With the development of large language models (LLMs) in the field of programming, intelligent programming coaching systems have gained widespread attention. However, most research focuses on repairing the buggy code of programming learners without providing the underlying causes of the bugs. To address this gap, we introduce a novel task, namely LPR (Learner-Tailored Program Repair). We then propose a novel and effective framework, LSGen (Learner-Tailored Solution Generator), to enhance program repair while offering the bug descriptions for the buggy code. In the first stage, we utilize a repair solution retrieval framework to construct a solution retrieval database and then employ an edit-driven code retrieval approach to retrieve valuable solutions, guiding LLMs in identifying and fixing the bugs in buggy code. In the second stage, we propose a solution-guided program repair method, which fixes the code and provides explanations under the guidance of retrieval solutions. Moreover, we propose an Iterative Retrieval Enhancement method that utilizes evaluation results of the generated code to iteratively optimize the retrieval direction and explore more suitable repair strategies, improving performance in practical programming coaching scenarios. The experimental results show that our approach outperforms a set of baselines by a large margin, validating the effectiveness of our framework for the newly proposed LPR task.

Language model inversion (LMI), i.e., recovering hidden prompts from outputs, emerges as a concrete threat to user privacy and system security. We recast LMI as reusing the LLM's own latent space and propose the Invariant Latent Space Hypothesis (ILSH): (1) diverse outputs from the same source prompt should preserve consistent semantics (source invariance), and (2) inputoutput cyclic mappings should be self-consistent within a shared latent space (cyclic invariance). Accordingly, we present Inv2A, which treats the LLM as an invariant decoder and learns only a lightweight inverse encoder that maps outputs to a denoised pseudo-representation. When multiple outputs are available, they are sparsely concatenated at the representation layer to increase information density. Training proceeds in two stages: contrastive alignment (source invariance) and supervised reinforcement (cyclic invariance). An optional training-free neighborhood search can refine local performance. Across 9 datasets covering user and system prompt scenarios, Inv2A outperforms baselines by an average of 4.77% BLEU score while reducing dependence on large inverse corpora. Our analysis further shows that prevalent defenses provide limited protection, underscoring the need for stronger strategies.

Natural language to SQL (NL2SQL) provides an intuitive interface for querying structured data, yet real user questions are often noisy, ambiguous, and weakly grounded to database semantics.As a result, token-level schema linking and single-pass SQL decoding can be brittle: small misunderstandings in language or schema grounding may propagate into incorrect generation.We present QBridge, an agentic, feedback-driven NL2SQL framework based on a Refined Gold Query Paradigm, which bridges natural language and SQL via Gold Query-a structured, SQL-aligned intermediate representation.A core insight of QBridge is Distilled Back-Translation (DBT) for SL-independent rewriting.DBT converts SQL-grounded supervision into execution-verified Gold-Querystyle rewrites from a teacher model, and distills a lightweight, plug-and-play rewriter that generates schema-aware rewrites without requiring explicit schema linking at inference.QBridge then (i) verifies and conservatively refines the rewrite into a high-fidelity Refined Gold Query, and (ii) refines the generated SQL with dual feedback from execution validity and semantic consistency, enabling interpretable self-correction while remaining compatible with diverse SQL backbones.Extensive experiments on Spider, BIRD, and three robustness variants demonstrate that QBridge consistently improves zero-shot NL2SQL, outperforming strong prompting and agentic baselines while showing strong robustness and generalization.Code and data are available at https: //github.com/WannaBSteve/QBridge.

Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness; and (2) current methods lack an explicit self-improving mechanism to align with clinical preference.We introduce clinically aligned Evidence-aware Self-Correcting Reinforcement Learning (ESC-RL), comprising two key components.First, a Group-wise Evidence-aware Alignment Reward (GEAR) delivers group-wise, evidence-aware feedback.GEAR reinforces consistent grounding for true positives, recovers missed findings for false negatives, and suppresses unsupported content for false positives.Second, a Self-correcting Preference Learning (SPL) strategy automatically constructs a reliable, disease-aware preference dataset from multiple noisy observations and leverages an LLM to synthesize refined reports without human supervision.ESC-RL promotes clinically faithful, disease-aligned reward and supports continual self-improvement during training.Extensive experiments on two public chest X-ray datasets demonstrate consistent gains and state-of-the-art performance.

Detecting early brain anomalies is crucial for patient prognosis and recovery, but obtaining expert-annotated data is challenging, especially for clinically silent early brain anomalies. Unsupervised brain anomaly detection, which identifies anomalous regions by modeling normal brain patterns, has gained interest for its label efficiency. However, the inherent variability in normal brains and subtle anomalies that closely resemble normal tissue pose challenges for traditional autoencoders in distinguishing anomalies. Denoising AutoEncoder (DAE) methods have been explored to enhance the model's ability, while their success hinges on effective noise generation strategies. In this paper, we introduce a novel, structure-preserving noise generation scheme based on cross-modal CutMix, aiming to enhance the diversity of noise patterns while preserving the anatomical structure of the brain. To enhance the robustness of DAE learning, we propose an ensemble approach featuring dual experts, each incorporating distinct scale of noise. This dual-expert scheme effectively amplifies reconstruction errors in anomalous regions and suppresses false alarms in healthy areas. Additionally, we propose an anatomically-aware bidirectional consistency loss to ensure high-fidelity reconstruction at the regional level, using superpixels for anatomy perception and bidirectional distillation for reliable knowledge transfer. Extensive experiments across two different settings demonstrate the effectiveness and generalization ability of our proposed method.

As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pretrained models and select the most suitable one for the new target task. Existing model selection techniques are often constrained in their scope and tend to overlook the nuanced relationships between models and tasks. In this paper, we present a pragmatic framework Fennec, delving into a diverse, large-scale model repository while meticulously considering the intricate connections between tasks and models. The key insight is to map all models and historical tasks into a transfer-related subspace, where the distance between model vectors and task vectors represents the magnitude of transferability. A large vision model, as a proxy, infers a new task's representation in the transfer space, thereby circumventing the computational burden of extensive forward passes and reliance on labels. We also investigate the impact of the inherent inductive bias of models on transfer results and propose a novel method called archi2vec to encode the intricate structures of models. The transfer score is computed through straightforward vector arithmetic with a constant time complexity of O(k) per model inference (where k is the dimension of the latent space). Finally, we make a substantial contribution to the field by releasing a comprehensive benchmark that includes 105 different models. We validate the effectiveness of Fennec through rigorous testing on two benchmarks. Our framework achieves the best evaluation accuracy on both benchmarks. On the PARC benchmark, the feature extraction time is 6.5× faster than the baseline at the same level, and the inference time is 5.7× faster than the fastest baseline. On the larger benchmark, the performance gains are even more pronounced, with feature extraction time being 52.3× faster and inference time 1.8× faster than the fastest baseline, demonstrating remarkable performance efficiency. The code has been made publicly available at: https://github.com/Fay-why/Fennec.

Recovering trajectories of all moving vehicles from urban-scale cameras is an attractive but challenging topic for massive video data management. Existing solutions frame it as an iterative image clustering problem. The snapshots from the same vehicle are grouped within a cluster, which is further refined according to the spatial-temporal attributes. However, these approaches exhibit expensive iterative clustering overhead and ineffective exploitation of spatial-temporal clues. Moreover, they are designed for batch processing, facing performance degradation when handling newly collected surveillance data. In this paper, we propose a novel joint representation clustering framework, which recovers trajectories from vehicle snapshots in an efficient and accurate fashion and is inherently suited for processing video streaming data. Technically, spatial-temporal features are explicitly extracted to construct the joint representation, eliminating the need for iterative refinement, which significantly reduces computational overhead. Furthermore, we present a simple yet effective clustering scheme with one-pass scan on joint representations to generate large-scale clusters. To mitigate the dependency on external data, a joint training method based on self-supervised learning is introduced. We conduct extensive experiments in both batch and streaming modes. The results show that in the batch mode, TRACER achieves a speedup of at least 2.3× and yields recovery F1-score improvements of 1.7% − 19.6%. In the streaming experimental setup, it achieves 1.1%−27.6% improvement in F1-score, and reduces the average snapshot processing time by up to 84.8%.

Dynamic Graph Neural Networks (GNNs) combine temporal information with GNNs to capture structural, temporal, and contextual relationships in dynamic graphs simultaneously, leading to enhanced performance in various applications. As the demand for dynamic GNNs continues to grow, numerous models and frameworks have emerged to cater to different application needs. There is a pressing need for a comprehensive survey that evaluates the performance, strengths, and limitations of various approaches in this domain. This paper aims to fill this gap by offering a thorough comparative analysis and experimental evaluation of dynamic GNNs. It covers 91 dynamic GNN models with a novel taxonomy, 17 dynamic GNN training frameworks, and commonly used benchmarks. We also evaluate the experimental results of ten representative dynamic GNN models and five frameworks on six datasets. Evaluation metrics focus on convergence accuracy, training efficiency, and GPU memory usage, enabling a thorough performance comparison across various models and frameworks. From the analysis and evaluation results, we identify key challenges and offer principles for future research to enhance the design of models and frameworks in the dynamic GNNs field. Our code is made publicly available athttps://github.com/fengwudi/DGNN_model_and_data

A precise workload forecaster is the key to effective resource management, system scalability, and overall operational efficiency in cloud environments. However, real-world cloud systems frequently operate in dynamic and unpredictable settings, causing workloads that exhibit significant diversity and fluctuations. To address these problems, we introduce OMCR, a novel online multivariate forecaster for cloud resource management, that overcomes the limitations of existing static forecasting methods through online learning. OMCR integrates long-term memory with a rapid response mechanism to short-term changes in cloud systems, while also considering the impact of multivariate relationships on workload prediction. OMCR minimizes its reliance on historical data, thereby reducing training difficulty and maintaining lower prediction loss in the long run. OMCR also offers an adaptive approach to forecasting peak workloads in a certain time span, which helps cloud resource management. Experimental results demonstrate the superior performance of our proposed framework compared to state-of-the-art methods in MAE and MSE metrics when forecasting cloud workloads.

Generation-based testing techniques have proven effective in detecting logic bugs in DBMS, often stemming from the improper implementation of query optimizers. However, existing generation-based debugging tools predominantly rely on random testing, which tends to overlook critical error-prone areas such as multi-table joining and grouped aggregation. In this article, we propose TQS, a novel testing framework targeted at detecting logic bugs arising from SPJG (Select-Project-Join-Group By) query optimizations. Given a target DBMS, TQS achieves the goal with two key components: Data-guided Schema and Query Generation (DSG) and Knowledge-guided Query Space Exploration (KQE). DSG addresses the key challenge of multi-table query debugging: how to generate ground-truth (query, result) pairs for verification. DSG utilizes data derived from dimensionally aggregated data cubes, which store data of grouped metric columns. It maps data from data cubes to a wide table, applies database normalization techniques to the wide table to generate a testing schema and maintains a bitmap index for result tracking. To improve debug efficiency, DSG also artificially inserts some noises into the generated data. To avoid repetitive query space search, KQE guides the generation of error-prone cubes, and forms the problem as isomorphic graph set discovery and combines the graph embedding and weighted random walk for query generation. We evaluated TQS on four popular DBMSs: MySQL, MariaDB, TiDB, and PolarDB. Experimental results show that TQS is effective in finding logic bugs of SPJG query optimization in database management systems. It successfully detected 226 bugs within 24 hours, including 63 bugs in MySQL, 52 in MariaDB, 68 in TiDB, and 43 in PolarDB, respectively.

Automated Program Repair (APR) is a task to automatically generate patches for the buggy code. However, most research focuses on generating correct patches while ignoring the consistency between the fixed code and the original buggy code. How to conduct adaptive bug fixing and generate patches with minimal modifications have seldom been investigated. To bridge this gap, we first introduce a novel task, namely AdaPR (Adaptive Program Repair). We then propose a two-stage approach AdaPatcher (Adaptive Patch Generator) to enhance program repair while maintaining the consistency. In the first stage, we utilize a Bug Locator with self-debug learning to accurately pinpoint bug locations. In the second stage, we train a Program Modifier to ensure consistency between the post-modified fixed code and the pre-modified buggy code. The Program Modifier is enhanced with a location-aware repair learning strategy to generate patches based on identified buggy lines, a hybrid training strategy for selective reference and an adaptive preference learning to prioritize fewer changes. The experimental results show that our approach outperforms a set of baselines by a large margin, validating the effectiveness of our two-stage framework for the newly proposed AdaPR task.

Malignant brain tumors have become an aggressive and dangerous disease that leads to death worldwide. Multi-modal MRI data is crucial for accurate brain tumor segmentation, but missing modalities common in clinical practice can severely degrade the segmentation performance. While incomplete multi-modal learning methods attempt to address this, learning robust and discriminative features from arbitrary missing modalities remains challenging. To address this challenge, we propose a novel Semantic-guided Masked Mutual Learning (SMML) approach to distill robust and discriminative knowledge across diverse missing modality scenarios. Specifically, we propose a novel dual-branch masked mutual learning scheme guided by Hierarchical Consistency Constraints (HCC) to ensure multi-level consistency, thereby enhancing mutual learning in incomplete multi-modal scenarios. The HCC framework comprises a pixel-level constraint that selects and exchanges reliable knowledge to guide the mutual learning process. Additionally, it includes a feature-level constraint that uncovers robust inter-sample and inter-class relational knowledge within the latent feature space. To further enhance multi-modal learning from missing modality data, we integrate a refinement network into each student branch. This network leverages semantic priors from the Segment Anything Model (SAM) to provide supplementary information, effectively complementing the masked mutual learning strategy in capturing auxiliary discriminative knowledge. Extensive experiments on three challenging brain tumor segmentation datasets demonstrate that our method significantly improves performance over state-of-the-art methods in diverse missing modality settings.

Integrating split learning with large language model fine-tuning (LLM-FT) enables secure collaboration between a trusted local client and a well-equipped remote server, but it is vulnerable to data reconstruction attacks (DRAs) that exploit transmitted activations and gradients.Current defense methods, like adding noise to activations or gradients, often sacrifice task-specific model performance under strict privacy constraints.This paper introduces Du-alGuard, a bidirectional defense mechanism against DRAs for split-based LLM-FT.Du-alGuard proposes a local warm-up parameter space transformation to alter client-side model parameters before training, using multi-task learning to strike a balance between privacy protection and model performance.Additionally, a global fine-tuning parameter space retention strategy prevents the model from reverting to vulnerable states during formal fine-tuning.Experiments show that DualGuard outperforms current defense methods against various DRAs, while maintaining task performance.Our code will be made publicly available.

Tabular data, which accounts for over 80% of enterprise data assets, is vital in various fields. With growing concerns about privacy protection and data-sharing restrictions, generating high-quality synthetic tabular data has become essential. Recent advancements show that large language models (LLMs) can effectively generate realistic tabular data by leveraging semantic information and overcoming the challenges of high-dimensional data that arise from one-hot encoding. However, current methods do not fully utilize the rich information available in tables. To address this, we introduce AI Generative Table based on prompt enhancement, a novel approach that utilizes metadata information, such as table descriptions and schemas, as prompts to generate ultra-high-quality synthetic data. To overcome the token limit constraints of LLMs, we propose long-token partitioning algorithms that enable AIGT to model tables of any scale. AIGT achieves state-of-the-art performance on 14 out of 20 public datasets and two real industry datasets within the Alipay risk control system.

Automated radiology report generation is essential for improving diagnostic efficiency and reducing the workload of medical professionals. However, existing methods face significant challenges, such as disease class imbalance and insufficient cross-modal fusion. To address these issues, we propose the learnable Retrieval Enhanced Visual-Text Alignment and Fusion (REVTAF) framework, which effectively tackles both class imbalance and visual-text fusion in report generation. REVTAF incorporates two core components: (1) a Learnable Retrieval Enhancer (LRE) that utilizes semantic hierarchies from hyperbolic space and intra-batch context through a ranking-based metric. LRE adaptively retrieves the most relevant reference reports, enhancing image representations, particularly for underrepresented (tail) class inputs; and (2) a fine-grained visual-text alignment and fusion strategy that ensures consistency across multi-source cross-attention maps for precise alignment. This component further employs an optimal transport-based cross-attention mechanism to dynamically integrate task-relevant textual knowledge for improved report generation. By combining adaptive retrieval with multi-source alignment and fusion, REVTAF achieves fine-grained visual-text integration under weak image-report level supervision while effectively mitigating data imbalance issues. The experiments demonstrate that REVTAF outperforms state-of-the-art methods, achieving an average improvement of 7.4% on the MIMIC-CXR dataset and 2.9% on the IU X-Ray dataset. Comparisons with mainstream multimodal LLMs (e.g., GPT-series models), further highlight its superiority in radiology report generation https://github.com/banbooliang/REVTAF-RRG.

The rise of Large Language Models (LLMs) has revolutionized numerous domains, yet these models still exhibit weakness in understanding structured tabular data. Although the growing context window promises to accommodate a larger volume of table contents, it does not inherently improve the model's ability to understand the underlying structure and semantics of tabular data. To bridge the semantic gap between **T**ext and **T**able, we propose **T**n**T**, a table-language model that features multimodal table representations to empower LLMs to effectively and efficiently abstract structure-enriched semantics from tabular data. **T**n**T** also introduces a scalable and efficient training pipeline, featuring novel self-supervised tasks, to integrate abstract tabular knowledge into the language modality. Extensive experimental results on NL2SQL demonstrate a much better table understanding of **T**n**T**, which achieves up to **14.4** higher execution accuracy compared with traditional text-based table representations.

Program performance optimization is essential for achieving high execution efficiency, yet it remains a challenging task that requires expertise in both software and hardware. Large Language Models (LLMs), trained on high-quality code from platforms like GitHub and other open-source sources, have shown promise in generating optimized code for simple snippets. However, current LLM-based solutions often fall short when tackling project-level programs due to the complexity of call graphs and the intricate interactions among functions. In this paper, we emulate the process a human expert might follow when optimizing project-level programs and introduce a three-phase framework POLO (PrOject-Level Optimizer) to address this limitation. First, we profile the program to identify performance bottlenecks using an iterative weighting algorithm. Next, we conduct structural analysis by scanning the project and generating a graph that represents the program's structure. Finally, two LLM agents collaborate in iterative cycles to rewrite and optimize the code at these hotspots, gradually improving performance. We conduct experiments on open-source and proprietary projects. The results demonstrate that POLO accurately identifies performance bottlenecks and successfully applies optimizations. Under the O3 compilation flag, the optimized programs achieved speedups ranging from 1.34x to 21.5x.

Understanding and predicting the effects of cellular perturbations using single-cell sequencing technology remains a critical and challenging problem in biotechnology. In this work, we introduce CycSeq, a deep learning framework that leverages cyclic data generation and recent advances in neural architectures to predict single-cell responses under specified perturbations across multiple cell lines, while also generating the corresponding single-cell expression profiles. Specifically, CycSeq addresses the challenge of learning heterogeneous perturbation responses from unpaired single-cell gene expression data by generating pseudo-pairs through cyclic data generation. Experimental results demonstrate that CycSeq outperforms existing methods in perturbation prediction tasks, as evaluated using computational metrics such as R-squared and MAE. Furthermore, CycSeq employs a unified architecture that integrates information from multiple cell lines, enabling robust predictions even for long-tail cell lines with limited training data. The source code is publicly available at https://github.com/yczju/cycseq.

Dynamic graph learning is crucial for accurately modeling complex systems by integrating topological structure and temporal information within graphs. While memory-based methods are commonly used and excel at capturing short-range temporal correlations, they struggle with modeling long-range dependencies, harmonizing long-range and short-range correlations, and integrating structural information effectively. To address these challenges, we present SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater. SALoM features a memory module that addresses gradient vanishing and information forgetting, enabling the capture of long-term dependencies across various time scales. Additionally, SALoM utilizes a long-short memory updater (LSMU) to dynamically balance long-range and short-range temporal correlations, preventing over-generalization. By integrating co-occurrence encoding and LSMU through information bottleneck-based fusion, SALoM effectively captures both the structural and temporal information within graphs. Experimental results across various graph datasets demonstrate SALoM's superior performance, achieving state-of-the-art results in dynamic graph link prediction. Our code is openly accessible at https://github.com/wave5418/SALoM.

Abstract Combinatorial optimization problems over graphs, such as the traveling salesman problem, longest path problem, and maximum independent set problem, are well-known for being computationally costly, some even NP-hard problems. In this paper, we propose a general quantum algorithm framework searching for approximate solutions to combinatorial optimization problems with linear objective functions. Our framework provides APIs (application programming interfaces) that enable developers to encode weighted graph structures onto quantum circuits and utilize variational algorithms to generate approximate solutions. One key advantage of our framework is that it allows developers to design new graph algorithms for the graph problem represented as linear combinations of edge weights without requiring expertise in quantum programming. Besides, it only uses a logarithmic level of quantum bit scale, making our framework work on quantum computers with limited physical resources. Our experimental results demonstrate that our framework can provide good approximations for the traveling salesman problem compared to current quantum algorithm.

The Internet of Everything (IoE) has recently become a hot topic. With the development of Internet of Things (IoT) technology, people can connect to networks in increasingly diverse ways. The surge in users, devices, and requests poses significant challenges to network capacity and backhaul links. Content caching technology has long been considered a promising approach to improving network performance. However, existing methods still have room for improvement in terms of content transmission efficiency and user access latency. To address these issues, this paper proposes an Influence-Driven Content Caching (IDCC) method. Specifically, based on a caching strategy of “caching content that is likely to have the greatest future influence on the most influential edge devices", this paper designs a comprehensive framework encompassing content selection, updating, and placement to optimize content caching efficiency, enhance network spectral efficiency, and improve user’s quality of experience (QoE). First, a content selection strategy based on the popularity dynamics prediction method is developed by utilizing graph neural networks and contrastive learning to model heterogeneous data. Second, a content update mechanism for cached content and key caching information is designed based on the popularity of content and Near-Field Communications (NFC) between users. Furthermore, interconnected network devices are represented as a graph, and the communication influence of key network nodes is predicted using autoencoders and graph neural networks to identify the optimal caching nodes for maximizing benefits. Finally, extensive experiments show that the proposed IDCC method offers significant advantages in reducing network latency and improving network utilization.

Online map matching is a fundamental problem in location-based services, aiming to incrementally match trajectory data step-by-step onto a road network. However, existing methods fail to meet the needs for efficiency, robustness, and accuracy required by large-scale online applications, making this task still challenging. This paper introduces a novel framework that achieves high accuracy and efficient matching while ensuring robustness in handling diverse scenarios. To improve efficiency, we begin by modeling the online map matching problem as an Online Markov Decision Process (OMDP) based on its inherent characteristics. This approach helps efficiently merge historical and real-time data, reducing unnecessary calculations. Next, to enhance robustness, we design a reinforcement learning method, enabling robust handling of real-time data from dynamically changing environments. In particular, we propose a novel model learning process and a comprehensive reward function, allowing the model to make reasonable current matches from a future-oriented perspective, and to continuously update and optimize during the decision-making process based on feedback. Lastly, to address the heterogeneity between trajectories and roads, we design distinct graph structures, facilitating efficient representation learning through graph and recurrent neural networks. To further align trajectory and road data, we introduce contrastive learning to decrease their distance in the latent space, thereby promoting effective integration of the two. Extensive evaluations on three real-world datasets confirm that our method significantly outperforms existing state-of-the-art solutions in terms of accuracy, efficiency and robustness.

Integrating machine learning (ML) analytics into existing database management systems (DBMSs) not only eliminates the need for costly data transfers to external ML platforms but also ensures compliance with regulatory standards. While some DBMSs have integrated functionalities for training and applying ML models for analytics, these tasks still present challenges, particularly due to limited support for automatic feature engineering (AutoFE), which is crucial for optimizing ML model performance. In this paper, we introduce Adda, an agent-driven in-database feature generation tool designed to automatically create high-quality features for ML analytics directly within the database. Adda interprets ML analytics tasks described in natural language and generates code for feature construction by leveraging the power of large language models (LLMs) integrated with specialized agents. This code is then translated into SQL statements using a predefined set of operators and compiled just-in-time (JIT) into user-defined functions (UDFs). The result is a seamless, fully in-database solution for feature generation, specifically tailored for ML analytics tasks. Extensive experiments across 14 public datasets, with five ML tasks per dataset, show that Adda improves the AUC by up to 33.2% and reduces end-to-end latency by up to 100x compared to Madlib.

The increasing demand for deep neural inference within database environments has driven the emergence of AI?native DBMSs. However, existing solutions either rely on model-centric designs requiring developers to manually select, configure, and maintain models, resulting in high development overhead, or adopt task-centric AutoML approaches with high computational costs and poor DBMS integration. We present MorphingDB, a task-centric AI-native DBMS that automates model storage, selection, and inference within PostgreSQL. To enable flexible, I/O-efficient storage of deep learning models, we first introduce specialized schemas and multi-dimensional tensor data types to support BLOB-based all-in-one and decoupled model storage. Then we design a transfer learning framework for model selection in two phases, which builds a transferability subspace via offline embedding of historical tasks and employs online projection through feature-aware mapping for real-time tasks. To further optimize inference throughput, we propose pre-embedding with vectoring sharing to eliminate redundant computations and DAG-based batch pipelines with cost-aware scheduling to minimize the inference time. Implemented as a PostgreSQL extension with LibTorch, MorphingDB outperforms AI-native DBMSs (EvaDB, Madlib, GaussML) and AutoML platforms (AutoGluon, AutoKeras, AutoSklearn) across nine public datasets, encompassing series, NLP, and image tasks. Our evaluation demonstrates a robust balance among accuracy, resource consumption, and time cost in model selection and significant gains in throughput and resource efficiency.

Discovering co-movement patterns from urban-scale video data sources has emerged as an attractive topic. This task aims to identify groups of objects that travel together along a common route, which offers effective support for government agencies in enhancing smart city management. However, the previous work has made a strong assumption on the accuracy of recovered trajectories from videos and their co-movement pattern definition requires the group of objects to appear across consecutive cameras along the common route. In practice, this often leads to missing patterns if a vehicle is not correctly identified from a certain camera due to object occlusion or vehicle mis-matching. To address this challenge, we propose a relaxed definition of co-movement patterns from video data, which removes the consecutiveness requirement in the common route and accommodates a certain number of missing captured cameras for objects within the group. Moreover, a novel enumeration framework called Max-Growth is developed to efficiently retrieve the relaxed patterns. Unlike previous filter-and-refine frameworks comprising both candidate enumeration and subsequent candidate verification procedures, MaxGrowth incurs no verification cost for the candidate patterns. It treats the co-movement pattern as an equivalent sequence of clusters, enumerating candidates with increasing sequence length while avoiding the generation of any false positives. Additionally, we also propose two effective pruning rules to efficiently filter the non-maximal patterns. Extensive experiments are conducted to validate the efficiency of MaxGrowth and the quality of its generated co-movement patterns. Our MaxGrowth runs up to two orders of magnitude faster than the baseline algorithm. It also demonstrates high accuracy in real video dataset when the trajectory recovery algorithm is not perfect.

Querying and analyzing data in data lakes requires substantial manual intervention, including numerous data preprocessing steps, and often demands complex domain expertise. However, the advent of Large Language Models (LLMs) has introduced a promising solution to these challenges by providing a unified framework for interpreting the heterogeneous datasets within data lakes. In this paper, we demonstrate QueryArtisan, a novel LLM-powered analytical system tailored for data lakes. It enables users to issue complex queries in natural language without the need for domain-specific expertise. The system automatically executes user-submitted queries and performs data processing and analysis based on the query results. QueryArtisan extends beyond traditional ETL (Extract, Transform, Load) processes by generating just-in-time code customized for dataset-specific tasks. A suite of heterogeneous operators is developed to process data across various modalities. In addition, a cost-based query optimization mechanism is integrated to improve the efficiency of the generated code. Furthermore, QueryArtisan can dynamically instantiate multiple agents in response to user-defined analytical requirements to perform further in-depth analysis of the retrieved data.

Many GaussDB customers, particularly small and medium-sized enterprises (SMEs), require high transaction throughput with occasional analytical queries. HTAP systems that deploy both OLTP and OLAP engines on a single server to manage hybrid workloads have become increasingly popular among customers for achieving high cost-efficiency and data freshness. However, co-locating these systems can lead to resource contention, particularly for memory, potentially degrading overall system performance and causing Service-Level Agreements (SLA) violations. To address this issue, we propose T 2 (Twisted Twin), an adaptive memory management approach that dynamically allocates memory between OLTP and OLAP components. This approach ensures OLTP meets SLA while optimizing the efficiency of OLAP query processing. However, this is non-trivial, as memory allocation triggers a cascade of effects, including in-memory column selection and data synchronization, both critical in HTAP systems. To overcome these challenges, we introduce a Bayesian optimization framework tailored for fluctuating workloads that adjusts memory allocation responsively. Experiments conducted on the real-world HTAP system, GaussDB-HTAP, demonstrate the effectiveness and efficiency of T 2 .

Memory-based temporal graph neural network (MTGNN) models are effective for predicting temporal graphs by using node memory and message-passing modules to capture temporal and structural information, respectively. However, distributed training for large graphs presents challenges such as accuracy loss and decreased efficiency due to remote features and memory transmission. Despite improvements in MTGNN system optimizations, issues like dynamic load imbalances, communication overhead, and memory staleness persist. To tackle these challenges, we introduce MemShare, a distributed MTGNN system. MemShare introduces a novel shared node memory paradigm that utilizes a small subset of shared nodes across machines and GPUs to reduce distributed communication for memory management. It incorporates techniques like shared nodes-centric graph partitioning, shared nodes-aware boundary decay sampling, and shared nodes-targeted synchronous smoothing aggregation. Experiments show that MemShare outperforms existing distributed MTGNN systems in accuracy and training efficiency.

Log-based anomaly detection plays a crucial role in ensuring the reliability of systems. While deep learning-based small detection models (SDMs) are efficient, the large language models (LLMs) are accurate and capable of providing explanations. Intuitively, a compelling question arises: Can we seamlessly combine the advantages of both approaches? In this work, we delve into this underexplored research direction and propose CoLA, a novel collaborative log anomaly detection framework. During collaborative inference, an SDM serves as a filter to select potentially anomalous instances, while a downstream LLM acts as an expert to detect anomalies, offer explanations, and refine the SDM. Extensive experiments on three large real-world datasets demonstrate that CoLA significantly outperforms state-of-the-art methods in terms of effectiveness, efficiency, and explainability, while also greatly reducing labor costs.

Cryo-CMOS IC for quantum applications, proposed for tens of years, are designed to control quantum processors operating at cryogenic temperatures (CTs). The reference circuits play a significant role in quantum controllers, providing a relatively stable biasing for analog and radio frequency (RF) circuit blocks. Based on a literature review, we discovered that achieving high-accuracy reference voltage or current at CTs is challenging due to the unstable temperature characteristics of complementary metal-oxide-semiconductor (CMOS), bipolar junction transistor (BJT), or resistors in the general CMOS process at CTs. Therefore, certain specialized device structures, such as dynamic threshold MOS (DTMOS), can be employed within the bulk CMOS process. Alternatively, BJT and other devices found in specific processes, such as silicon-germanium (SiGe) and fully depleted silicon on insulator (FD-SOI) CMOS, can achieve adaptive temperature compensation. This paper provides a succinct overview of several fundamental structures and common research hot spots about the reference voltage circuits, and then assesses their suitability for CT circuit design, considering the reliability of devices in bulk CMOS, FD-SOI CMOS, and SiGe process. Finally, the paper summarizes the types of cryo-temperature reference circuits and offers an overview and comparison of them.

Graph neural networks (GNNs) are effective models for analyzing graph-structured data, but encounter challenges when training on large distributed graphs. Existing GNN training frameworks use sampling parallelism and historical embedding methods to support distributed training and enhance efficiency. However, these methods suffer from issues like stale historical embeddings, imbalanced communication messages, and redundant storage and computation costs. In this paper, we present Emma, a distributed GNN training framework that incorporates source node centric chunking for frequent updates of embeddings and balanced communication, as well as a moving message aggregation technique to boost training efficiency and reduce storage costs. Experimental results show that Emma significantly enhances training efficiency by reducing computation and communication overhead, leading to a notable speedup while maintaining convergence accuracy compared to state-of-the-art distributed GNN training methods.

Multi-Object Tracking (MOT) is a cornerstone operator for video surveillance applications. To enable real-time processing of large-scale live video streams, we study an interesting scenario called down-sampled MOT, which performs object tracking only on a small subset of video frames. The problem is challenging for state-of-the-art MOT methods, which exhibit significant performance degradation under high frame reduction ratios. In this paper, we devise a sampling-resilient tracker with a novel sparse-observation Kalman filter (SOKF). It integrates an LSTM network to capture non-linear and dynamic motion patterns caused by sparse observations. Since the LSTM-based state transition is not compatible with the original noise estimation mechanism, we propose new estimation strategies based on Bayesian neural networks and derive the optimal Kalman gain for SOKF. To associate the detected bounding boxes robustly, we also propose a comprehensive similarity metric that systematically integrates multiple spatial matching signals. Experiments on three benchmark datasets show that our proposed tracker achieves the best trade-off between efficiency and accuracy. With the same tracking accuracy, we reduce the total processing time of ByteTrack by 2× in MOT17 and 3× in DanceTrack.

The scarcity of training data restricts a neural network from capturing schema diversity and intricacies, hindering schema-matching models' generalization capabilities. In this paper, we propose ISResMat, a framework specifically designed to match the schemas of relational tables by fine-tuning a pre-trained language model. We first offer a training data construction method, Pairwise Sampling, which could generate the training dataset with table data. Next, we design two loss functions (i.e., Meta-Matching Loss and Agent-Delegating Loss) to learn representations of table columns. With those representations, we could calculate matching scores between different table columns for deducing the matching candidates, which provides a novel approach to schema matching. Finally, we present two optimizations (i.e., Matching Rectification Loss and Distribution-Aware Fingerprint) to handle the problems of matching cardinality constraints and numerical columns, respectively. ISResMat is a flexible framework supporting instance-based, schema-based, and hybrid matching without significant modification. Experiments on 500+ fabricated and human-curated relation pairs spanning diverse domains and matching scenarios showcase that our approach outperforms existing state-of-the-art methods.

Verbal and visual-spatial information processing are two critical subsystems that activate different brain regions and often collaborate together for cognitive reasoning. Despite the rapid advancement of LLM-based reasoning, the mainstream frameworks, such as Chain-of-Thought (CoT) and its variants, primarily focus on the verbal dimension, resulting in limitations in tackling reasoning problems with visual and spatial clues. To bridge the gap, we propose a novel dual-modality reasoning framework called Vision-Augmented Prompting (VAP). Upon receiving a textual problem description, VAP automatically synthesizes an image from the visual and spatial clues by utilizing external drawing tools. Subsequently, VAP formulates a chain of thought in both modalities and iteratively refines the synthesized image. Finally, a conclusive reasoning scheme based on self-alignment is proposed for final result generation. Extensive experiments are conducted across four versatile tasks, including solving geometry problems, Sudoku, time series prediction, and travelling salesman problem. The results validated the superiority of VAP over existing LLMs-based reasoning frameworks.

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established *adaptor* modules like LoRA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the *out-of-distribution* concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The *aesthetics* score and *concept-matching* score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric.

Tabular data pervades the landscape of the World Wide Web, playing a foundational role in the digital architecture that underpins online information. Given the recent influence of large-scale pretrained models like ChatGPT and SAM across various domains, exploring the application of pretraining techniques for mining tabular data on the web has emerged as a highly promising research direction. Indeed, there have been some recent works around this topic where most (if not all) of them are limited in the scope of a fixed-schema/single table. Due to the scale of the dataset and the parameter size of the prior models, we believe that we have not reached the ''BERT moment'' for the ubiquitous tabular data. The development on this line significantly lags behind the counterpart research domains such as natural language processing. In this work, we first identify the crucial challenges behind tabular data pretraining, particularly overcoming the cross-table hurdle. As a pioneering endeavor, this work mainly (i)-contributes a high-quality real-world tabular dataset, (ii)-proposes an innovative, generic, and efficient cross-table pretraining framework, dubbed as CM2, where the core to it comprises a semantic-aware tabular neural network that uniformly encodes heterogeneous tables without much restriction and (iii)-introduces a novel pretraining objective --- prompt Masked Table Modeling (pMTM) --- inspired by NLP but intricately tailored to scalable pretraining on tables. Our extensive experiments demonstrate CM2's state-of-the-art performance and validate that cross-table pretraining can enhance various downstream tasks.

Abstract Federated learning (FL) is a promising approach for learning a model from data distributed on massive clients without exposing data privacy. It works effectively in the ideal federation where clients share homogeneous data distribution and learning behavior. However, FL may fail to function appropriately when the federation is not ideal, amid an unhealthy state called Negative Federated Learning (NFL), in which most clients gain no benefit from participating in FL. Many studies have tried to address NFL. However, their solutions either (1) predetermine to prevent NFL in the entire learning life-cycle or (2) tackle NFL in the aftermath of numerous learning rounds. Thus, they either (1) indiscriminately incur extra costs even if FL can perform well without such costs or (2) waste numerous learning rounds. Additionally, none of the previous work takes into account the clients who may be unwilling/unable to follow the proposed NFL solutions when using those solutions to upgrade an FL system in use. This paper introduces FL-GUARD, a holistic framework that can be employed on any FL system for tackling NFL in a run-time paradigm. That is, to dynamically detect NFL at the early stage (tens of rounds) of learning and then to activate recovery measures when necessary. Specifically, we devise a cost-effective NFL detection mechanism, which relies on an estimation of performance gain on clients. Only when NFL is detected, we activate the NFL recovery process, in which each client learns in parallel an adapted model when training the global model. Extensive experiment results confirm the effectiveness of FL-GUARD in detecting NFL and recovering from NFL to a healthy learning state. We also show that FL-GUARD is compatible with previous NFL solutions and robust against clients unwilling/unable to take any recovery measures.

Scalable video query optimization has re-emerged as an attractive research topic in recent years. The OTIF system, a video database with cutting-edge efficiency, has introduced a new paradigm of utilizing view materialization to facilitate online query processing. Specifically, it stores the results of multi-object tracking queries to answer common video queries with sub-second latency. However, the cost associated with view materialization in OTIF is prohibitively high for supporting large-scale video streams. In this paper, we study efficient MOT-based view materialization in video databases. We first conduct a theoretical analysis and establish two types of optimality measures that serve as lower bounds for video frame sampling. In order to minimize the number of processed video frames, we propose a novel predictive sampling framework, namely LEAP, exhibits near-optimal sampling performance. Its efficacy relies on a data-driven motion manager that enables accurate trajectory prediction, a compact object detection model via knowledge distillation, and a robust cross-frame associator to connect moving objects in two frames with a large time gap. Extensive experiments are conducted in 7 real datasets, with 7 baselines and a comprehensive query set, including selection, aggregation and top-k queries. The results show that with comparable query accuracy to OTIF, our LEAP can reduce the number of processed video frames by up to 9× and achieve 5× speedup in query processing time. Moreover, LEAP demonstrates impressive throughput when handling large-scale video streams, as it leverages a single NVIDIA RTX 3090ti GPU to support real-time MOT-based view materialization from 160 video streams simultaneously.

Similarity search is a fundamental but expensive operator in querying trajectory data, due to its quadratic complexity of distance computation. To mitigate the computational burden for long trajectories, neural networks have been widely employed for similarity learning and each trajectory is encoded as a high-dimensional vector for similarity search with linear complexity. Given the sequential nature of trajectory data, previous efforts have been primarily devoted to the utilization of RNNs or Transformers. In this paper, we argue that the common practice of treating trajectory as sequential data results in excessive attention to capturing long-term global dependency between two sequences. Instead, our investigation reveals the pivotal role of local similarity, prompting a revisit of simple CNNs for trajectory similarity learning. We introduce ConvTraj, incorporating both 1D and 2D convolutions to capture sequential and geo-distribution features of trajectories, respectively. In addition, we conduct a series of theoretical analyses to justify the effectiveness of ConvTraj. Experimental results on four real-world large-scale datasets demonstrate that ConvTraj achieves state-of-the-art accuracy in trajectory similarity search. Owing to the simple network structure of ConvTraj, the training and inference speed on the Porto dataset with 1.6 million trajectories are increased by at least 240x and 2.16x, respectively.

Query processing over data lakes is a challenging task, often requiring extensive data pre-processing activities such as data cleaning, transformation, and loading. However, the advent of Large Language Models (LLMs) has illuminated a new pathway to address these complexities by offering a unified approach to understanding the diverse datasets submerged in data lakes. In this paper, we introduce QueryArtisan, a novel LLM-powered analytic tool specifically designed for data lakes. QueryArtisan transcends traditional ETL (Extract, Transform, Load) processes by generating just-intime code for dataset-specific queries. It eliminates the need for an intermediary schema, enabling users to query the data lake directly using natural language. To achieve this, we have developed a suite of heterogeneous operators capable of processing data across various modalities. Additionally, QueryArtisan incorporates a cost model-based query optimization technique, significantly enhancing its code generation capabilities for efficient query resolution. Our extensive experimental evaluations, conducted with real-life datasets, demonstrate that QueryArtisan markedly outperforms existing solutions in terms of effectiveness, efficiency and usability.

Quantum computing represents a next-generation technology in data processing, promising to transcend the limitations of traditional computation. In this paper, we undertake an early exploration of the potential integration of quantum computing with database query optimization. We introduce a pioneering hybrid classical-quantum algorithm for sampling-based approximate query processing (AQP). The core concept of the algorithm revolves around identifying rare groups, which often follow a long-tail distribution, and applying distinct sampling methodologies to normal and rare groups. By leveraging the quantum capabilities of the diffusion gate and QRAM, the algorithm defines a novel quantum sampling approach that iteratively amplifies the signals of these infrequent groups. The algorithm operates without the need for preprocessing or prior knowledge of workloads or data. It utilizes the power of quadratic acceleration to achieve well-balanced sampling across various data categories. Experimental results demonstrate that in the context of AQP, the new sampling scheme provides higher accuracy at the same sampling cost. Additionally, the benefits of quantum computing become more pronounced as query selectivity increases.

The last decade has witnessed the success of deep learning and the surge of publicly released trained models, which necessitates the quantification of the model functional distance for various purposes. However, quantifying the model functional distance is always challenging due to the opacity in inner workings and the heterogeneity in architectures or tasks. Inspired by the concept of "field" in physics, in this work we introduce Model Gradient Field (abbr. ModelGiF) to extract homogeneous representations from the heterogeneous pre-trained models. Our main assumption underlying ModelGiF is that each pre-trained deep model uniquely determines a ModelGiF over the input space. The distance between models can thus be measured by the similarity between their ModelGiFs. We validate the effectiveness of the proposed ModelGiF with a suite of testbeds, including task relatedness estimation, intellectual property protection, and model unlearning verification. Experimental results demonstrate the versatility of the proposed ModelGiF on these tasks, with significantly superiority performance to state-of-the-art competitors. Codes are available at https://github.com/zju-vipa/modelgif.

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust AGgregation Rules (AGRs) have been proposed to defend against Byzantine attacks. However, Byzantine clients can still circumvent robust AGRs when data is non-Identically and Independently Distributed (non-IID). In this paper, we first reveal the root causes of performance degradation of current robust AGRs in non-IID settings: the curse of dimensionality and gradient heterogeneity. In order to address this issue, we propose GAS, a GrAdient Splitting approach that can successfully adapt existing robust AGRs to non-IID settings. We also provide a detailed convergence analysis when the existing robust AGRs are combined with GAS. Experiments on various real-world datasets verify the efficacy of our proposed GAS. The implementation code is provided in https://github.com/YuchenLiu-a/byzantine-gas.

The mission of active learning is to identify the most valuable data samples, thus attaining decent performance with much fewer samples. The data augmentation techniques seem straightforward yet promising to enhance active learning by extending the exploration of the input space, which helps locate more valuable samples. In this work, we thoroughly study the coupling of data augmentation and active learning, thereby proposing Controllable Augmentation ManiPulator for Active Learning. In contrast to the few prior works that touched on this line, CAMPAL emphasizes a purposeful, tighten, and better-controlled integration of data augmentation into active learning in three folds: (i)-carefully designed augmentation policies applied separately on labeled and unlabeled data pools; (ii)-controlled and quantifiably optimizable augmentation strengths; (iii)-full and flexible coverage for most (if not all) active learning schemes. Theories are proposed and associated with the development of key components in CAMPAL. Through extensive empirical experiments, we bring the performance of active learning methods to a new level: an absolute performance boost of 16.99% on CIFAR-10 and 12.25 on SVHN with 1,000 annotated samples. Codes are available at https://github.com/jnzju/CAMPAL.

Abstract Textile pattern design is a time‐consuming and tedious work. Mihui, our ongoing developing system, employs deep‐learning techniques to automatically generate huge volumes of patterns with the help of human guidance. However, trained as a black box, Mihui cannot provide customized service for each individual designer who shows unique aesthetics preferences. In this article, we introduce the recommendation module of Mihui. The module forwards all generated pattern images to a deep encoding network, where images are mapped into 128‐dimension vectors. For each user of Mihui, we create a profile by his/her purchased or downloaded history. A novel encoder network is proposed to learn a personal taste vector for each user, based on which, we recommend new patterns to him/her. Our records in Mihui show that the recommendation module effectively improve users' experience on Mihui.

Generation-based testing techniques have shown their effectiveness in detecting logic bugs of DBMS, which are often caused by improper implementation of query optimizers. Nonetheless, existing generation-based debug tools are limited to single-table queries and there is a substantial research gap regarding multi-table queries with join operators. In this paper, we propose TQS, a novel testing framework targeted at detecting logic bugs derived by queries involving multi-table joins. Given a target DBMS, TQS achieves the goal with two key components: Data-guided Schema and Query Generation (DSG) and Knowledge-guided Query Space Exploration (KQE). DSG addresses the key challenge of multi-table query debugging: how to generate ground-truth (query, result) pairs for verification. It adopts the database normalization technique to generate a testing schema and maintains a bitmap index for result tracking. To improve debug efficiency, DSG also artificially inserts some noises into the generated data. To avoid repetitive query space search, KQE forms the problem as isomorphic graph set discovery and combines the graph embedding and weighted random walk for query generation. We evaluated TQS on four popular DBMSs: MySQL, MariaDB, TiDB and PolarDB. Experimental results show that TQS is effective in finding logic bugs of join optimization in database management systems. It successfully detected 115 bugs within 24 hours, including 31 bugs in MySQL, 30 in MariaDB, 31 in TiDB, and 23 in PolarDB respectively.

Recent work has applied learning-based approaches to replace the conventional cost model, but these approaches are expensive to train and result in high inference overheads. Furthermore, due to a lack of explainability, models trained for one database may not be easily transferred to another, requiring a complete re-training process. In this paper, we propose a new approach to tuning the conventional formula-based cost model for DBMS. Our approach involves identifying important parameters within the cost model rules and using a fast-learning model to adjust them for each specific hardware and software configuration of the DBMS deployment. We dynamically partition the search space of hardware and software configurations to gradually refine the cost model estimation. To apply our cost model to a new DBMS instance, we start with a rough estimation and progressively refine it with finer granularity. Our experiments with different hardware and software configurations show that our approach enables the conventional cost model to be quickly transferred to any database instance, achieving comparable results to a fine-tuned learning-based model. Overall, our approach provides a practical solution to tuning the conventional cost model for DBMS, with significant benefits in terms of reduced cost and improved performance.

Many IoT applications require the use of multiple deep neural networks (DNNs) to perform various tasks on low-cost edge devices with limited computation resources. However, existing DNN model serving platforms, such as TensorFlow Serving and TorchServe, are resource-intensive and require high-performance GPUs that are often not available on low-cost edge devices. In this paper, we propose SmartLite, a lightweight DBMS that addresses these challenges by storing the parameters and structural information of neural networks as database tables and implementing neural network operators inside the DBMS engine. SmartLite quantizes model parameters as binarized values, applies neural pruning techniques to compress the models, and transforms tensor manipulations into value lookup operations of the DBMS to reduce computation overhead. Experimental results show that SmartLite requires 98% less memory while achieving about a 134% performance speedup compared to Torch-Serve. Our proposed solution addresses the challenges of running multiple DNN models on low-cost edge devices and provides a significant contribution to the field of IoT applications.

Database management systems (DBMSs) are prone to logic bugs that can result in incorrect query results. Current debugging tools are limited to single table queries and struggle with issues like lack of ground-truth results and repetitive query space exploration. In this paper, we demonstrate DLBD, a system that automatically detects logic bugs in databases. DLBD offers holistic logic bug detection by providing automatic schema and query generation and ground-truth query result retrieval. Additionally, DLBD provides minimal test cases and root cause analysis for each bug to aid developers in reproducing and fixing detected bugs. DLBD incorporates heuristics and domain-specific knowledge to efficiently prune the search space and employs query space exploration mechanisms to avoid the repetitive search. Finally, DLBD utilizes a distributed processing framework to test database logic bugs in a scalable and efficient manner. Our system offers developers a reliable and effective way to detect and fix logic bugs in DBMSs.

Concerning the usability and efficiency to manage video data generated from large-scale cameras, we demonstrate DoveDB, a declarative and low-latency video database. We devise a more comprehensive video query language called VMQL to improve the expressiveness of previous SQL-like languages, which are augmented with functionalities for model-oriented management and deployment. We also propose a light-weight ingestion scheme to extract tracklets of all the moving objects and build semantic indexes to facilitate efficient query processing. For user interaction, we construct a simulation environment with 120 cameras deployed in a road network and demonstrate three interesting scenarios. Using VMQL, users are allowed to 1) train a visual model using SQL-like statement and deploy it on dozens of target cameras simultaneously for online inference; 2) submit multi-object tracking (MOT) requests on target cameras, store the ingested results and build semantic indexes; and 3) issue an aggregation or top- k query on the ingested cameras and obtain the response within milliseconds. A preliminary video introduction of DoveDB is available at https://www.youtube.com/watch?v=N139dEyvAJk

Recently, Convolutional Neural Network (CNN) has achieved excellent performance in the classification task. It is widely known that CNN is deemed as a 'blackbox', which is hard for understanding the prediction mechanism and debugging the wrong prediction. Some model debugging and explanation works are developed for solving the above drawbacks. However, those methods focus on explanation and diagnosing possible causes for model prediction, based on which the researchers handle the following optimization of models manually. In this paper, we propose the first completely automatic model diagnosing and treating tool, termed as Model Doctor. Based on two discoveries that 1) each category is only correlated with sparse and specific convolution kernels, and 2) adversarial samples are isolated while normal samples are successive in the feature space, a simple aggregate gradient constraint is devised for effectively diagnosing and optimizing CNN classifiers. The aggregate gradient strategy is a versatile module for mainstream CNN classifiers. Extensive experiments demonstrate that the proposed Model Doctor applies to all existing CNN classifiers, and improves the accuracy of 16 mainstream CNN classifiers by 1%~5%.

In Alibaba's IoT platform, we face the challenge of processing analytical queries involving both structured and unstructured data. Normally, collaborative queries need deep learning (DL) models and relational algebras to work intertwined to produce sophisticated analytical answers. To be able to support collaborative queries, a variety of approaches have been proposed. In this paper, we present the three most representative ones and study their advantages and limitations. The first one translates the collaborative query into a series of database and DL sub-queries and then maintains the dependence of the intermediate results of two sub-systems and computes the final results on the fly. The second one transforms a DL model to a database built-in User Defined Function(UDF) implemented in C++. The whole collaborative query is then processed by the database system independently. The third one is our novel solution proposed in the paper, DL2SQL, where neural operators underneath DL models are rewritten as SQL queries, and collaborative queries are processed using native SQL syntax. A cost model for our SQL-native neural operators is designed to leverage the database's optimizer to generate an efficient query plan. All three approaches are implemented on the ClickHouse. Finally, we use the real-world workloads on Alibaba's IoT platform as our benchmark and deploy various approaches on both an embedded device and a Cloud server to compare their performance. Results show that DL2SQL outperforms others in most scenarios and is more extensible.

In this paper, we study a new variant of trajectory similarity search from the context of continuous query processing. Given a moving object from$s$to$d$, following a reference route$T_{r}$, we monitor the trajectory similarity between the reference route and the current partial route at each timestamp for online detour detection. We consider deviation calculation in both Euclidean space and road networks. Furthermore, we propose efficient incremental processing strategies to facilitate continuous query processing for moving objects. Our experiments are conducted on multiple real datasets and the experimental results verify the efficiency of our query processing algorithms.

Deep learning has recently achieved remarkable performance in image classification tasks, which depends heavily on massive annotation. However, the classification mechanism of existing deep learning models seems to contrast to humans' recognition mechanism. With only a glance at an image of the object even unknown type, humans can quickly and precisely find other same category objects from massive images, which benefits from daily recognition of various objects. In this paper, we attempt to build a generalizable framework that emulates the humans' recognition mechanism in the image classification task, hoping to improve the classification performance on unseen categories with the support of annotations of other categories. Specifically, we investigate a new task termed Comparison Knowledge Translation (CKT). Given a set of fully labeled categories, CKT aims to translate the comparison knowledge learned from the labeled categories to a set of novel categories. To this end, we put forward a Comparison Classification Translation Network (CCT-Net), which comprises a comparison classifier and a matching discriminator. The comparison classifier is devised to classify whether two images belong to the same category or not, while the matching discriminator works together in an adversarial manner to ensure whether classified results match the truth. Exhaustive experiments show that CCT-Net achieves surprising generalization ability on unseen categories and SOTA performance on target categories.

Recently, the learning-based models are shown to outperform the conventional methods for many database tasks such as cardinality estimation, join order selection and performance tuning. However, most existing learning-based methods adopt the one-hot encoding for SQL query representation, unable to catch complicated semantic context, e.g. structure of query, database schema definition and distribution variance of columns. To address such above problem, we propose a novel pre-trained SQL representation model, called PreQR, which extends the language representation approach to SQL queries. We propose an automaton to encode the query structures, and apply a graph neural network to encode database schema information conditioned on the query. A new SQL encoder is then established by adopting the attention mechanism to support on-the-fly query-aware schema linking. Experimental results on real datasets show that replacing the one-hot encoding with our query representation can significantly improve the performances of existing learning-based models on several database tasks.

The autonomous database of the next generation aims to apply the reinforcement learning (RL) on tasks like query optimization and performance tuning with little or no human DBAs’ intervention. Despite the promise, to obtain a decent policy model in the domain of database optimization is still challenging — primarily due to the inherent computational overhead involved in the data hungry RL frameworks — in particular on large databases. In the line of mitigating this adverse effect, we propose Mirror in this work. The core to Mirror is a sampling process built in an RL framework together with a transferring process of the policy model from the sampled database to its original counterpart. While being conceptually simple, we identify that the policy transfer between databases involves heavy noise and prediction drifting that cannot be neglectable. Thereby we build a theoretical-guided sampling algorithm in Mirror assisted by a continuous fine-tuning module. The experiments on the PostgreSQL and an industry database PolarDB validate that Mirror has effectively reduced the computational cost while maintaining a satisfactory performance.

Abstract Thanks to the rapid advances in artificial intelligence, a brand new venue for database performance optimization is through deep neural networks and the reinforcement learning paradigm. Alongside the long literature in this regime, an iconic and crucial problem is the index structure building. For this problem, the prior works have largely adopted a pure learning-based solution replacing the traditional methods such as a B-tree and Hashing. While this line of research has drawn much attention in the field, they ubiquitously abandon the semantic guarantees and also suffer from performance loss in certain scenarios. In this work, we propose the Neural Index Search (NIS) framework. The core to this framework is to train a search policy to find a near optimal combination plan over the existing index structures, together with the required configuration parameters associated with each index structure in the plan. We argue that compared against the pure learning approaches, NIS enjoys the advantages brought by the chosen conventional index structures and further robustly enhances the performance from any singular index structure. Extensive empirical results demonstrate that our framework achieves state-of-the-art performances on several benchmarks.

Complex data mining algorithms are processed in multiple iterations, where output of one iteration is used as input for the subsequent iterations. Existing parallel programming frameworks, e.g., MapReduce, Pregel and Spark, adopt the breadth first search (BFS) strategy to process those iterative jobs. They invoke the user-defined functions for every key-value pair or vertex to produce all possible intermediate results for the next iteration. Such BFS strategy incurs high I/O overheads, because normally, the size of intermediate search results of BFS is exponential to the size of original data, making it impossible to maintain those intermediate results in memory. In this paper, we present a new type of parallel programming model, the stack-centric model, where all computations are defined for a stack maintained in the distributed shared memory. The stack can be adaptively split into multiple stacks and disseminated to different compute nodes for parallel processing. The most distinguished feature of the stack-centric model is its support for the depth first search (DFS) algorithm which incurs much less memory overhead than its BFS counterpart. The maximal memory usage of DFS algorithm is determined by the height of its search tree, and hence, it is possible to conduct the computation of DFS algorithm mostly in memory. Our stack-centric model is not a pure DFS framework. It supports the hybrid BFS and DFS algorithms by tuning the trade-off between memory usage and parallelism. To show the advantages of stack-centric model, we implement two algorithms, frequent pattern mining algorithm and DNA sequence matching algorithm, on both stack-centric model and Spark. The memory usage of stack-centric model is 10 times less than the Spark, resulting in a significant performance improvement.

In this paper, we study a new variant of trajectory similarity search from the context of continuous query processing. Given a moving object from$s$to$d$, following a reference route$T_r$, we monitor the trajectory similarity between the reference route and the current partial route at each timestamp for online detour detection. Since existing trajectory distance measures fail to adequately capture the deviation between a partial route and a complete route, we propose a partial trajectory similarity measure to bridge the gap. In particular, we enumerate all the possible routes extended from the partial route to reach the destination$d$and calculate their minimum distance to$T_r$. We consider deviation calculation in both euclidean space and road networks. In euclidean space, we can directly infer the optimal future path with the minimum trajectory distance. In road networks, we propose an efficient expansion algorithm with a suite of pruning rules. Furthermore, we propose efficient incremental processing strategies to facilitate continuous query processing for moving objects. Our experiments are conducted on multiple real datasets and the experimental results verify the efficiency of our query processing algorithms.

Nearest neighbor (NN) search in high-dimensional spaces is inherently computationally expensive due to the curse of dimensionality. As a well-known solution to approximate NN search, locality-sensitive hashing (LSH) is able to answer c-approximate NN (c-ANN) queries in sublinear time with a well-defined performance bound. The success of LSH family mainly depends on the design of randomly projected hash functions. However, instead of randomly drawing hash functions from a conventional hashing family such as Gaussian projection for Euclidean space, we argue that whether there could be a set of data sensitive hashing functions with higher capacity to distinguish nearby points and far away points, which could have rigorous performance guarantee like conventional LSH. To this end, we propose a learning to tune framework, called LSH-tuning, which consists of a pruning model and a learning to rank model. The pruning model reduces the total number of hash tables to maximize the separating capacity on the given data distribution and minimize the storage overhead. The learning to rank model ranks hash tables based on their effectiveness on NN retrieval. We also have a theoretic model that guides us to gradually search more hash tables and probe nearby buckets. Extensive experiments with real-world data demonstrate that LSH-tuning is capable of outperforming existing proposals with respect to both efficiency and storage overhead.

Most, if not all, modern deep learning systems restrict themselves to a single dataset for neural network training and inference. In this article, we are interested in systematic ways to join datasets that are made of similar purposes. Unlike previous published works that ubiquitously conduct the dataset joining in the uninterpretable latent vectorial space, the core to our method is an augmentation procedure in the label space. The primary challenge to address the label space for dataset joining is the discrepancy between labels: non-overlapping label annotation sets, different labeling granularity or hierarchy and etc. Notably we propose a new technique leveraging artificially created knowledge graph, recurrent neural networks and policy gradient that successfully achieve the dataset joining in the label space. Empirical results on both image and text classification justify the validity of our approach.

Metric learning aims to project original data into a new space, where data points can be classified more accurately using kNN or similar types of classification algorithms. To avoid trivial learning results such as indistinguishably projecting the data onto a line, many existing approaches formulate metric learning as a constrained optimization problem, like finding a metric that minimizes the distance between data points from the same class, with a constraint of ensuring a certain separation for data points from different classes, and then they approximate the optimal solution to the constrained optimization in an iterative way. In order to improve the classification accuracy as much as possible, we try to find a metric that is able to minimize the intra-class distance and maximize the inter-class distance simultaneously. Towards this, we formulate metric learning as a penalized optimization problem, and provide design guideline, paradigms with a general formula, as well as two representative instantiations for the penalty term. In addition, we provide an analytical solution for the penalized optimization, with which costly computation can be avoid, and more importantly, there is no need to worry about the convergence rates or approximation ratios any more. Extensive experiments on real-world data sets are conducted, and the results verify the effectiveness and efficiency of our approach.

Previous work on the spatio-temporal index often adopts a simple linear model to predict the future positions of moving objects, which may generate numerous errors for complex road networks and fast moving objects. In this paper, we propose NEIST, a neural-enhanced index to process spatio-temporal queries with enhanced efficiency and accuracy, by intelligently leveraging the movement patterns among moving objects. NEIST applies a Recurrent Neural Network (RNN) model to predict future positions of moving objects based on observed trajectories. To reduce the prediction overhead, a suffix-tree is further built to index trajectories with similar suffixes, and thus similar objects within a given similarity bound are grouped together to share the same prediction result. A prediction result in NEIST represents possible positions of a group of moving objects in the next t time slots. Inside each time slot, traditional linear prediction model is then adopted and a TPR-Tree is built to support spatio-temporal queries. We use Singapore and Porto taxi trajectory datasets to evaluate NEIST. Compared to previous approaches, NEIST achieves a much more efficient query performance and is able to produce about 70 percent more accurate results.

In this demonstration, we present a new definition of integrity constraint that is more powerful for anomalous data discovery. In our definition, a constraint is functioned on both categorical and numerical attributes in relational tables, as well as their derivative attributes, leading to a huge search space. Furthermore, we are the first to take into account attribute value distribution as part of a constraint. Based on the proposed integrity constraint, we build AUDITOR on top of relational tables from the industry of healthcare auditing and demonstrate its effectiveness and ease-of-use for domain experts to discover anomalous data.

Entity matching (EM) is a classic research problem that identifies data instances referring to the same real-world entity. Recent technical trend in this area is to take advantage of deep learning (DL) to automatically extract discriminative features. DeepER and DeepMatcher have emerged as two pioneering DL models for EM. However, these two state-of-the-art solutions simply incorporate vanilla RNNs and straightforward attention mechanisms. In this paper, we fully exploit the semantic context of embedding vectors for the pair of entity text descriptions. In particular, we propose an integrated multi-context attention framework that takes into account self-attention, pair-attention and global-attention from three types of context. The idea is further extended to incorporate attribute attention in order to support structured datasets. We conduct extensive experiments with 7 benchmark datasets that are publicly accessible. The experimental results clearly establish our superiority over DeepER and DeepMatcher in all the datasets.

Textile pattern design is a challenging task that can be hardly resolved by a single deep neural network, due to the requirements on high resolution, periodic tiling, copyright protection and aesthetic preference of designers. In this paper, we present our NAD system which can automatically produce high-quality textile patterns for printing industry. Our NAD system splits the work into three steps: layout design, image filtering and pattern style transfer. In the first and last step, we employ different neural models to learn the process of artwork creation by human designers. Specifically, a reinforcement learning model is first developed for layout adjustment, followed by a CNN-based model for style transfer. We have employed our NAD system in an online production system with real customers and the results are very impressive and promising. The NAD system not only frees human designers from the labor intensive design process, but also results in a 2%-5% daily purchase rate.

DBSCAN is one of important density-based clustering methods, which has a wide range of applications in machine learning and data mining, to name but a few. However, the rapid growing volume and variety of data nowadays challenges traditional DBSCAN, and thus, distributed DBSCAN in metric spaces is required. In this paper, we propose DBSCAN-MS, a distributed density-based clustering in metric spaces. To ensure load balancing, we present a k-d tree based partitioning approach. It utilizes pivots to map the data in metric spaces to vector spaces, and employs k-d tree partitioning technique to equally divide the data. To avoid unnecessary computation and communication cost, we propose a framework that divides data into partitions, find out local DBSCAN result, and merge local result based on a merging graph. In addition, the pivot filtering and the sliding window techniques are also used in the framework for pruning. Extensive experiments with both real and synthetic datasets demonstrate the efficiency and scalability of our proposed DBSCAN-MS.

Many new memory indexing structures have been proposed and outperform current in-memory skip-list index adopted by LevelDB, RocksDB and other key-value systems. However, those new indexes cannot be easily intergrated with key-value systems, because most of them do not consider how the data can be efficiently flushed to disk. Some assumptions, such as fixed size key and value, are unrealistic for real applications. In this paper, we present S3, a scalable in-memory skip-list index for the customized version of RocksDB in Alibaba Cloud. S3 adopts a two-layer structure. In the top layer, a cache-sensitive structure is used to maintain a few guard entries to facilitate the search over the skip-list. In the bottom layer, a semi-ordered skip-list index is built to support highly concurrent insertions and fast lookup and range query. To further improve the performance, we train a neural model to select guard entries intelligently according to the data distribution and query distribution. Experiments on multiple datasets show that S3 achieves a comparable performance to other new memory indexing schemes, and can replace current in-memory skip-list of LevelDB and RocksDB to support huge volume of data.

Intelligent fashion outfit composition has become more popular in recent years. Some deep-learning-based approaches reveal competitive composition. However, the uninterpretable characteristic makes such a deep-learning-based approach fail to meet the businesses’, designers’, and consumers’ urges to comprehend the importance of different attributes in an outfit composition. To realize interpretable and intelligent multi-item fashion outfit compositions, we propose a partitioned embedding network to learn interpretable embeddings from clothing items. The network contains two vital components: attribute partition module and partition adversarial module. In the attribute partition module, multiple attribute labels are adopted to ensure that different parts of the overall embedding correspond to different attributes. In the partition adversarial module, adversarial operations are adopted to achieve the independence of different parts. With the interpretable and partitioned embedding, we then construct an outfit-composition graph and an attribute matching map. Extensive experiments demonstrate that (1) the partitioned embedding have unmingled parts that correspond to different attributes and (2) outfits recommended by our model are more desirable in comparison with the existing methods.

Entity resolution identifies all records in a database that refer to the same entity. The mainstream solutions rely on supervised learning or crowd assistance, both requiring labor overhead for data annotation. To avoid human intervention, we propose an unsupervised graph-theoretic fusion framework with two components, namely ITER and CliqueRank. Specifically, ITER constructs a weighted bipartite graph between terms and record-record pairs and iteratively propagates the node salience until convergence. Subsequently, CliqueRank constructs a record graph to estimate the likelihood of two records resident in the same clique. The derived likelihood from CliqueRank is fed back to ITER to rectify the edge weight until a joint optimum can be reached. Experimental evaluation was conducted among 14 competitors and results show that without any labeled data or crowd assistance, our unsupervised framework is comparable or even superior to state-of-the-art methods among three benchmark datasets.

CNN (Convolution Neural Network) is widely used in visual analysis and achieves exceptionally high performances in image classification, face detection, object recognition, image recoloring, and other learning jobs. Using deep learning frameworks, such as Torch and Tensorflow, CNN can be efficiently computed by leveraging the power of GPU. However, one drawback of GPU is its limited memory which prohibits us from handling large images. Passing a 4K resolution image to the VGG network will result in an exception of out-of-memory for Titan-X GPU. In this paper, we propose a new approach that adopts the BSP (bulk synchronization parallel) model to compute CNNs for images of any size. Before fed to a specific CNN layer, the image is split into smaller pieces which go through the neural network separately. Then, a specific padding and normalization technique is adopted to merge sub-images back into one image. Our approach can be easily extended to support distributed multi-GPUs. In this paper, we use neural style network as our example to illustrate the effectiveness of our approach. We show that using one Titan-X GPU, we can transfer the style of an image with 10,000×10,000 pixels within 1 minute.

New data has been generated in an unexpected high speed. To get insight of those data, data analysts will perform a thorough study using state-of-the-art big data analytical tools. Before the analysis starts, a preprocessing is conducted, where data analyst tends to issue a few ad-hoc queries on a new dataset to explore and gain a better understanding. However, it is costly to perform such ad-hoc queries on large scale data using traditional data management systems, e.g., DBMS, because data loading and indexing are very expensive. In this demo, we propose a novel visual data explorer system, FlashView, which omits the loading process by directly querying raw data. FlashView applies approximate query processing technique to achieve real-time query results. It builds both in-memory index and disk index to facilitate the data scanning. It also supports tracking and updating multiple queries concurrently. Note that FlashView is not designed as a replacement of full-fledged DBMS. Instead, it tries to help the analysts quickly understand the characteristics of data, so he/she can selectively load data into the DBMS to do more sophisticated analysis.

In spite of vast business potential, targeted advertising in public transportation systems is a grossly unexplored research area. For instance, SBS Transit in Singapore can reach 1 billion passengers per year but the annual advertising revenue contributes less than $35 million. To bridge the gap, we propose a probabilistic data model that captures the motion patterns and user interests so as to quantitatively evaluate the impact of an advertisement among the passengers. In particular, we leverage hundreds of millions of bus/train boarding transaction records to quantitatively estimate the probability as well as the extent of a user being influenced by an ad. Based on the influence model, we study a top-kretrieval problem for bus/train ad recommendation, which acts as a primitive operator to support various advanced applications. We solve the retrieval problem efficiently to support real-time decision making. In the experimental study, we use the dataset from SBS Transit as a case study to verify the effectiveness and efficiency of our proposed methodologies.

Each user session in an e-commerce system can be modeled as a sequence of web pages, indicating how the user interacts with the system and makes his/her purchase. A typical recommendation approach, e.g., Collaborative Filtering, generates its results at the beginning of each session, listing the most likely purchased items. However, such approach fails to exploit current viewing history of the user and hence, is unable to provide a real-time customized recommendation service. In this paper, we build a deep recurrent neural network to address the problem. The network tracks how users browse the website using multiple hidden layers. Each hidden layer models how the combinations of webpages are accessed and in what order. To reduce the processing cost, the network only records a finite number of states, while the old states collapse into a single history state. Our model refreshes the recommendation result each time when user opens a new web page. As user's session continues, the recommendation result is gradually refined. Furthermore, we integrate the recurrent neural network with a Feedfoward network which represents the user-item correlations to increase the prediction accuracy. Our approach has been applied to Kaola (http://www.kaola.com), an e-commerce website powered by the NetEase technologies. It shows a significant improvement over previous recommendation service.

We demonstrate iGlasses, a novel recommendation system that accepts a frontal face photo as the input and returns the best-fit eyeglasses as the output. As conventional recommendation techniques such as collaborative filtering become inapplicable in the problem, we propose a new recommendation method which exploits the implicit matching rules between human faces and eyeglasses. We first define fine-grained attributes for human faces and frames of glasses respectively. Then, we develop a recommendation framework based on a probabilistic graphical model, which effectively captures the correlation among these fine-grained attributes. Ranking of the frames (glasses) is done by their similarity to the query facial attributes. Finally, we produce a synthesized image for the input face to demonstrate the visual effect when wearing the recommended glasses.

By maintaining the data in main memory, in-memory databases dramatically reduce the I/O cost of transaction processing. However, for recovery purposes, in-memory systems still need to flush the log to disk, which incurs a substantial number of I/Os. Recently, command logging has been proposed to replace the traditional data log (e.g., ARIES logging) in in-memory databases. Instead of recording how the tuples are updated, command logging only tracks the transactions that are being executed, thereby effectively reducing the size of the log and improving the performance. However, when a failure occurs, all the transactions in the log after the last checkpoint must be redone sequentially and this significantly increases the cost of recovery. In this paper, we first extend the command logging technique to a distributed system, where all the nodes can perform their recovery in parallel. We show that in a distributed system, the only bottleneck of recovery caused by command logging is the synchronization process that attempts to resolve the data dependency among the transactions. We then propose an adaptive logging approach by combining data logging and command logging. The percentage of data logging versus command logging becomes a tuning knob between the performance of transaction processing and recovery to meet different OLTP requirements, and a model is proposed to guide such tuning. Our experimental study compares the performance of our proposed adaptive logging, ARIES-style data logging and command logging on top of H-Store. The results show that adaptive logging can achieve a 10x boost for recovery and a transaction throughput that is comparable to that of command logging.

Due to the "curse of dimensionality" problem, it is very expensive to process the nearest neighbor (NN) query in high-dimensional spaces; and hence, approximate approaches, such as Locality-Sensitive Hashing (LSH), are widely used for their theoretical guarantees and empirical performance. Current LSH-based approaches target at the L1 and L2 spaces, while as shown in previous work, the fractional distance metrics (Lp metrics with 0 < p < 1) can provide more insightful results than the usual L1 and L2 metrics for data mining and multimedia applications. However, none of the existing work can support multiple fractional distance metrics using one index. In this paper, we propose LazyLSH that answers approximate nearest neighbor queries for multiple Lp metrics with theoretical guarantees. Different from previous LSH approaches which need to build one dedicated index for every query space, LazyLSH uses a single base index to support the computations in multiple Lp spaces, significantly reducing the maintenance overhead. Extensive experiments show that LazyLSH provides more accurate results for approximate kNN search under fractional distance metrics.

This paper presents a project called KnowIng camera prototype SyStem (KISS) for real-time places-of-interest (POI) recognition and annotation for smartphone photos, with the availability of online geotagged images for POIs as our knowledge base. We propose a “Spatial+Visual” (S+V) framework which consists of a probabilistic field-of-view (pFOV) model in the spatial phase and sparse coding similarity metric in the visual phase to recognize phone-captured POIs. Moreover, we put forward an offline Collaborative Salient Area (COSTAR) mining algorithm to detect common visual features (called Costars) among the noisy photos geotagged on each POI, thus to clean the geotagged image database. The mining result can be utilized to annotate the region-of-interest on the query image during the online query processing. Besides, this mining procedure also improves the efficiency and accuracy of the S+V framework. Furthermore, we extend the pFOV model into a Bayesian FOV($\beta$FOV) model which improves the spatial recognition accuracy by more than 30 percent and also further alleviates visual computation. From a bayesian point of view, the likelihood of a certain POI being captured by phones is a prior probability in pFOV model which is represented as a posterior probability in$\beta$FOV model.Our experiments in the real-world and Oxford 5K datasets show promising recognition results. In order to provide a fine-grained annotation ground truth, we labeled a new dataset based on Oxford 5K and make it public available on the web. Our COSTAR mining techniqueoutperforms state-of-the-art approach on both dataset.

Various big data management systems have emerged to handle different types of applications, which cast very different demands on storage, indexing and retrieval of large amount of data on distributed file system. Such diversity on demands has raised huge challenges to the design of new generation of data access service for big data. In this paper, we present PABIRS, a unified data access middleware to support mixed workloads. PABIRS encapsulates the underlying distributed file system (DFS) and provides a unified access interface to systems such as MapReduce and key-value stores. PABIRS achieves dramatic improvement on efficiency by employing a novel hybrid indexing scheme. Based on the data distribution, the indexing scheme adaptively builds bitmap index and Log Structured Merge Tree (LSM) index. Moreover, PABIRS distributes the computation to multiple index nodes and utilizes a Pregel-based algorithm to facilitate parallel data search and retrieval. We empirically evaluate PABIRS against other existing distributed data processing systems and verify the huge advantages of PABIRS on shorter response time, higher throughput and better scalability, over big data with real-life phone logs and TPC-H benchmark.

In this paper, we present FGSS (Fashion Glasses Search System), an innovative cross-scenario eyeglasses retrieval system which automatically recognizes eyeglasses in real-world photos, e.g. the photo of a fashion girl with a stylish pair of eyeglasses, and retrieves a ranking list of visually similar product instances from the database. We propose a novel segmentation-free framework for FGSS to bridge two search gaps, semantic gap and feature gap, where a new type of keypoint-based scheme called EGYPT is tailored for eyeglasses to facilitate the search. In the EGYPT, we use the hybrid descriptors which combine the shape, color and texture features as a feature representation for eyeglasses. The experimental study on the real-world photo dataset and eyeglasses product dataset demonstrates the effectiveness of EGYPT model.

The solid-state hybrid drive (SSHD) incorporates a small NAND flash memory into a hard drive, resulting in an integrated device with combined Hard Disk Drive (HDD ) and Solid State Disk (SSD) storage. By identifying the data highly associated with the performance and buffering them in the SSD part, SSHD can deliver a better performance than the standard hard drive. However, that requires a significant redesign for existing data processing systems. In this paper, we examine the problem of efficiently processing relational data using MapReduce on a cluster using SSHDs as the underlying storage devices. We present the design of Hybrid MapReduce (HM ), a column-oriented MapReduce system, which adopts different storage layout, query optimizer, data index, and compression algorithm from previous MapReduce systems. In HM, the Distributed File System (DFS ) is deployed on SSHDs, and data layout (how data chunks are disseminated to HDDs and SSDs) plays a key role for the performance. Hence, an approximate algorithm is used to tune the data layout adaptively to maximize the query performance. We evaluate HM using TPC-H benchmark and the results show that with our new design, the hybrid system can provide a similar performance as the SSD-only system.

This paper presents a project called Knowing Camera for real-time recognizing and annotating places-of-interest(POI) in smartphone photos, with the availability of online geotagged images of such places. We propose a`"Spatial+Visual" (S+V) framework which consists of a probabilistic field-of-view model in the spatial phase and sparse coding similarity metric in the visual phase to recognize phone-captured POIs. Moreover, we put forward an offline Collaborative Salient Area (COSTAR) mining algorithm to detect common visual features (called Costars) among the noisy photos geotagged on each POI, thus to clean the geotagged image database. The mining result can be utilized to annotate the region-of-interest on the query image during the online query processing. Besides, this mining procedure further improves the efficiency and accuracy of the S+V framework. Our experiments in the real-world and Oxford 5K datasets show promising recognition and annotation performances of the proposed approach, and that the proposed COSTAR mining technique outperforms state-of-the-art approach.

The Big Data problem is characterized by the so called 3V features: Volume - a huge amount of data, Velocity - a high data ingestion rate, and Variety - a mix of structured data, semi-structured data, and unstructured data. The state-of-the-art solutions to the Big Data problem are largely based on the MapReduce framework (aka its open source implementation Hadoop). Although Hadoop handles the data volume challenge successfully, it does not deal with the data variety well since the programming interfaces and its associated data processing model is inconvenient and inefficient for handling structured data and graph data. This paper presents epiC , an extensible system to tackle the Big Data's data variety challenge. epiC introduces a general Actor-like concurrent programming model, independent of the data processing models, for specifying parallel computations. Users process multi-structured datasets with appropriate epiC extensions, the implementation of a data processing model best suited for the data type and auxiliary code for mapping that data processing model into epiC 's concurrent programming model. Like Hadoop, programs written in this way can be automatically parallelized and the runtime system takes care of fault tolerance and inter-machine communications. We present the design and implementation of epiC 's concurrent programming model. We also present two customized data processing model, an optimized MapReduce extension and a relational model, on top of epiC. Experiments demonstrate the effectiveness and efficiency of our proposed epiC.

MapReduce has become the state-of-the-art for data parallel processing. Nevertheless, Hadoop, an open-source equivalent of MapReduce, has been noted to have sub-optimal performance in the database context since it is initially designed to operate on raw data without utilizing any type of indexes. To alleviate the problem, we present ScalaGiST - scalable generalized search tree that can be seamlessly integrated with Hadoop, together with a cost-based data access optimizer for efficient query processing at run-time. ScalaGiST provides extensibility in terms of data and query types, hence is able to support unconventional queries (e.g., multi-dimensional range and k -NN queries) in MapReduce systems, and can be dynamically deployed in large cluster environments for handling big users and data. We have built ScalaGiST and demonstrated that it can be easily instantiated to common B + -tree and R-tree indexes yet for dynamic distributed environments. Our extensive performance study shows that ScalaGiST can provide efficient write and read performance, elastic scaling property, as well as effective support for MapReduce execution of ad-hoc analytic queries. Performance comparisions with recent proposals of specialized distributed index structures, such as SpatialHadoop, Data Mapping, and RT-CAN further confirm its efficiency.

YZStack is our developing solution which implements many well-established big data techniques as selectable modules and allows users to customize their systems as a process of module selection. In particular, it includes an openstack based IaaS (Infrastructure as a Service) layer, a distributed file system based DaaS (Data as a Service) layer, a PaaS (Platform as a Service) layer equipped with parallel processing techniques and a SaaS (Software as a Service) layer with popular data analytic algorithms. Layers of YZStack are loosely connected, so that customization of one layer does not affect the other layers and their interactions. In this paper, we use a smart financial system developed for the Zhejiang Provincial Department of Finance to demonstrate how to leverage YZStack to speed up the implementation of big data system. We also introduce two popular applications of the financial system, economic prediction and detection of improper payment.

Creating an efficient and economic trip plan is the most annoying job for a backpack traveler. Although travel agency can provide some predefined itineraries, they are not tailored for each specific customer. Previous efforts address the problem by providing an automatic itinerary planning service, which organizes the points-of-interests (POIs) into a customized itinerary. Because the search space of all possible itineraries is too costly to fully explore, to simplify the complexity, most work assume that user's trip is limited to some important POIs and will complete within one day. To address the above limitation, in this paper, we design a more general itinerary planning service, which generates multiday itineraries for the users. In our service, all POIs are considered and ranked based on the users' preference. The problem of searching the optimal itinerary is a team orienteering problem (TOP), a well-known NP-complete problem. To reduce the processing cost, a two-stage planning scheme is proposed. In its preprocessing stage, single-day itineraries are precomputed via the MapReduce jobs. In its online stage, an approximate search algorithm is used to combine the single day itineraries. In this way, we transfer the TOP problem with no polynomial approximation into another NP-complete problem (set-packing problem) with good approximate algorithms. Experiments on real data sets show that our approach can generate high-quality itineraries efficiently.

The corporate network is often used for sharing information among the participating companies and facilitating collaboration in a certain industry sector where companies share a common interest. It can effectively help the companies to reduce their operational costs and increase the revenues. However, the inter-company data sharing and processing poses unique challenges to such a data management system including scalability, performance, throughput, and security. In this paper, we present BestPeer++, a system which delivers elastic data sharing services for corporate network applications in the cloud based on BestPeer - a peer-to-peer (P2P) based data management platform. By integrating cloud computing, database, and P2P technologies into one system, BestPeer++ provides an economical, flexible and scalable platform for corporate network applications and delivers data sharing services to participants based on the widely accepted pay-as-you-go business model. We evaluate BestPeer++ on Amazon EC2 Cloud platform. The benchmarking results show that BestPeer++ outperforms HadoopDB, a recently proposed large-scale data processing system, in performance when both systems are employed to handle typical corporate network workloads. The benchmarking results also demonstrate that BestPeer++ achieves near linear scalability for throughput with respect to the number of peer nodes.

In crowdsourcing database, human operators are embedded into the database engine and collaborate with other conventional database operators to process the queries. Each human operator publishes small HITs (Human Intelligent Task) to the crowdsourcing platform, which consists of a set of database records and corresponding questions for human workers. The human workers complete the HITs and return the results to the crowdsourcing database for further processing. In practice, published records in HITs may contain sensitive attributes, probably causing privacy leakage so that malicious workers could link them with other public databases to reveal individual private information. Conventional privacy protection techniques, such asK-Anonymity, can be applied to partially solve the problem. However, after generalizing the data, the result of standard K-Anonymity algorithms may render uncontrollable information loss and affects the accuracy of crowdsourcing. In this paper, we first study the tradeoff between the privacy and accuracy for the human operator within data anonymization process. A probability model is proposed to estimate the lower bound and upper bound of the accuracy for general K-Anonymity approaches. We show that searching the optimal anonymity approach is NP-Hard and only heuristic approach is available. The second contribution of the paper is a general feedback-based K-Anonymity scheme. In our scheme, synthetic samples are published to the human workers, the results of which are used to guide the selection on anonymity strategies. We apply the scheme on Mondrian algorithm by adaptively cutting the dimensions based on our feedback results on the synthetic samples. We evaluate the performance of the feedback-based approach on U.S. census dataset, and show that given a predefined$K$, our proposal outperforms standard K-Anonymity approaches on retaining the effectiveness of crowdsourcing.

The amount of data managed in today's Cloud systems has reached an unprecedented scale. In order to speed up query processing, an effective mechanism is to build indexes on attributes that are used in query predicates. However, conventional indexing schemes fail to provide a scalable service: as the size of these indexes are proportional to the data size, it is not space efficient to build many indexes. As such, it becomes more crucial to develop effective index to provide scalable database services in the Cloud. In this paper, we propose a compact bitmap indexing scheme for a large-scale data store. The bitmap indexing scheme combines state-of-the-art bitmap compression techniques, such as WAH encoding and bit-sliced encoding. To further reduce the index cost, a novel and query efficient partial indexing technique is adopted, which dynamically refreshes the index to handle updates and process queries. The intuition of our indexing approach is to maximize the number of indexed attributes, so that a wider range of queries, including range and join queries, can be efficiently supported. Our indexing scheme is light-weight and its creation can be seamlessly grafted onto the MapReduce processing engine without incurring significant running cost. Moreover, the compactness allows us to maintain the bitmap indexes in memory so that performance overhead of index access is minimal. We implement our indexing scheme on top of the underlying Distributed File System (DFS) and evaluate its performance on an in-house cluster. We compare our index-based query processing with HadoopDB to show its superior performance. Our experimental results confirm the effectiveness, efficiency and scalability of the indexing scheme.

Most crowdsourcing systems leverage the public platforms, such as Amazon Mechanical Turk (AMT), to publish their jobs and collect the results. They are charged for using the platform's service and they are also required to pay the workers for each successful job. Although the average wage of the online human worker is not high, for a 24×7 running service, the crowdsourcing system becomes very expensive to maintain. We observe that there are, in fact, many sources that can provide free online human volunteers. Microblogging system is one of the most promising human resources. In this paper, we present our CrowdAnswer system, which is built on top of Weibo, the largest microblogging system in China. CrowdAnswer is a question-answering system, which distributes various questions to different groups of microblogging users adaptively. The answers are then collected from those users' tweets and visualized for the question originator. CrowdAnswer maintains a virtual credit system. The users need credits to publish questions and they can gain credits by answering the questions. A novel algorithm is proposed to route the questions to the interested users, which tries to maximize the probability of successfully answering a question.

This paper presents a framework called Knowing Camera for real-time recognizing places-of-interest in smartphone photos, with the availability of online geotagged images of such places. We propose a probabilistic field-of-view model which captures the uncertainty in camera sensor data. This model can be used to retrieve a set of candidate images. The visual similarity computation of the candidate images relies on the sparse coding technique. We also propose an ANN filtering technique to speedup the sparse coding. The final ranking combines an uncertain geometric relevance with the visual similarity. Our preliminary experiments conducted in an urban area of a large city show promising results. The most distinguishing feature of our framework is its ability to perform well in contaminated, real-world online image database. Besides, our framework is highly scalable as it does not incur any complex data structure.

The corporate network is often used for sharing information among the participating companies and facilitating collaboration in a certain industry sector where companies share a common interest. It can effectively help the companies to reduce their operational costs and increase the revenues. However, the inter-company data sharing and processing poses unique challenges to such a data management system including scalability, performance, throughput, and security. In this paper, we present Best Peer++, a system which delivers elastic data sharing services for corporate network applications in the cloud based on Best Peer -- a peer-to-peer (P2P) based data management platform. By integrating cloud computing, database, and P2P technologies into one system, Best Peer++ provides an economical, flexible and scalable platform for corporate network applications and delivers data sharing services to participants based on the widely accepted pay-as-you-go business model. We evaluate Best Peer++ on Amazon EC2 Cloud platform. The benchmarking results show that Best Peer++ outperforms Hadoop DB, a recently proposed large-scale data processing system, in performance when both systems are employed to handle typical corporate network workloads. The benchmarking results also demonstrate that Best Peer++ achieves near linear scalability for throughput with respect to the number of peer nodes.

The abundance of Web 2.0 resources in various media formats calls for better resource integration to enrich user experience. This naturally leads to a new cross-modal resource search requirement, in which a query is a resource in one modal and the results are closely related resources in other modalities. With cross-modal search, we can better exploit existing resources. Tags associated with Web 2.0 resources are intuitive medium to link resources with different modality together. However, tagging is by nature an ad hoc activity. They often contain noises and are affected by the subjective inclination of the tagger. Consequently, linking resources simply by tags will not be reliable. In this paper, we propose an approach for linking tagged resources to concepts extracted from Wikipedia, which has become a fairly reliable reference over the last few years. Compared to the tags, the concepts are therefore of higher quality. We develop effective methods for cross-modal search based on the concepts associated with resources. Extensive experiments were conducted, and the results show that our solution achieves good performance.

Some complex problems, such as image tagging and natural language processing, are very challenging for computers, where even state-of-the-art technology is yet able to provide satisfactory accuracy. Therefore, rather than relying solely on developing new and better algorithms to handle such tasks, we look to the crowdsourcing solution -- employing human participation -- to make good the shortfall in current technology. Crowdsourcing is a good supplement to many computer tasks. A complex job may be divided into computer-oriented tasks and human-oriented tasks, which are then assigned to machines and humans respectively. To leverage the power of crowdsourcing, we design and implement a Crowdsourcing Data Analytics System, CDAS. CDAS is a framework designed to support the deployment of various crowdsourcing applications. The core part of CDAS is a quality-sensitive answering model, which guides the crowdsourcing engine to process and monitor the human tasks. In this paper, we introduce the principles of our quality-sensitive model. To satisfy user required accuracy, the model guides the crowdsourcing query engine for the design and processing of the corresponding crowdsourcing jobs. It provides an estimated accuracy for each generated result based on the human workers' historical performances. When verifying the quality of the result, the model employs an online strategy to reduce waiting time. To show the effectiveness of the model, we implement and deploy two analytics jobs on CDAS, a twitter sentiment analytics job and an image tagging job. We use real Twitter and Flickr data as our queries respectively. We compare our approaches with state-of-the-art classification and image annotation techniques. The results show that the human-assisted methods can indeed achieve a much higher accuracy. By embedding the quality-sensitive model into crowdsourcing query engine, we effectively reduce the processing cost while maintaining the required query answer quality.

MapReduce has been widely recognized as an efficient tool for large-scale data analysis. It achieves high performance by exploiting parallelism among processing nodes while providing a simple interface for upper-layer applications. Some vendors have enhanced their data warehouse systems by integrating MapReduce into the systems. However, existing MapReduce-based query processing systems, such as Hive, fall short of the query optimization and competency of conventional database systems. Given an SQL query, Hive translates the query into a set of MapReduce jobs sentence by sentence. This design assumes that the user can optimize his query before submitting it to the system. Unfortunately, manual query optimization is time consuming and difficult, even to an experienced database user or administrator. In this paper, we propose a query optimization scheme for MapReduce-based processing systems. Specifically, we embed into Hive a query optimizer which is designed to generate an efficient query plan based on our proposed cost model. Experiments carried out on our in-house cluster confirm the effectiveness of our query optimizer.

Cloud computing represents a paradigm shift driven by the increasing demand of Web based applications for elastic, scalable and efficient system architectures that can efficiently support their ever-growing data volume and large-scale data analysis. A typical data management system has to deal with real-time updates by individual users, and as well as periodical large scale analytical processing, indexing, and data extraction. While such operations may take place in the same domain, the design and development of the systems have somehow evolved independently for transactional and periodical analytical processing. Such a system-level separation has resulted in problems such as data freshness as well as serious data storage redundancy. Ideally, it would be more efficient to apply ad-hoc analytical processing on the same data directly. However, to the best of our knowledge, such an approach has not been adopted in real implementation. Intrigued by such an observation, we have designed and implemented epiC, an elastic power-aware data-itensive Cloud platform for supporting both data intensive analytical operations (ref. as OLAP) and online transactions (ref. as OLTP). In this paper, we present ES2- the elastic data storage system of epiC, which is designed to support both functionalities within the same storage. We present the system architecture and the functions of each system component, and experimental results which demonstrate the efficiency of the system.

Real-time search dictates that new contents be made available for search immediately following their creation. From the database perspective, this requirement may be quite easily met by creating an up-to-date index for the contents and measuring search quality by the time gap between insertion time and availability of the index. This approach, however, poses new challenges for micro-blogging systems where thousands of concurrent users may upload their micro-blogs or tweets simultaneously. Due to the high update and query loads, conventional approaches would either fail to index the huge amount of newly created contents in real time or fall short of providing a scalable indexing service.

To achieve high reliability and scalability, most large-scale data warehouse systems have adopted the cluster-based architecture. In this paper, we propose the design of a new cluster-based data warehouse system, LLama, a hybrid data management system which combines the features of row-wise and column-wise database systems. In Llama, columns are formed into correlation groups to provide the basis for the vertical partitioning of tables. Llama employs a distributed file system (DFS) to disseminate data among cluster nodes. Above the DFS, a MapReduce-based query engine is supported. We design a new join algorithm to facilitate fast join processing. We present a performance study on TPC-H dataset and compare Llama with Hive, a data warehouse infrastructure built on top of Hadoop. The experiment is conducted on EC2. The results show that Llama has an excellent load performance and its query performance is significantly better than the traditional MapReduce framework based on row-wise storage.

In corporate networks, daily business data are generated in gigabytes or even terabytes. It is costly to process aggregate queries in those systems. In this paper, we propose PACA, a probably approximately correct aggregate query processing scheme, for answering aggregate queries in structured Peer-to-Peer (P2P) network. PACA retrieves random samples from peers' databases and applies the samples to process queries. Instead of scanning the entire database of each peer, PACA only accesses a small random number of data. Moreover, based on the query distribution,PACA publishes a precomputed synopsis and uses the synopsis to answer future queries. Most queries are expected to be answered by the precomputed synopsis partially or fully. And the synopsis is adaptively tuned to follow the query distribution. Experiments on the PlanetLab show the effectiveness of the approach.

Providing scalable database services is an essential requirement for extending many existing applications of the Cloud platform. Due to the diversity of applications, database services on the Cloud must support large-scale data analytical jobs and high concurrent OLTP queries. Most existing work focuses on some specific type of applications. To provide an integrated framework, we are designing a new system, epiC, as our solution to next-generation database systems. In epiC, indexes play an important role in improving overall performance. Different types of indexes are built to provide efficient query processing for different applications.

In this paper, we propose an online aggregation system called COSMOS (Continuous Sampling for Multiple queries in an Online aggregation System), to process multiple aggregate queries efficiently. In COSMOS, a dataset is first scrambled so that sequentially scanning the dataset gives rise to a stream of random samples for all queries. Moreover, COSMOS organizes queries into a dissemination graph to exploit the dependencies across queries. In this way, aggregates of queries closer to the root (source of data flow) can potentially be used to compute the aggregates of descendent/dependent queries. COSMOS applies some statistical approach to combine answers from ancestor nodes to generate the online aggregates for a node. COSMOS also offers a partitioning strategy to further salvage intermediate answers. We have implemented COSMOS and conducted an extensive experimental study in PostgreSQL. Our results on the TPC-H benchmark show the efficiency and effectiveness of COSMOS.

MapReduce has been widely used for large-scale data analysis in the Cloud. The system is well recognized for its elastic scalability and fine-grained fault tolerance although its performance has been noted to be suboptimal in the database context. According to a recent study [19], Hadoop, an open source implementation of MapReduce, is slower than two state-of-the-art parallel database systems in performing a variety of analytical tasks by a factor of 3.1 to 6.5. MapReduce can achieve better performance with the allocation of more compute nodes from the cloud to speed up computation; however, this approach of "renting more nodes" is not cost effective in a pay-as-you-go environment. Users desire an economical elastically scalable data processing system, and therefore, are interested in whether MapReduce can offer both elastic scalability and efficiency. In this paper, we conduct a performance study of MapReduce (Hadoop) on a 100-node cluster of Amazon EC2 with various levels of parallelism. We identify five design factors that affect the performance of Hadoop, and investigate alternative but known methods for each factor. We show that by carefully tuning these factors, the overall performance of Hadoop can be improved by a factor of 2.5 to 3.5 for the same benchmark used in [19], and is thus more comparable to that of parallel database systems. Our results show that it is therefore possible to build a cloud data processing system that is both elastically scalable and efficient.

A Cloud may be seen as a type of flexible computing infrastructure consisting of many compute nodes, where resizable computing capacities can be provided to different customers. To fully harness the power of the Cloud, efficient data management is needed to handle huge volumes of data and support a large number of concurrent end users. To achieve that, a scalable and high-throughput indexing scheme is generally required. Such an indexing scheme must not only incur a low maintenance cost but also support parallel search to improve scalability. In this paper, we present a novel, scalable B + -tree based indexing scheme for efficient data processing in the Cloud. Our approach can be summarized as follows. First, we build a local B + -tree index for each compute node which only indexes data residing on the node. Second, we organize the compute nodes as a structured overlay and publish a portion of the local B + -tree nodes to the overlay for efficient query processing. Finally, we propose an adaptive algorithm to select the published B + -tree nodes according to query patterns. We conduct extensive experiments on Amazon's EC2, and the results demonstrate that our indexing scheme is dynamic, efficient and scalable.

Traditionally, distributed databases assume that the (small) set of nodes participating in a query is known apriori, the data is well placed, and the statistics are readily available. However, these assumptions are no longer valid in a peer-based database management system (PDBMS). As such, it is a challenge to process and optimize queries in a PDBMS. In this paper, we present our distributed solution to this problem for multi-way join queries. Our approach first processes a multi-way join query based on an initial query evaluation plan (generated using statistical data that may be obsolete or inaccurate); as the query is being processed, statistics obtained on-the-fly are used to (continuously) refine the current plan dynamically into a more effective one. We have conducted an extensive performance study which shows that our adaptive query processing strategy can reduce the network traffic significantly.

In many decision making applications, users typically issue aggregate queries. To evaluate these computationally expensive queries, online aggregation has been developed to provide approximate answers (with their respective confidence intervals) quickly, and to continuously refine the answers. In this paper, we extend the online aggregation technique to a distributed context where sites are maintained in a DHT (Distributed Hash Table) network. Our Distributed Online Aggregation (DoA) scheme iteratively and progressively produces approximate aggregate answers as follows: in each iteration, a small set of random samples are retrieved from the data sites and distributed to the processing sites; at each processing site, a local aggregate is computed based on the allocated samples; at a coordinator site, these local aggregates are combined into a global aggregate. DoA adaptively grows the number of processing nodes as the sample size increases. To further reduce the sampling overhead, the samples are retained as a precomputed synopsis over the network to be used for processing future queries. We also study how these synopsis can be maintained incrementally. We have conducted extensive experiments on PlanetLab. The results show that our DoA scheme reduces the initial waiting time significantly and provides high quality approximate answers with running confidence intervals progressively.

Structured peer-to-peer (P2P) overlays have been successfully employed in many applications to locate content. However, they have been less effective in handling massive amounts of data because of the high overhead of maintaining indexes. In this paper, we propose PISCES, a Peer-based system that Indexes Selected Content for Efficient Search. Unlike traditional approaches that index all data, PISCES identifies a subset of tuples to index based on some criteria (such as query frequency, update frequency, index cost, etc.). In addition, a coarse-grained range index is built to facilitate the processing of queries that cannot be fully answered by the tuple-level index. More importantly, PISCES can adaptively self-tune to optimize the subset of tuples to be indexed. That is, the (partial) index in PISCES is built in a Just-In-Time (JIT) manner. Beneficial tuples for current users are pulled for indexing while indexed tuples with infrequent access and high maintenance cost are discarded. We also introduce a light-weight monitoring scheme for structured networks to collect the necessary statistics. We have conducted an extensive experimental study on PlanetLab to illustrate the feasibility, practicality and efficiency of PISCES. The results show that PISCES incurs lower maintenance cost and offers better search and query efficiency compared to existing methods.