Locality sensitive hashing (LSH) is a widely used technique for approximate nearest neighbor search (ANNS). In an LSH-based solution for ANNS, the computation of query-to-data (Q2D) distances accounts for a considerable fraction of the query time, but such distance information is thrown away after nearest neighbors are identified. In this paper, we propose CanDE (Candidate-based Distribution Estimation), a lightweight add-on to LSH that reuses such information for a wide range of analytics tasks including Q2D distance distribution estimation (QDDE), kernel density estimation (KDE), and query-time recall estimation (QTRE). This allows for significant savings in indexing costs and query time for multiple tasks associated with the original query.The main technical hurdle that CanDE addresses is the accurate estimation of some important statistics of the dataset via importance sampling. We discover that the existing estimators of these statistics are not accurate, because they approximate the actual number of collisions (called collision rate) in the LSH index using the theoretical collision probability (of the LSH function family), and this approximation is crude. To address this issue, we propose more accurate estimators based on a novel scheme called inferred collision rate (ICR), which gives a much better approximation to the actual collision rate. Furthermore, we propose an efficient algorithm for computing ICR from the nearest neighbor candidates returned by ANNS. Our evaluation shows that CanDE outperforms existing solutions on multiple analytics tasks while adding only about 8% to 19% query time overhead to ANNS.

Many data analytics systems store and process large datasets in partitions containing millions of rows. By mapping rows to partitions in an optimized way, it is possible to improve query performance by skipping over large numbers of irrelevant partitions during query processing. This mapping is referred to as a data layout. Recent works have shown that customizing the data layout to the anticipated query workload greatly improves query performance, but the performance benefits may disappear if the workload changes. Reorganizing data layouts to accommodate workload drift can resolve this issue, but reorganization costs could exceed query savings if not done carefully. In this paper, we present an algorithmic framework OReO that makes online reorganization decisions to balance the benefits of improved query performance with the costs of reorganization. Our framework extends results from Metrical Task Systems to provide a tight bound on the worst-case performance guarantee for online reorganization, without prior knowledge of the query workload. Through evaluation on real-world datasets and query workloads, our experiments demonstrate that online reorganization with OReO can lead to an up to 32% improvement in combined query and reorganization time compared to using a single, optimized data layout for the entire workload.

Localizing video moments based on the movement patterns of objects is an important task in video analytics. Existing video analytics systems offer two types of querying interfaces based on natural language and SQL, respectively. However, both types of interfaces have major limitations. SQL-based systems require high query specification time, whereas natural language-based systems require large training datasets to achieve satisfactory retrieval accuracy. To address these limitations, we present SketchQL, a video database management system (VDBMS) for offline, exploratory video moment retrieval that is both easy to use and generalizes well across multiple video moment datasets. To improve ease-of-use, SketchQL features a visual query interface that enables users to sketch complex visual queries through intuitive drag-and-drop actions. To improve generalizability, SketchQL operates on object-tracking primitives that are reliably extracted across various datasets using pre-trained models. We present a learned similarity search algorithm for retrieving video moments closely matching the user's visual query based on object trajectories. SketchQL trains the model on a diverse dataset generated with a novel simulator, that enhances its accuracy across a wide array of datasets and queries. We evaluate SketchQL on four real-world datasets with nine queries, demonstrating its superior usability and retrieval accuracy over state-of-the-art VDBMSs.

Biased data can lead to unfair machine learning models, highlighting the importance of embedding fairness at the beginning of data analysis, particularly during dataset curation and labeling. In response, we propose Falcon, a scalable fair active learning framework. Falcon adopts a data-centric approach that improves machine learning model fairness via strategic sample selection. Given a user-specified group fairness measure, Falcon identifies samples from "target groups" (e.g., (attribute=female, label=positive)) that are the most informative for improving fairness. However, a challenge arises since these target groups are defined using ground truth labels that are not available during sample selection. To handle this, we propose a novel trial-and-error method, where we postpone using a sample if the predicted label is different from the expected one and falls outside the target group. We also observe the trade-off that selecting more informative samples results in higher likelihood of postponing due to undesired label prediction, and the optimal balance varies per dataset. We capture the trade-off between informativeness and postpone rate as policies and propose to automatically select the best policy using adversarial multi-armed bandit methods, given their computational efficiency and theoretical guarantees. Experiments show that Falcon significantly outperforms existing fair active learning approaches in terms of fairness and accuracy and is more efficient. In particular, only Falcon supports a proper trade-off between accuracy and fairness where its maximum fairness score is 1.8--4.5x higher than the second-best results.

In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface. This novel interface allows users to specify object trajectory events with simple mouse drag-and-drop operations. Users can use trajectories of single objects as building blocks to compose complex events. Using a pre-trained model that encodes trajectory similarity, SketchQL achieves zero-shot video moments retrieval by performing similarity searches over the video to identify clips that are the most similar to the visual query. In this demonstration, we introduce the graphic user interface of SketchQL and detail its functionalities and interaction mechanisms. We also demonstrate the end-to-end usage of SketchQL from query composition to video moments retrieval using real-world scenarios.

In this demonstration, we present VCR, an automated slice discovery method (SDM) for object detection models that helps practitioners identify and explain specific scenarios in which their models exhibit systematic errors. VCR leverages the capabilities of vision foundation models to generate segment-level visual concepts that serve as interpretable explanation primitives. By integrating these visual concepts with additional image metadata in a tabular format, VCR uses a scalable frequent itemset mining-based technique to identify common patterns associated with model performance. We will demonstrate VCR's capabilities through three usage scenarios. First, users can explore the automatically extracted visual concepts and their associated labels. Second, users can run slice finding on a large object detection dataset and visually inspect the results to discover systematic errors. Finally, users can iteratively refine their slicing results by providing feedback on the granularity of visual concepts and the quality of the generated labels. These scenarios will illustrate how VCR can aid practitioners in discovering non-trivial gaps in their models' performance, providing actionable insights for model improvement.

Data preprocessing is a crucial step in the machine learning process that transforms raw data into a more usable format for downstream ML models. However, it can be costly and time-consuming, often requiring the expertise of domain experts. Existing automated machine learning (AutoML) frameworks claim to automate data preprocessing. However, they often use a restricted search space of data preprocessing pipelines which limits the potential performance gains, and they are often too slow as they require training the ML model multiple times. In this paper, we propose DiffPrep, a method that can automatically and efficiently search for a data preprocessing pipeline for a given tabular dataset and a differentiable ML model such that the performance of the ML model is maximized. We formalize the problem of data preprocessing pipeline search as a bi-level optimization problem. To solve this problem efficiently, we transform and relax the discrete, non-differential search space into a continuous and differentiable one, which allows us to perform the pipeline search using gradient descent with training the ML model only once. Our experiments show that DiffPrep achieves the best test accuracy on 15 out of the 18 real-world datasets evaluated and improves the model's test accuracy by up to 6.6 percentage points.

Cluster managers play a crucial role in data centers by distributing workloads among infrastructure resources. Declarative Cluster Management (DCM) is a new cluster management architecture that enables users to express placement policies declaratively using SQL-like queries. This paper presents our experiences in scaling this architecture from moderate-sized enterprise clusters (102- 103nodes) to hyperscale clusters (104nodes) via query optimization techniques. First, we formally specify the syntax and semantics of DCM's declarative language, C-SQL, a SQL variant used to express constraint optimization problems. We showcase how constraints on the desired state of the cluster system can be succinctly represented as C-SQL programs, and how query optimization techniques like incremental view maintenance and predicate pushdown can enhance the execution of C-SQL programs. We evaluate the effectiveness of our optimizations through a case study of building Kubernetes schedulers using C-SQL. Our optimizations demonstrated an almost 3000× speed up in database latency and reduced the size of optimization problems by as much as 1/300 of the original, without affecting the quality of the scheduling solutions.

In this demonstration, we will present EVA, an end-to-end AI-Relational database management system. We will demonstrate the capabilities and utility of EVA using three usage scenarios: (1) EVA serves as a backend for an exploratory video analytics interface developed using Streamlit and React, (2) EVA seamlessly integrates with the Python and Data Science ecosystems by allowing users to access EVA in a Python notebook alongside other popular libraries such as Pandas and Matplotlib, and (3) EVA facilitates bulk labeling with Label Studio, a widely-used labeling framework. By optimizing complex vision queries, we illustrate how EVA allows a wide range of application developers to harness the recent advances in computer vision.

In this work, we report on a novel application of Locality Sensitive Hashing (LSH) to seismic data at scale. Based on the high waveform similarity between reoccurring earthquakes, our application identifies potential earthquakes by searching for similar time series segments via LSH. However, a straightforward implementation of this LSH-enabled application has difficulty scaling beyond 3 months of continuous time series data measured at a single seismic station. As a case study of a data-driven science workflow, we illustrate how domain knowledge can be incorporated into the workload to improve both the efficiency and result quality. We describe several end-to-end optimizations of the analysis pipeline from pre-processing to post-processing, which allow the application to scale to time series data measured at multiple seismic stations. Our optimizations enable an over 100× speedup in the end-to-end analysis pipeline. This improved scalability enabled seismologists to perform seismic analysis on more than ten years of continuous time series data from over ten seismic stations, and has directly enabled the discovery of 597 new earthquakes near the Diablo Canyon nuclear power plant in California and 6123 new earthquakes in New Zealand.

As data volumes continue to rise, manual inspection is becoming increasingly untenable. In response, we present MacroBase, a data analytics engine that prioritizes end-user attention in high-volume fast data streams. MacroBase enables efficient, accurate, and modular analyses that highlight and aggregate important and unusual behavior, acting as a search engine for fast data. MacroBase is able to deliver order-of-magnitude speedups over alternatives by optimizing the combination of explanation (i.e., feature selection) and classification tasks and by leveraging a new reservoir sampler and heavy-hitters sketch specialized for fast data streams. As a result, MacroBase delivers accurate results at speeds of up to 2M events per second per query on a single core. The system has delivered meaningful results in production, including at a telematics company monitoring hundreds of thousands of vehicles.

As data volumes continue to rise, manual inspection is becoming increasingly untenable. In response, we present MacroBase, a data analytics engine that prioritizes end-user attention in high-volume fast data streams. MacroBase enables efficient, accurate, and modular analyses that highlight and aggregate important and unusual behavior, acting as a search engine for fast data. MacroBase is able to deliver order-of-magnitude speedups over alternatives by optimizing the combination of explanation and classification tasks and by leveraging a new reservoir sampler and heavy-hitters sketch specialized for fast data streams. As a result, MacroBase delivers accurate results at speeds of up to 2M events per second per query on a single core. The system has delivered meaningful results in production, including at a telematics company monitoring hundreds of thousands of vehicles.

Data volumes are rising at an increasing rate, stressing the limits of human attention. Current techniques for prioritizing user attention in this fast data are characterized by either cumbersome, ad-hoc analysis pipelines comprised of a diverse set of analytics tools, or brittle, static rule-based engines. To address this gap, we have developed MacroBase, a fast data analytics engine that acts as a search engine over fast data streams. MacroBase provides a set of highly-optimized, modular operators for streaming feature transformation, classification, and explanation. Users can leverage these optimized operators to construct efficient pipelines tailored for their use case. In this demonstration, SIGMOD attendees will have the opportunity to interactively answer and refine queries using MacroBase and discover the potential benefits of an advanced engine for prioritizing attention in high-volume, real-world data streams.

Time series visualization of streaming telemetry (i.e., charting of key metrics such as server load over time) is increasingly prevalent in modern data platforms and applications. However, many existing systems simply plot the raw data streams as they arrive, often obscuring large-scale trends due to small-scale noise. We propose an alternative: to better prioritize end users' attention, smooth time series visualizations as much as possible to remove noise, while retaining large-scale structure to highlight significant deviations. We develop a new analytics operator called ASAP that automatically smooths streaming time series by adaptively optimizing the trade-off between noise reduction (i.e., variance) and trend retention (i.e., kurtosis). We introduce metrics to quantitatively assess the quality of smoothed plots and provide an efficient search strategy for optimizing these metrics that combines techniques from stream processing, user interface design, and signal processing via autocorrelation-based pruning, pixel-aware preaggregation, and on-demand refresh. We demonstrate that ASAP can improve users' accuracy in identifying long-term deviations in time series by up to 38.4% while reducing response times by up to 44.3%. Moreover, ASAP delivers these results several orders of magnitude faster than alternative search strategies.