient and of great usefulness in various applications. While there exist approximate algorithms for butterfly counting, these algorithms are mainly based on the techniques designed for general graphs, and hence, they are less effective on bipartite graphs. Not to mention that there is still a lack of study on approximate bi-triangle counting. Motivated by this, we first propose a novel butterfly counting algorithm, called one-sided weighted sampling, which is tailored for bipartite graphs. The basic idea of this algorithm is to estimate the total butterfly count with the number of butterflies containing two randomly sampled vertices from the same side of the two vertex sets. We prove that our estimation is unbiased, and our technique can be further extended (non-trivially) for bi-triangle count estimation. Theoretical analyses under a power-law random bipartite graph model and extensive experiments on multiple large real datasets demonstrate that our proposed approximate counting algorithms can reach high accuracy, yet achieve up to three orders (resp. four orders) of magnitude speed-up over the state-of-the-art exact butterfly (resp. bi-triangle) counting algorithms. Additionally, we present an approximate clustering coefficient estimation framework for bipartite graphs, which shows a similar speed-up over the exact solutions with less than 1% relative error.

Distributed vertex-centric graph systems, or VC-systems, have achieved tremendous success in the industry. A common usage pattern of VC-systems is multi-processing, or the concurrent processing of multiple unit tasks. Example multi-processing includes answering multiple single-source shortest path queries on a graph. However, concurrent processing of all the unit tasks may overload the system with excessive memory usage, leading to intolerable system delays. To ad-dress the important challenge, we present V C- Tune, a system with a convenient interface to help practitioners orchestrate the unit tasks for improving the overall performance within the system limit. This demonstration allows the audience to interact with our system to explore the configuration space of multi-processing in VC-systems and compare different sys-tem configurations. In addition, we embed into the system an automatic configuration search algorithm, which can directly recommend to the practitioners a suitable configuration that gives a satisfactory system performance. An introduction video is at (https://sites.google.com/view/vc-tune-video).

Deep neural networks have strong capabilities of memorizing the underlying training data, which can be a serious privacy concern. An effective solution to this problem is to train models withdifferential privacy(DP), which provides rigorous privacy guarantees by injecting random noise to the gradients. This paper focuses on the scenario where sensitive data are distributed among multiple participants, who jointly train a model throughfederated learning, using bothsecure multiparty computation(MPC) to ensure the confidentiality of each gradient update, and differential privacy to avoid data leakage in the resulting model. A major challenge in this setting is that common mechanisms for enforcing DP in deep learning, which injectreal-valued noise, are fundamentally incompatible with MPC, which exchangesfinite-field integersamong the participants. Consequently, most existing DP mechanisms require rather high noise levels, leading to poor model utility. Motivated by this, we proposeSkellam mixture mechanism(SMM), a novel approach to enforcing DP on models built via federated learning. Compared to existing methods, SMM eliminates the assumption that the input gradients must be integer-valued, and, thus, reduces the amount of noise injected to preserve DP. The theoretical analysis of SMM is highly non-trivial, especially considering (i) the complicated math of DP deep learning in general and (ii) the fact that the mixture of two Skellam distributions is rather complex. Extensive experiments on various practical settings demonstrate that SMM consistently and significantly outperforms existing solutions in terms of the utility of the resulting model.

Given a graph G where each node is associated with a set of attributes, and a parameter k specifying the number of output clusters, k-attributed graph clustering (k-AGC) groups nodes in G into k disjoint clusters, such that nodes within the same cluster share similar topological and attribute characteristics, while those in different clusters are dissimilar. This problem is challenging on massive graphs, e.g., with millions of nodes and billions of attribute values. For such graphs, existing solutions either incur prohibitively high costs, or produce clustering results with compromised quality.

Local differential privacy (LDP) is a well-established privacy protection scheme for collecting sensitive data, which has been integrated into major platforms such as iOS, Chrome, and Windows. The main idea is that each individual randomly perturbs her data on her local device, and only uploads the noisy version to an untrusted data aggregator. This paper focuses on the collection of streaming data consisting of regular updates, e.g. , daily app usage. Such streams, when aggregated over a large population, often exhibit strong autocorrelations , e.g. , the average usage of an app usually does not change dramatically from one day to the next. To our knowledge, this property has been largely neglected in existing LDP mechanisms. Consequently, data collected with current LDP methods often exhibit unrealistically violent fluctuations due to the added noise, drowning the overall trend, as shown in our experiments. This paper proposes a novel correlated Gaussian mechanism ( CGM ) for enforcing (ϵ, δ)-LDP on streaming data collection, which reduces noise by exploiting public-known autocorrelation patterns of the aggregated data. This is done through non-trivial modifications to the core of the underlying Gaussian Mechanism; in particular, CGM injects temporally correlated noise, computed through an optimization program that takes into account the given autocorrelation pattern, data value range, and utility metric. CGM comes with formal proof of correctness, and consumes negligible computational resources. Extensive experiments using real datasets from different application domains demonstrate that CGM achieves consistent and significant utility gains compared to the baseline method of repeatedly running the underlying one-shot LDP mechanism.

Given a graph G and a node u ∈ G, a single source SimRank query evaluates the similarity between u and every node v ∈ G. Existing approaches to single source SimRank computation incur either long query response time, or expensive pre-computation, which needs to be performed again whenever the graph G changes. Consequently, to our knowledge none of them is ideal for scenarios in which (i) query processing must be done in realtime, and (ii) the underlying graph G is massive, with frequent updates. Motivated by this, we propose SimPush, a novel algorithm that answers single source SimRank queries without any pre-computation, and achieves significantly higher query speed than even the fastest known index-based solutions. Further, SimPush provides rigorous result quality guarantees, and its high performance does not rely on any strong assumption of the graph. Specifically, compared to existing methods, SimPush employs a radically different algorithmic design that focuses on (i) identifying a small number of nodes relevant to the query, and subsequently (ii) computing statistics and performing residue push from these nodes only. We prove the correctness of SimPush, analyze its time complexity, and compare its asymptotic performance with that of existing methods. Meanwhile, we evaluate the practical performance of SimPush through extensive experiments on 9 real datasets. The results demonstrate that SimPush consistently outperforms all existing solutions, often by over an order of magnitude. In particular, on a commodity machine, SimPush answers a single source SimRank query on a web graph containing over 133 million nodes and 5.4 billion edges in under 62 milliseconds, with 0.00035 empirical error, while the fastest index-based competitor needs 1.18 seconds.

Given a graph G where each node is associated with a set of attributes, attributed network embedding (ANE) maps each node v ∈ G to a compact vector X v , which can be used in downstream machine learning tasks. Ideally, X v should capture node v 's affinity to each attribute, which considers not only v 's own attribute associations, but also those of its connected nodes along edges in G . It is challenging to obtain high-utility embeddings that enable accurate predictions; scaling effective ANE computation to massive graphs with millions of nodes pushes the difficulty of the problem to a whole new level. Existing solutions largely fail on such graphs, leading to prohibitive costs, low-quality embeddings, or both. This paper proposes PANE, an effective and scalable approach to ANE computation for massive graphs that achieves state-of-the-art result quality on multiple benchmark datasets, measured by the accuracy of three common prediction tasks: attribute inference, link prediction, and node classification. In particular, for the large MAG data with over 59 million nodes, 0.98 billion edges, and 2000 attributes, PANE is the only known viable solution that obtains effective embeddings on a single server, within 12 hours. PANE obtains high scalability and effectiveness through three main algorithmic designs. First, it formulates the learning objective based on a novel random walk model for attributed networks. The resulting optimization task is still challenging on large graphs. Second, PANE includes a highly efficient solver for the above optimization problem, whose key module is a carefully designed initialization of the embeddings, which drastically reduces the number of iterations required to converge. Finally, PANE utilizes multi-core CPUs through non-trivial parallelization of the above solver, which achieves scalability while retaining the high quality of the resulting embeddings. Extensive experiments, comparing 10 existing approaches on 8 real datasets, demonstrate that PANE consistently outperforms all existing methods in terms of result quality, while being orders of magnitude faster.

Given an input graph G and a node v ∈ G , homogeneous network embedding (HNE) maps the graph structure in the vicinity of v to a compact, fixed-dimensional feature vector. This paper focuses on HNE for massive graphs, e.g. , with billions of edges. On this scale, most existing approaches fail, as they incur either prohibitively high costs, or severely compromised result utility. Our proposed solution, called Node-Reweighted PageRank (NRP), is based on a classic idea of deriving embedding vectors from pairwise personalized PageRank (PPR) values. Our contributions are twofold: first, we design a simple and efficient baseline HNE method based on PPR that is capable of handling billion-edge graphs on commodity hardware; second and more importantly, we identify an inherent drawback of vanilla PPR, and address it in our main proposal NRP. Specifically, PPR was designed for a very different purpose, i.e. , ranking nodes in G based on their relative importance from a source node's perspective. In contrast, HNE aims to build node embeddings considering the whole graph. Consequently, node embeddings derived directly from PPR are of suboptimal utility. The proposed NRP approach overcomes the above deficiency through an effective and efficient node reweighting algorithm, which augments PPR values with node degree information, and iteratively adjusts embedding vectors accordingly. Overall, NRP takes O ( m log n ) time and O ( m ) space to compute all node embeddings for a graph with m edges and n nodes. Our extensive experiments that compare NRP against 18 existing solutions over 7 real graphs demonstrate that NRP achieves higher result utility than all the solutions for link prediction, graph reconstruction and node classification, while being up to orders of magnitude faster. In particular, on a billion-edge Twitter graph, NRP terminates within 4 hours, using a single CPU core.

In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation model (DBRec). DBRec performs latent user/item group discovery simultaneously with collaborative filtering, and interacts group information with users/items for bridging similar users/items. Therefore, a user's preference over an unobserved item, in DBRec, can be bridged by the users within the same group who have rated the item, or the user-rated items that share the same group with the unobserved item. In addition, we propose to jointly learn user-user group (item-item group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations. We jointly integrate collaborative filtering, latent group discovering and hierarchical modelling into a unified framework, so that all the model parameters can be learned toward the optimization of the objective function. We validate the effectiveness of the proposed model with two real datasets, and demonstrate its advantage over the state-of-the-art recommendation models with extensive experiments.

Local differential privacy (LDP) is a recently proposed privacy standard for collecting and analyzing data, which has been used, e.g., in the Chrome browser, iOS and macOS. In LDP, each user perturbs her information locally, and only sends the randomized version to an aggregator who performs analyses, which protects both the users and the aggregator against private information leaks. Although LDP has attracted much research attention in recent years, the majority of existing work focuses on applying LDP to complex data and/or analysis tasks. In this paper, we point out that the fundamental problem of collecting multidimensional data under LDP has not been addressed sufficiently, and there remains much room for improvement even for basic tasks such as computing the mean value over a single numeric attribute under LDP. Motivated by this, we first propose novel LDP mechanisms for collecting a numeric attribute, whose accuracy is at least no worse (and usually better) than existing solutions in terms of worst-case noise variance. Then, we extend these mechanisms to multidimensional data that can contain both numeric and categorical attributes, where our mechanisms always outperform existing solutions regarding worst-case noise variance. As a case study, we apply our solutions to build an LDP-compliant stochastic gradient descent algorithm (SGD), which powers many important machine learning tasks. Experiments using real datasets confirm the effectiveness of our methods, and their advantages over existing solutions.

Given a graph G , a source node s ∈ G and a positive integer k , a top- k Personalized PageRank (PPR) query returns the k nodes with the highest PPR values with respect to s , where the PPR of a node v measures its relevance from the perspective of source s. Top- k PPR processing is a fundamental task in many important applications such as web search, social networks, and graph analytics. This paper aims to answer such a query in realtime , i.e., within less than 100ms, on an Internet-scale graph with billions of edges. This is far beyond the current state of the art, due to the immense computational cost of processing a PPR query. We achieve this goal with a novel algorithm kPAR, which utilizes the massive parallel processing power of GPUs. The main challenge in designing a GPU-based PPR algorithm lies in that a GPU is mainly a parallel computation device, whereas PPR processing involves graph traversals and value propagation operations, which are inherently sequential and memory-bound. Existing scalable PPR algorithms are mostly described as single-thread CPU solutions that are resistant to parallelization. Further, they usually involve complex data structures which do not have efficient adaptations on GPUs. kPAR overcomes these problems via both novel algorithmic designs (namely, adaptive forward push and inverted random walks ) and system engineering (e.g., load balancing) to realize the potential of GPUs. Meanwhile, kPAR provides rigorous guarantees on both result quality and worst-case efficiency. Extensive experiments show that kPAR is usually 10x faster than parallel adaptations of existing methods. Notably, on a billion-edge Twitter graph, kPAR answers a top-1000 PPR query in 42.4 milliseconds.

Given a graph G , a source node s, and a target node t , the personalized PageRank ( PPR ) of t with respect to s is the probability that a random walk starting from s terminates at t . An important variant of the PPR query is single-source PPR ( SSPPR ), which enumerates all nodes in G and returns the top- k nodes with the highest PPR values with respect to a given source s . PPR in general and SSPPR in particular have important applications in web search and social networks, e.g., in Twitter’s Who-To-Follow recommendation service. However, PPR computation is known to be expensive on large graphs and resistant to indexing. Consequently, previous solutions either use heuristics, which do not guarantee result quality, or rely on the strong computing power of modern data centers, which is costly. Motivated by this, we propose effective index-free and index-based algorithms for approximate PPR processing, with rigorous guarantees on result quality. We first present FORA, an approximate SSPPR solution that combines two existing methods—Forward Push (which is fast but does not guarantee quality) and Monte Carlo Random Walk (accurate but slow)—in a simple and yet non-trivial way, leading to both high accuracy and efficiency. Further, FORA includes a simple and effective indexing scheme, as well as a module for top- k selection with high pruning power. Extensive experiments demonstrate that the proposed solutions are orders of magnitude more efficient than their respective competitors. Notably, on a billion-edge Twitter dataset, FORA answers a top-500 approximate SSPPR query within 1s, using a single commodity server.

A mobile operating system often needs to collect frequent new terms from users in order to build and maintain a comprehensive dictionary. Collecting keyboard usage data, however, raises privacy concerns. Local differential privacy (LDP) has been established as a strong privacy standard for collecting sensitive information from users. Currently, the best known solution for LDP-compliant frequent term discovery transforms the problem into collecting n-grams under LDP, and subsequently reconstructs terms from the collected n-grams by modelling the latter into a graph, and identifying cliques on this graph. Because the transformed problem (i.e., collecting n-grams) is very different from the original one (discovering frequent terms), the end result has poor utility. Further, this method is also rather expensive due to clique computation on a large graph. In this paper we tackle the problem head on: our proposal, PrivTrie, directly collects frequent terms from users by iteratively constructing a trie under LDP. While the methodology of building a trie is an obvious choice, obtaining an accurate trie under LDP is highly challenging. PrivTrie achieves this with a novel adaptive approach that conserves privacy budget by building internal nodes of the trie with the lowest level of accuracy necessary. Experiments using real datasets confirm that PrivTrie achieves high accuracy on common privacy levels, and consistently outperforms all previous methods.

Differential privacy, which has been applied in Google Chrome and Apple iOS, provides strong privacy assurance to users while retaining the capability to discover statistical patterns from sensitive data. We focus on top-k frequent itemset mining on sensitive data, with the goal of obtaining high result utility while satisfying differential privacy. There are two basic methodologies to design a high-utility solution: one uses generic differential privacy mechanisms as building blocks, and minimizes result error through algorithm design. Most existing work follows this approach. The other methodology is to devise a new building block customized for frequent itemset mining. This is much more challenging: to our knowledge, only one recent work, NoisyCut, attempts to do so, unfortunately, Noisycut has been found to violate differential privacy. This paper proposes a novel solution PrivSuper, which contains both a new algorithm and a new differential privacy mechanism. Unlike most existing methods that follow the Apriori framework, which starts from single items and iteratively forms larger itemsets, PrivSuper directly searches for maximal frequent itemsets, and subsequently adds their sub-itemsets to the results without additional privacy budget consumption. During the search, PrivSuper applies a customized mechanism to extend the current itemset with one more item, which we call the sequence exponential mechanism (SEM). Notably, SEM does not consume any privacy budget at all, if it turns out that the current itemset cannot be extended. Extensive experiments using several real datasets demonstrate that PrivSuper achieves significantly higher result utility compared to previous solutions.

Given a graph G, a source node s and a target node t, the personalized PageRank (PPR) of t with respect to s is the probability that a random walk starting from s terminates at t. A single-source PPR (SSPPR) query enumerates all nodes in G, and returns the top-k nodes with the highest PPR values with respect to a given source node s. SSPPR has important applications in web search and social networks, e.g., in Twitter's Who-To-Follow recommendation service. However, SSPPR computation is immensely expensive, and at the same time resistant to indexing and materialization. So far, existing solutions either use heuristics, which do not guarantee result quality, or rely on the strong computing power of modern data centers, which is costly.

Differential privacy enables organizations to collect accurate aggregates over sensitive data with strong, rigorous guarantees on individuals' privacy. Previous work has found that under differential privacy, computing multiple correlated aggregates as a batch, using an appropriate strategy, may yield higher accuracy than computing each of them independently. However, finding the best strategy that maximizes result accuracy is non-trivial, as it involves solving a complex constrained optimization program that appears to be non-convex. Hence, in the past much effort has been devoted in solving this non-convex optimization program. Existing approaches include various sophisticated heuristics and expensive numerical solutions. None of them, however, guarantees to find the optimal solution of this optimization problem.

An in-memory database cluster consists of multiple interconnected nodes with a large capacity of RAM and modern multi-core CPUs. As a conventional query processing strategy, pipelining remains a promising solution for in-memory parallel database systems, as it avoids expensive intermediate result materialization and parallelizes the data processing among nodes. However, to fully unleash the power of pipelining in a cluster with multi-core nodes, it is crucial for the query optimizer to generate good query plans with appropriate intra-node parallelism, in order to maximize CPU and network bandwidth utilization. A suboptimal plan, on the contrary, causes load imbalance in the pipelines and consequently degrades the query performance. Parallelism assignment optimization at compile time is nearly impossible, as the workload in each node is affected by numerous factors and is highly dynamic during query evaluation. To tackle this problem, we propose elastic pipelining, which makes it possible to optimize intra-node parallelism assignments in the pipelines based on the actual workload at runtime. It is achieved with the adoption of new elastic iterator model and a fully optimized dynamic scheduler. The elastic iterator model generally upgrades traditional iterator model with new dynamic multi-core execution adjustment capability. And the dynamic scheduler efficiently provisions CPU cores to query execution segments in the pipelines based on the light-weight measurements on the operators. Extensive experiments on real and synthetic (TPC-H) data show that our proposal achieves almost full CPU utilization on typical decision-making analytical queries, outperforming state-of-the-art open-source systems by a huge margin.

In a constrained shortest path (CSP) query, each edge in the road network is associated with both a length and a cost. Given an origin s , a destination t , and a cost constraint θ , the goal is to find the shortest path from s to t whose total cost does not exceed θ . Because exact CSP is NP-hard, previous work mostly focuses on approximate solutions. Even so, existing methods are still prohibitively expensive for large road networks. Two main reasons are (i) that they fail to utilize the special properties of road networks and (ii) that most of them process queries without indices; the few existing indices consume large amounts of memory and yet have limited effectiveness in reducing query costs. Motivated by this, we propose COLA , the first practical solution for approximate CSP processing on large road networks. COLA exploits the facts that a road network can be effectively partitioned, and that there exists a relatively small set of landmark vertices that commonly appear in CSP results. Accordingly, COLA indexes the vertices lying on partition boundaries, and applies an on-the-fly algorthm called α - Dijk for path computation within a partition, which effectively prunes paths based on landmarks. Extensive experiments demonstrate that on continent-sized road networks, COLA answers an approximate CSP query in sub-second time, whereas existing methods take hours. Interestingly, even without an index, the α-Dijk algorithm in COLA still outperforms previous solutions by more than an order of magnitude.

Personalized PageRank (PPR) computation is a fundamental operation in web search, social networks, and graph analysis. Given a graph G , a source s, and a target t, the PPR query Π( s, t ) returns the probability that a random walk on G starting from s terminates at t. Unlike global PageRank which can be effectively pre-computed and materialized, the PPR result depends on both the source and the target, rendering results materialization infeasible for large graphs. Existing indexing techniques have rather limited effectiveness; in fact, the current state-of-the-art solution, BiPPR, answers individual PPR queries without pre-computation or indexing, and yet it outperforms all previous index-based solutions. Motivated by this, we propose HubPPR, an effective indexing scheme for PPR computation with controllable tradeoffs for accuracy, query time, and memory consumption. The main idea is to pre-compute and index auxiliary information for selected hub nodes that are often involved in PPR processing. Going one step further, we extend HubPPR to answer top- k PPR queries, which returns the k nodes with the highest PPR values with respect to a source s , among a given set T of target nodes. Extensive experiments demonstrate that compared to the current best solution BiPPR, HubPPR achieves up to 10x and 220x speedup for PPR and top- k PPR processing, respectively, with moderate memory consumption. Notably, with a single commodity server, HubPPR answers a top- k PPR query in seconds on graphs with billions of edges, with high accuracy and strong result quality guarantees.

Differential privacy is a promising privacy-preserving paradigm for statistical query processing over sensitive data. It works by injecting random noise into each query result such that it is provably hard for the adversary to infer the presence or absence of any individual record from the published noisy results. The main objective in differentially private query processing is to maximize the accuracy of the query results while satisfying the privacy guarantees. Previous work, notably Li et al. [2010], has suggested that, with an appropriate strategy, processing a batch of correlated queries as a whole achieves considerably higher accuracy than answering them individually. However, to our knowledge there is currently no practical solution to find such a strategy for an arbitrary query batch; existing methods either return strategies of poor quality (often worse than naive methods) or require prohibitively expensive computations for even moderately large domains. Motivated by this, we propose a low-rank mechanism (LRM), the first practical differentially private technique for answering batch linear queries with high accuracy. LRM works for both exact (i.e., ϵ-) and approximate (i.e., (ϵ, δ)-) differential privacy definitions. We derive the utility guarantees of LRM and provide guidance on how to set the privacy parameters, given the user's utility expectation. Extensive experiments using real data demonstrate that our proposed method consistently outperforms state-of-the-art query processing solutions under differential privacy, by large margins.

We demonstrate OceanRT, a novel cloud-based infrastructure that performs online analytics in real time, over large-scale temporal data such as call logs from a telecommunication company. Apart from proprietary systems for which few details have been revealed, most existing big-data analytics systems are built on top of an offline, MapReduce-style infrastructure, which inherently limits their efficiency. In contrast, OceanRT employs a novel computing architecture consisting of interconnected Access Query Engines (AQEs), as well as a new storage scheme that ensures data locality and fast access for temporal data. Our preliminary evaluation shows that OceanRT can be up to 10x faster than Impala [10], 12x faster than Shark [5], and 200x faster than Hive [13]. The demo will show how OceanRT manages a real call log dataset (around 5TB per day) from a large mobile network operator in China. Besides presenting the processing of a few preset queries, we also allow the audience to issue ad hoc HiveQL [13] queries, watch how OceanRT answers them, and compare the speed of OceanRT with its competitors.

In real-time interactive data analytics, the user expects to receive the results of each query within a short time period such as seconds. This is especially challenging when the data is big (e.g., on the scale of petabytes), and the analytics system runs on top of cloud infrastructure (e.g., thousands of interconnected commodity servers). We have been building such a system, called OceanRT, for managing large spatio-temporal data such as call logs and mobile web browsing records collected by a telecommunication company. Although there already exist systems for querying big data in real time, OceanRT's performance stands out due to several novel designs and components that address key efficiency and scalability issues that were largely overlooked in existing systems. First, OceanRT makes extensive use of software RDMA one-sided operations, which reduce networking costs without requiring specialized hardware. Second, OceanRT exploits the parallel computing capabilities of each node in the cloud through a novel architecture consisting of Access-Query Engines (AQEs) connected with minimal overhead. Third, OceanRT contains a novel storage scheme that optimizes for queries with joins and multi-dimensional selections, which are common for large spatio-temporal data. Experiments using the TPC-DS benchmark show that OceanRT is usually more than an order of magnitude faster than the current state-of-the-art systems.

Differential privacy (DP) enables publishing statistical query results over sensitive data, with rigorous privacy guarantees, and very conservative assumptions about the adversary's background knowledge. This paper focuses on the interactive DP framework, which processes incoming queries on the fly, each of which consumes a portion of the user-specified privacy budget. Existing systems process each query independently, which often leads to considerable privacy budget waste. Motivated by this, we propose Pioneer, a query optimizer for an interactive, DP-compliant DBMS. For each new query, Pioneer creates an execution plan that combines past query results and new results from the underlying data. When a query has multiple semantically equivalent plans, Pioneer automatically selects one with minimal privacy budget consumption. Extensive experiments confirm that Pioneer achieves significant savings of the privacy budget, and can answer many more queries than existing systems for a fixed total budget, with comparable result accuracy.

Continuous clustering analysis over a data stream reports clustering results incrementally as updates arrive. Such analysis has a wide spectrum of applications, including traffic monitoring and topic discovery on microblogs. A common characteristic of streaming applications is that the amount of workload fluctuates, often in an unpredictable manner. On the other hand, most existing solutions for continuous clustering assume either a central server, or a distributed setting with a fixed number of dedicated servers. In other words, they are not ELASTIC, meaning that they cannot dynamically adapt to the amount of computational resources to the fluctuating workload. Consequently, they incur considerable waste of resources, as the servers are under-utilized when the amount of workload is low. This paper proposes C-Cube, the first elastic approach to continuous streaming clustering. Similar to popular cloud-based paradigms such as MapReduce, C-Cube routes each new record to a processing unit, e.g., a virtual machine, based on its hash value. Each processing unit performs the required computations, and sends its results to a lightweight aggregator. This design enables dynamic adding/removing processing units, as well as replacing faulty ones and re-running their tasks. In addition to elasticity, C-Cube is also effective (in that it provides quality guarantees on the clustering results), efficient (it minimizes the computational workload at all times), and generally applicable to a large class of clustering criteria. We implemented C-Cube in a real system based on Twitter Storm, and evaluated it using real and synthetic datasets. Extensive experimental results confirm our performance claims.

We propose Resa, a novel framework for robust, elastic and realtime stream processing in the cloud. In addition to traditional functionalities of streaming and cloud systems, Resa provides (i) a novel mechanism that handles dynamic additions and removals nodes in an operator, and (ii) a node re-assignment scheme that minimizes output latency using a queuing model. We have implemented Resa on top of Twitter Storm. Experiments using real data demonstrate the effectiveness and efficiency of Resa.

epsilon-differential privacy is rapidly emerging as the state-of-the-art scheme for protecting individuals' privacy in published analysis results over sensitive data. The main idea is to perform random perturbations on the analysis results, such that any individual's presence in the data has negligible impact on the randomized results. This paper focuses on analysis tasks that involve model fitting, i.e., finding the parameters of a statistical model that best fit the dataset. For such tasks, the quality of the differentially private results depends upon both the effectiveness of the model fitting algorithm, and the amount of perturbations required to satisfy the privacy guarantees. Most previous studies start from a state-of-the-art, non-private model fitting algorithm, and develop a differentially private version. Unfortunately, many model fitting algorithms require intensive perturbations to satisfy -differential privacy, leading to poor overall result quality.

We assume a data set that is vertically decomposed among several servers, and a client that wishes to compute the skyline by obtaining the minimum number of points. Existing solutions for this problem are restricted to the case where each server maintains exactly one dimension. This paper proposes a general solution for vertical decompositions of arbitrary dimensionality. We first investigate some interesting problem characteristics regarding the pruning power of points. Then, we introduce vertical partition skyline (VPS), an algorithmic framework that includes two steps. Phase 1 searches for an anchor point Pancthat dominates, and hence eliminates, a large number of records. Starting with Panc, Phase 2 constructs incrementally a pruning area using an interesting union-intersection property of dominance regions. Servers do not transmit points that fall within the pruning area in their local subspace. Our experiments confirm the effectiveness of the proposed methods under various settings.

Differential privacy (DP) is a promising scheme for releasing the results of statistical queries on sensitive data, with strong privacy guarantees against adversaries with arbitrary background knowledge. Existing studies on DP mostly focus on simple aggregations such as counts. This paper investigates the publication of DP-compliant histograms, which is an important analytical tool for showing the distribution of a random variable, e.g., hospital bill size for certain patients. Compared to simple aggregations whose results are purely numerical, a histogram query is inherently more complex, since it must also determine its structure, i.e., the ranges of the bins. As we demonstrate in the paper, a DP-compliant histogram with finer bins may actually lead to significantly lower accuracy than a coarser one, since the former requires stronger perturbations in order to satisfy DP. Moreover, the histogram structure itself may reveal sensitive information, which further complicates the problem. Motivated by this, we propose two novel algorithms, namely Noise First and Structure First, for computing DP-compliant histograms. Their main difference lies in the relative order of the noise injection and the histogram structure computation steps. Noise First has the additional benefit that it can improve the accuracy of an already published DP-complaint histogram computed using a naiive method. Going one step further, we extend both solutions to answer arbitrary range queries. Extensive experiments, using several real data sets, confirm that the proposed methods output highly accurate query answers, and consistently outperform existing competitors.

e-differential privacy (e-DP) is a strong and rigorous scheme for protecting individuals' privacy while releasing useful statistical information. The main idea is to inject random noise into the results of statistical queries, such that the existence of any single record has negligible impact on the distributions of query results. The accuracy of such randomized results depends heavily upon the query processing technique, which has been an active research topic in recent years. So far, most existing methods focus on 1-dimensional queries. The only work that handles multi-dimensional query processing under e-DP is [1], which indexes the sensitive data using variants of the quad-tree and the k-d-tree. As we point out in this paper, these structures are inherently suboptimal for answering queries under e-DP. Consequently, the solutions in [1] suffer from several serious drawbacks, including limited and unstable query accuracy, as well as bias towards certain types of queries. Motivated by this, we propose the DP-tree, a novel index structure for multi-dimensional query processing under e-DP that eliminates the problems encountered by the methods in [1]. Further, we show that the effectiveness of the DP-tree can be improved using statistical information about the query workload. Extensive experiments using real and synthetic datasets confirm that the DP-tree achieves significantly higher query accuracy than existing methods. Interestingly, an adaptation of the DP-tree also outperforms previous 1D solutions in their restricted scope, by large margins.

Data privacy has been an important research topic in the security, theory and database communities in the last few decades. However, many existing studies have restrictive assumptions regarding the adversary's prior knowledge, meaning that they preserve individuals' privacy only when the adversary has rather limited background information about the sensitive data, or only uses certain kinds of attacks. Recently, differential privacy has emerged as a new paradigm for privacy protection with very conservative assumptions about the adversary's prior knowledge. Since its proposal, differential privacy had been gaining attention in many fields of computer science, and is considered among the most promising paradigms for privacy-preserving data publication and analysis. In this tutorial, we will motivate its introduction as a replacement for other paradigms, present the basics of the differential privacy model from a database perspective, describe the state of the art in differential privacy research, explain the limitations and shortcomings of differential privacy, and discuss open problems for future research.

Differential privacy is a promising privacy-preserving paradigm for statistical query processing over sensitive data. It works by injecting random noise into each query result, such that it is provably hard for the adversary to infer the presence or absence of any individual record from the published noisy results. The main objective in differentially private query processing is to maximize the accuracy of the query results, while satisfying the privacy guarantees. Previous work, notably the matrix mechanism [16], has suggested that processing a batch of correlated queries as a whole can potentially achieve considerable accuracy gains, compared to answering them individually. However, as we point out in this paper, the matrix mechanism is mainly of theoretical interest; in particular, several inherent problems in its design limit its accuracy in practice, which almost never exceeds that of naïve methods. In fact, we are not aware of any existing solution that can effectively optimize a query batch under differential privacy. Motivated by this, we propose the Low-Rank Mechanism (LRM), the first practical differentially private technique for answering batch queries with high accuracy, based on a low rank approximation of the workload matrix. We prove that the accuracy provided by LRM is close to the theoretical lower bound for any mechanism to answer a batch of queries under differential privacy. Extensive experiments using real data demonstrate that LRM consistently outperforms state-of-the-art query processing solutions under differential privacy, by large margins.

ε-differential privacy is the state-of-the-art model for releasing sensitive information while protecting privacy. Numerous methods have been proposed to enforce ε-differential privacy in various analytical tasks, e.g., regression analysis . Existing solutions for regression analysis, however, are either limited to non-standard types of regression or unable to produce accurate regression results. Motivated by this, we propose the Functional Mechanism , a differentially private method designed for a large class of optimization-based analyses. The main idea is to enforce ε-differential privacy by perturbing the objective function of the optimization problem, rather than its results. As case studies, we apply the functional mechanism to address two most widely used regression models, namely, linear regression and logistic regression . Both theoretical analysis and thorough experimental evaluations show that the functional mechanism is highly effective and efficient, and it significantly outperforms existing solutions.

In a wireless sensor network (WSN), each sensor monitors environmental parameters, and reports its readings to a base station, possibly through other nodes. A sensor works in cycles, in each of which it stays active for a fixed duration, and then sleeps until the next cycle. The frequency of such cycles determines the portion of time that a sensor is active, and is the dominant factor on its battery life. The majority of existing work assumes globally synchronized WSN where all sensors have the same frequency. This leads to waste of battery power for applications that entail different accuracy of measurements, or environments where sensor readings have large variability. To overcome this problem, we propose LS, a query processing framework for locally synchronized WSN. We consider that each sensor nihas a distinct sampling frequency fi, which is determined by the application or environment requirements. The complication of LS is that nihas to wake up with a network frequency Fi≥fi, in order to forward messages of other sensors. Our goal is to minimize the sum of Fiwithout delaying packet transmissions. Specifically, given a routing tree, we first present a dynamic programming algorithm that computes the optimal network frequency of each sensor; then, we develop a heuristic for finding the best tree topology, if this is not fixed in advance.

Multistep processing is commonly used for nearest neighbor (NN) and similarity search in applications involving high-dimensional data and/or costly distance computations. Today, many such applications require a proof of result correctness. In this setting, clients issue NN queries to a server that maintains a database signed by a trusted authority. The server returns the NN set along with supplementary information that permits result verification using the data set signature. An adaptation of the multistep NN algorithm incurs prohibitive network overhead due to the transmission of false hits, i.e., records that are not in the NN set, but are nevertheless necessary for its verification. In order to alleviate this problem, we present a novel technique that reduces the size of each false hit. Moreover, we generalize our solution for a distributed setting, where the database is horizontally partitioned over several servers. Finally, we demonstrate the effectiveness of the proposed solutions with real data sets of various dimensionalities.

Due to its considerable ease of use, relational keyword search (R-KWS) has become increasingly popular. Its simplicity, however, comes at the cost of intensive query processing. Specifically, R-KWS explores a vast search space, comprised of all possible combinations of keyword occurrences in any attribute of every table. Existing systems follow two general methodologies for query processing: (i) graph based, which traverses a materialized data graph, and (ii) operator based, which executes relational operator trees on an underlying DBMS. In both cases, computations are largely wasted on graph traversals or operator tree executions that fail to return results. Motivated by this observation, we introduce a comprehensive framework for reachability indexing that eliminates such fruitless operations. We describe a range of indexes that capture various types of join reachability. Extensive experiments demonstrate that the proposed techniques significantly improve performance, often by several orders of magnitude.

Database outsourcing requires that a query server constructs a proof of result correctness, which can be verified by the client using the data owner's signature. Previous authentication techniques deal with range queries on a single relation using an authenticated data structure (ADS). On the other hand, authenticated join processing is inherently more complex than ranges since only the base relations (but not their combination) are signed by the owner. In this paper, we present three novel join algorithms depending on the ADS availability: (i) Authenticated Indexed Sort Merge Join (AISM), which utilizes a single ADS on the join attribute, (ii) Authenticated Index Merge Join (AIM) that requires an ADS (on the join attribute) for both relations, and (iii) Authenticated Sort Merge Join (ASM), which does not rely on any ADS. We experimentally demonstrate that the proposed methods outperform two benchmark algorithms, often by several orders of magnitude, on all performance metrics, and effectively shift the workload to the outsourcing service. Finally, we extend our techniques to complex queries that combine multi-way joins with selections and projections.

The skyline of a d-dimensional dataset consists of all points not dominated by others. The incorporation of the skyline operator into practical database systems necessitates an efficient and effective cardinality estimation module. However, existing theoretical work on this problem is limited to the case where all d dimensions are independent of each other, which rarely holds for real datasets. The state of the art Log Sampling (LS) technique simply applies theoretical results for independent dimensions to non-independent data anyway, sometimes leading to large estimation errors. To solve this problem, we propose a novel Kernel-Based (KB) approach that approximates the skyline cardinality with nonparametric methods. Extensive experiments with various real datasets demonstrate that KB achieves high accuracy, even in cases where LS fails. At the same time, despite its numerical nature, the efficiency of KB is comparable to that of LS. Furthermore, we extend both LS and KB to the k-dominant skyline, which is commonly used instead of the conventional skyline for high-dimensional data.

We are experiencing an unprecedented increase of content contributed by users in forums such as blogs, social networking sites and microblogging services. Such abundance of content complements content on web sites and traditional media forums such as news papers, news and financial streams, and so on. Given such plethora of information there is a pressing need to cross reference information across textual services. For example, commonly we read a news item and we wonder if there are any blogs reporting related content or vice versa.

Relational Keyword Search (R-KWS) provides an intuitive way to query relational data without requiring SQL, or knowledge of the underlying schema. In this article we describe a comprehensive framework for R-KWS covering snapshot queries on conventional tables and continuous queries on relational streams. Our contributions are summarized as follows: (i) We provide formal semantics, addressing the temporal validity and order of results, spanning uniformly over tables and streams; (ii) we investigate two general methodologies for query processing, graph based and operator based , that resolve several problems of previous approaches; and (iii) we develop a range of algorithms and optimizations covering both methodologies. We demonstrate the effectiveness of R-KWS, as well as the significant performance benefits of the proposed techniques, through extensive experiments with static and streaming datasets.

In a data stream management system, a continuous query is processed by an execution plan consisting of multiple operators connected via the "consumer-producer" relationship, i.e., the output of an operator (the "producer") feeds to another downstream operator (the "consumer") as input. Existing techniques execute each operator separately and push all results to its consumers, without considering whether the consumers need them. Consequently, considerable CPU and memory resources are wasted on producing and storing useless intermediate results. Motivated by this, we propose just-in-time (JIT) processing, a novel methodology that enables a consumer to return feedback expressing its current demand to the producer. The latter selectively generates results based on this information. We show, through extensive experiments, that JIT achieves significant savings in terms of both CPU time and memory consumption.

The embedding of positioning capabilities in mobile devices and the emergence of location-based applications have created novel opportunities for utilizing several types of multidimensional data through spatial outsourcing. In this setting, a data owner (DO) delegates its data management tasks to a location-based service (LBS) that processes queries originating from several clients/subscribers. Because the LBS is not the real owner of the data, it must prove (to each client) the correctness of query output using an authenticated structure signed by the DO. Currently there is very narrow selection of multidimensional authenticated structures, among which the VR-tree is the best choice. Our first contribution is the MR-tree, a novel index suitable for spatial outsourcing. We show, analytically and experimentally, that the MR-tree outperforms the VR-tree, usually by orders of magnitude, on all performance metrics, including construction cost, index size, query and verification overhead. Motivated by the fact that successive queries by the same mobile client exhibit locality, we also propose a synchronized caching technique that utilizes the results of previous queries to reduce the size of the additional information sent to the client for verification purposes.

Given a data set P, a k-means query returns k points in space (called centers), such that the average squared distance between each point in P and its nearest center is minimized. Since this problem is NP-hard, several approximate algorithms have been proposed and used in practice. In this paper, we study continuous k-means computation at a server that monitors a set of moving objects. Reevaluating k-means every time there is an object update imposes a heavy burden on the server (for computing the centers from scratch) and the clients (for continuously sending location updates). We overcome these problems with a novel approach that significantly reduces the computation and communication costs, while guaranteeing that the quality of the solution, with respect to the reevaluation approach, is bounded by a user-defined tolerance. The proposed method assigns each moving object a threshold (i.e., range) such that the object sends a location update only when it crosses the range boundary. First, we develop an efficient technique for maintaining the k-means. Then, we present mathematical formulas and algorithms for deriving the individual thresholds. Finally, we justify our performance claims with extensive experiments.

Increasing monitoring of transactions, environmental parameters, homeland security, RFID chips and interactions of online users rapidly establishes new data sources and application scenarios. In this paper, we propose keyword search on relational data streams (S-KWS) as an effective way for querying in such intricate and dynamic environments. Compared to conventional query methods, S-KWS has several benefits. First, it allows search for combinations of interesting terms without a-priori knowledge of the data streams in which they appear. Second, it hides the schema from the user and allows it to change, without the need for query re-writing. Finally, keyword queries are easy to express. Our contributions are summarized as follows. (i) We provide formal semantics for S-KWS, addressing the temporal validity and order of results. (ii) We propose an efficient algorithm for generating operator trees, applicable to arbitrary schemas. (iii) We integrate these trees into an operator mesh that shares common expressions. (iv) We develop techniques that utilize the operator mesh for efficient query processing. The techniques adapt dynamically to changes in the schema and input characteristics. Finally, (v) we present methods for purging expired tuples, minimizing either CPU, or memory requirements.

In data stream environments, the initial plan of a long-running query may gradually become inefficient due to changes of the data characteristics. In this case, the query optimizer generates a more efficient plan based on the current statistics. The online transition from the old to the new plan is called dynamic plan migration. In addition to correctness, an effective technique for dynamic plan migration should achieve the following objectives: 1) minimize the memory and CPU overhead of the migration, 2) reduce the duration of the transition, and 3) maintain a steady output rate. The only known solutions for this problem are the moving states (MS) and parallel track (PT) strategies, which have some serious shortcomings related to the above objectives. Motivated by these shortcomings, we first propose HybMig, which combines the merits of MS and PT and outperforms both in every aspect. As a second step, we extend PT, MS, and HybMig to the general problem of migration, where both the new and the old plans are treated as black boxes

Semantic Portal is the next generation of web portals that are powered by Semantic Web technologies for improved information sharing and exchange for a community of users. Current methods of searching in Semantic Portals are limited to keyword-based search using information retrieval (IR) techniques, ontology-based formal query and reasoning, or a simple combination of the two. In this paper, we propose an enhanced model that tightly integrates IR with formal query and reasoning to fully utilize both textual and semantic information for searching in Semantic Portals. The model extends the search capabilities of existing methods and can answer more complex search requests. The ideas in a fuzzy description logic (DL) IR model and a formal DL query method are employed and combined in our model. Based on the model, a semantic search service is implemented and evaluated. The evaluation shows very large improvements over existing methods.