Background : Sedentary behavior (SB) is a risk factor for cardiometabolic disease. Existing cut points of hip-worn accelerometers to quantify SB underestimate sedentary bout durations by ignoring posture. To address this, we previously developed Convolutional Neural Network Hip Accelerometer Posture (CHAP), a deep-learning algorithm that predicts sitting and breaks from sitting. In this study, we applied CHAP to a randomized controlled trial to externally validate its accuracy for classifying sitting versus nonsitting and estimating intervention-related changes in SB. Methods : CHAP was applied to 30-Hz triaxial hip-worn ActiGraph-GT3X+ (AG) accelerometer data from free-living postmenopausal women who are overweight (≥55 years) in the Rise for Health RCT ( n = 406). CHAP-predicted SB accuracy (e.g., sensitivity) and daily pattern metrics (e.g., total sedentary time) were compared with a ground-truth device activPAL (AP) and standard cut-point method (AG100) at two timepoints for intervention arms—Healthy Living (control), Reduce Sitting, and Increase Transitions. Results : CHAP’s SB accuracy metrics were above 84.8%. Mean (standard error, p values) intervention effect estimates (mean change, intervention minus controls) from generalized estimating equation models for (a) total sedentary time were AP 65.1 min/day (16.2, p < .001), CHAP 38.2 min/day (15.4, p = .013), and AG100 0.28 min/day (13.9, p = .98; Reduce Sitting); (b) breaks from SB were AP 22/day (4.3, p < .001), CHAP 4/day (1.5, p = .003), and AG100 <1/day (2.1, p = .860; Increase Transitions). Conclusions : This study validated CHAP on an independent cohort. CHAP exhibited high prediction accuracy, and although less sensitive than AP, CHAP detected changes in SB more effectively than AG100. Thus, CHAP could make a strong contribution to SB intervention research.

Modern data applications increasingly involve heterogeneous data managed in different models and stored across disparate database engines, often deployed as separate installs. Limited research has addressed cross-model query processing in federated environments. This paper takes a step toward bridging this gap by: (1) formally defining a class of cross-model join queries between a graph store and a relational store by proposing a unified algebra; (2) introducing one real-world benchmark and four semi-synthetic benchmarks to evaluate such queries; and (3) proposing a lightweight middleware, MICRO, for efficient query execution. At the core of MICRO is CMLero, a learning-to-rank-based query optimizer that selects efficient execution plans without requiring exact cost estimation. By avoiding the need to materialize or convert all data into a single model, which is often infeasible due to third-party data control or cost, MICRO enables native querying across heterogeneous systems. Experimental results on the benchmark workloads demonstrate that MICRO outperforms the state-of-the-art federated relational system XDB by up to 2.1x in total runtime across the full test set. On the 93 test queries of real-world benchmark, 14 queries achieve over 100 speedup, including 4 queries with more than 100x speedup; however, 4 queries experienced slowdowns of over 5 seconds, highlighting opportunities for future improvement of MICRO. Further comparisons show that CMLero consistently outperforms rule-based and regression-based optimizers, highlighting the advantage of learning-to-rank in complex cross-model optimization.

Large Language Models (LLMs) have become the standard for natural language interfaces to databases, but their effectiveness can be limited by context window constraints, especially for databases with large schemas. Schema subsetting or linking, which is the task of reducing the schema information provided to the LLM, has emerged as a strategy to address these limitations, yet its impact on NL-to-SQL performance remains unclear, particularly for very large schemas. In this paper, we systematically evaluate 7 real-world schema subsetting modules across 3 contemporary NL-to-SQL benchmarks, including Bird, Spider 2, and SNAILS, and we introduce BigBird—an expansion of the Bird benchmark datasets that provides additional data for evaluating subsetting of large schemas. We also introduce new subsetting-specific performance and efficiency metrics that enable in-depth evaluation of subsetting methods. Our analysis aligns with other recent work that suggests that most subsetting methods actually degrade NL-to-SQL execution accuracy from between 3% -10% (model and method dependent) on smaller schemas, but also reveals that some subsetting methods can improve NL-to-SQL execution accuracy by up to 2% - 7% and others reduce token usage while generally maintaining the same execution accuracy performance as full-schema representations on large schemas. We also present SKALPEL, a prototype hybrid subsetting method that combines LLM-based question decomposition with semantic search, suggesting the potential for reduced token usage in NL-to-SQL workflows. These findings clarify the trade-offs of schema subsetting and motivate future research on scalable schema linking for large databases.

Accurate detection of sedentary behavior is important for studying health risks related to prolonged sitting, but posture-based classification remains challenging with wearable sensors, especially at the wrist. We study whether a deep learning model trained on hip-worn accelerometer data can transfer to wrist-worn accelerometer data for sitting versus non-sitting classification. We use CHAP, a CNN-BiLSTM model originally developed for hip accelerometers, and evaluate its zero-shot performance on wrist data as well as its adaptation through finetuning with varying amounts of labeled wrist data. Experiments are conducted on the iWatch dataset with ground-truth posture labels derived from wearable cameras. The hip-trained model performs strongly on hip data without retraining, but accuracy drops on wrist data due to sensor placement shift. Finetuning CHAP provides consistent advantages over transformer models trained from scratch. These findings suggest that hip-based pretraining provides a useful starting point for wrist deployment, while highlighting the need for wrist-specific adaptation to handle higher signal variability.

On October 19 and 20, 2023, the authors of this report convened in Cambridge, MA, to discuss the state of the database research field, its recent accomplishments and ongoing challenges, and future directions for research and community engagement. This gathering continues a long standing tradition in the database community, dating back to the late 1980s, in which researchers meet roughly every five years to produce a forward looking report. This report summarizes the key takeaways from our discussions. We begin with a retrospective on the academic, open source, and commercial successes of the community over the past five years. We then turn to future opportunities, with a focus on core data systems, particularly in the context of cloud computing and emerging hardware, as well as on the growing impact of data science, data governance, and generative AI. This document is not intended as an exhaustive survey of all technical challenges or industry innovations in the field. Rather, it reflects the perspectives of senior community members on the most pressing challenges and promising opportunities ahead.

Large Language Models (LLMs) have revolutionized Natural Language to SQL (NL-to-SQL), dominating most NL-to-SQL benchmarks. But LLMs still face limitations due to hallucinations, semantic ambiguity, and lexical mismatches between an NL query and the database schema. Naturally, a lot of work in the ML+DB intersection aims to mitigate such LLM limitations. In this work, we shine the light on a complementary data-centric question: How should DB schemas evolve in this era of LLMs to boost NL-to-SQL? The intuition is that more NL-friendly schema identifiers can help LLMs work better with DBs. We dive deeper into this seemingly obvious, but hitherto underexplored and important, connection between schema identifier ''naturalness'' and the behavior of LLM-based NL-to-SQL by creating a new integrated benchmark suite we call SNAILS. SNAILS has 4 novel artifacts: (1) A collection of real-world DB schemas not present in prior NL-to-SQL benchmarks; (2) A set of labeled NL-SQL query pairs on our collection not seen before by public LLMs; (3) A notion of naturalness level for schema identifiers and a novel labeled dataset of modified identifiers; and (4) AI artifacts to automatically modify identifier naturalness. Using SNAILS, we perform a comprehensive empirical evaluation of the impact of schema naturalness on LLM-based NL-to-SQL accuracy, and present a method for improving LLM-based NL-to-SQL with natural views. Our results reveal statistically significant correlations across multiple public LLMs from OpenAI, Meta, and Google on multiple databases using both zero-shot prompting as well as more complex NL-to-SQL workflows: DIN SQL, and CodeS. We present several fine-grained insights and discuss pathways for DB practitioners to better exploit LLMs for NL-to-SQL.

This paper provides a comprehensive overview of Natural Language Processing (NLP), a field at the intersection of computer science, artificial intelligence, and linguistics. It explores the core concepts, techniques, and algorithms employed in NLP, covering areas such as text processing, language modeling, machine translation, sentiment analysis, and question answering. The paper also delves into the diverse applications of NLP across various industries, highlighting its transformative impact on how humans interact with technology. Finally, it discusses current challenges and future research directions within the dynamic landscape of NLP. This paper also addresses the challenges NLP faces, including bias mitigation, contextual understanding, and ethical considerations. As NLP continues to evolve, it paves the way for enhanced human collaboration, breaking language barriers, and redefining creative and educational landscapes.

The high-profile success of Deep Learning (DL) at Big Tech companies, including recent Large Language Models (LLMs) such as the GPT and Llama families, has led to high demand among Web companies, consumer app companies, enterprises, healthcare, domain sciences, and even digital humanities and arts to adopt modern DL for their applications. The scale of DL workloads, domain- specific datasets, and publicly available pre-trained base models keeps growing. Naturally, tackling issues of scalability, usability, and resource/cost efficiency of DL systems are critical to democratizing modern DL-powered AI. We find that some key lessons from the decades of work on data system design, implementation, and optimization-when adapted prudently-can go a long way toward that goal. Specifically, our work shows that new analogues of multi-query optimization for DL systems can substantially reduce runtimes and costs, while improving ease of use. This article lays out how we reimagine DL workloads that way and summarizes the technical contributions powering this transformation.

Data analytics applications today often require processing heterogeneous data from different data models, including relational, graph, and text data, for more holistic analytics. While query optimization for single data models, especially relational data, has been studied for decades, there is surprisingly little work on query optimization for cross-model data analytics. Cross-model query optimization can benefit from the long line of prior work in query optimization in the relational realm, wherein cost-based and/or machine learning-based (ML-based) optimizers are common. Both approaches require a large and diverse set of query workloads to measure, tune, and evaluate a query optimizer. To the best of our knowledge, there are still no large public cross-model benchmark workloads, a significant obstacle for systems researchers in this space. In this paper, we take a step toward filling this research gap by generating new query workloads spanning relational and graph data, which are ubiquitous in analytics applications. Our approach leverages large language models (LLMs) via different prompting strategies to generate queries and proposes new rule-based post-processing methods to ensure query correctness. We evaluate the pros and cons of each strategy and perform an in-depth analysis by categorizing the syntactic and semantic errors of the generated queries. So far, we have produced over 4000 correct cross-model queries, the largest set ever. Our code, prompts, data, and query workloads will all be released publicly.

Background: There exist few maximal oxygen uptake (VO2max) non-exercise-based prediction equations, fewer using machine learning (ML), and none specifically for older adults. Since direct measurement of VO2max is infeasible in large epidemiologic cohort studies, we sought to develop, validate, compare, and assess the transportability of several ML VO2max prediction algorithms. Methods: The Baltimore Longitudinal Study of Aging (BLSA) participants with valid VO2max tests were included (n = 1080). Least absolute shrinkage and selection operator, linear- and tree-boosted extreme gradient boosting, random forest, and support vector machine (SVM) algorithms were trained to predict VO2max values. We developed these algorithms for: (a) the overall BLSA, (b) by sex, (c) using all BLSA variables, and (d) variables common in aging cohorts. Finally, we quantified the associations between measured and predicted VO2max and mortality. Results: The age was 69.0 ± 10.4 years (mean ± SD) and the measured VO2max was 21.6 ± 5.9 mL/kg/min. Least absolute shrinkage and selection operator, linear- and tree-boosted extreme gradient boosting, random forest, and support vector machine yielded root mean squared errors of 3.4 mL/kg/min, 3.6 mL/kg/min, 3.4 mL/kg/min, 3.6 mL/kg/min, and 3.5 mL/kg/min, respectively. Incremental quartiles of measured VO2max showed an inverse gradient in mortality risk. Predicted VO2max variables yielded similar effect estimates but were not robust to adjustment. Conclusion: Measured VO2max is a strong predictor of mortality. Using ML can improve the accuracy of prediction as compared to simpler approaches but estimates of association with mortality remain sensitive to adjustment. Future studies should seek to reproduce these results so that VO2max, an important vital sign, can be more broadly studied as a modifiable target for promoting functional resiliency and healthy aging.

The tedious grunt work involved in data preparation (prep) before ML reduces ML user productivity. It is also a roadblock to industrial-scale cloud AutoML workflows that build ML models for millions of datasets. One important data prep step for ML is cleaning duplicates in the Categorical columns, e.g., deduplicating CA with California in a State column. However, how such Categorical duplicates impact ML is ill-understood as there exist almost no in-depth scientific studies to assess their significance. In this work, we take the first step towards empirically characterizing the impact of Categorical duplicates on ML classification with a three-pronged approach. We first study how Categorical duplicates exhibit themselves by creating a labeled dataset of 1262 Categorical columns. We then curate a downstream benchmark suite of 16 real-world datasets to make observations on the effect of Categorical duplicates on five popular classifiers and five encoding mechanisms. We finally use simulation studies to validate our observations. We find that Logistic Regression and Similarity encoding are more robust to Categorical duplicates than two One-hot encoded high-capacity classifiers. We provide actionable takeaways that can potentially help AutoML developers to build better platforms and ML practitioners to reduce grunt work. While some of the presented insights have remained folklore for practitioners, our work presents the first systematic scientific study to analyze the impact of Categorical duplicates on ML and put this on an empirically rigorous footing. Our work presents novel data artifacts and benchmarks, as well as novel empirical analyses to spur more research on this topic.

We study the task of spoken natural language to SQL parsing (speech-to-SQL), where the goal is to map a spoken utterance to the corresponding SQL. A simple way to develop a speech-to-SQL parser is to pass the speech to an automatic speech recognition (ASR) system, and pass the transcription to a text-to-SQL parser. However, ASR is still error-prone. We propose an ASR correction method, DBATI (DataBase-Aware TaggerILM). The method first detects erroneous spans in the input, and rewrites each span. Our method leverages a novel joint representation of text and the database (DB). Our experiments show that our method yields better performance on both text quality and downstream SQL accuracy, compared to existing ASR error correction methods.

Recent advances in Graph Neural Networks (GNNs) have changed the landscape of modern graph analytics. The complexity of GNN training and the scalability challenges have also sparked interest from the systems community, with efforts to build systems that provide higher efficiency and schemes to reduce costs. However, we observe that many such systems basically "reinvent the wheel" of much work done in the database world on scalable graph analytics engines. Further, they often tightly couple the scalability treatments of graph data processing with that of GNN training, resulting in entangled complex problems and systems that often do not scale well on one of those axes. In this paper, we ask a fundamental question: How far can we push existing systems for scalable graph analytics and deep learning (DL) instead of building custom GNN systems? Are compromises inevitable on scalability and/or runtimes? We propose Lotan, the first scalable and optimized data system for full -batch GNN training with decoupled scaling that bridges the hitherto siloed worlds of graph analytics systems and DL systems. Lotan offers a series of technical innovations, including re -imagining GNN training as query plan-like dataflows, execution plan rewriting, optimized data movement between systems, a GNN-centric graph partitioning scheme, and the first known GNN model batching scheme. We prototyped Lotan on top of GraphX and PyTorch. An empirical evaluation using several real-world benchmark GNN workloads reveals a promising nuanced picture: Lotan significantly surpasses the scalability of state-of-the-art custom GNN systems, while often matching or being only slightly behind on time -to -accuracy metrics in some cases. We also show the impact of our system optimizations. Overall, our work shows that the GNN world can indeed benefit from building on top of scalable graph analytics engines. Lotan's new level of scalability can also empower new ML -oriented research on ever-larger graphs and GNNs.

Data science applications increasingly rely on heterogeneous data sources and analytics. This has led to growing interest in polystore systems, especially analytical polystores. In this work, we focus on a class of emerging multi-data model analytics workloads that fluidly straddle relational, graph, and text analytics. Instead of a generic polystore, we build a ``tri-store'' system that is more aware of the underlying data models to better optimize execution to improve scalability and runtime efficiency. We name our system AWESOME (Analytics WorkbEnch for SOcial MEdia). It features a powerful domain-specific language named ADIL. ADIL builds on top of underlying query engines (e.g., SQL and Cypher) and features native data types for succinctly specifying cross-engine queries and NLP operations, as well as automatic in-memory and query optimizations. Using real-world tri-model analytical workloads and datasets, we empirically demonstrate the functionalities of AWESOME for scalable data science applications and evaluate its efficiency.

Large models such as GPT-3 and ChatGPT have transformed deep learning (DL), powering applications that have captured the public's imagination. Such models must be trained on multiple GPUs due to their size and computational load, driving the development of a bevy of "model parallelism" techniques and tools. Navigating such parallelism choices, however, is a new burden for DL users such as data scientists, domain scientists, etc., who may lack the necessary systems knowhow. The need for model selection , which leads to many models to train due to hyper-parameter tuning or layer-wise finetuning, compounds the situation with two more burdens: resource apportioning and scheduling. In this work, we unify these three burdens by formalizing them as a joint problem that we call SPASE: Select a Parallelism, Allocate resources, and Schedule. We propose a new information system architecture to tackle the SPASE problem holistically, exploiting the performance opportunities presented by joint optimization. We devise an extensible template for existing parallelism schemes and combine it with an automated empirical profiler for runtime estimation. We then formulate SPASE as an MILP. We find that direct use of an MILP-solver is significantly more effective than several baseline heuristics. We optimize the system runtime further with an introspective scheduling approach. We implement all these techniques into a new data system we call Saturn. Experiments with benchmark DL workloads show that Saturn achieves 39-49% lower model selection runtimes than current DL practice.

In this paper, we propose Saturn, a new data system to improve the efficiency of multi-large-model training (e.g., during model selection/hyperparameter optimization). We first identify three key interconnected systems challenges for users building large models in this setting -- parallelism technique selection, distribution of GPUs over jobs, and scheduling. We then formalize these as a joint problem, and build a new system architecture to tackle these challenges simultaneously. Our evaluations show that our joint-optimization approach yields 39-49% lower model selection runtimes than typical current DL practice.

As part of the International Conference on Very Large Data Bases (VLDB) 2021 / Proceedings of the VLDB Endowment Volume 14, a new Research Track category named Scalable Data Science (SDS) was launched [2, 6]. The goal of SDS is to attract cutting-edge and impactful real-world work in the scalable data science arena to enhance the impact and visibility of the VLDB community on data science practice, spur new technical connections, and inspire new follow-on research. The inaugural year proved to be successful, with numerous interesting papers from a wide cross section of both industry and academia, spanning several data science topics, and originating from several countries around the world. In this report, we reflect on the inaugural year of SDS with some statistics on both submissions and accepted papers, SDS invited talks, and our observations, lessons, and tips as inaugural Associate Editors for SDS. We hope this article is helpful to future authors, reviewers, and organizers of SDS, as well as other interested members of the wider database / data management community and beyond.

Diversity and Inclusion (D&I) are core to fostering innovative thinking. Existing theories demonstrate that to facilitate inclusion, multiple types of exclusionary dynamics, such as self-segregation, communication apprehension, and stereotyping and stigmatizing, must be overcome [11]. A diverse group of people tends to surface different perspectives, which help to understand and address D&I. Fostering D&I in research communities must address issues related to inclusive interpersonal and small group dynamics, rules and codes of conduct, increasing diversity in under-represented groups and disciplines, and organizing D&I events, and longterm efforts to champion change [15].