Anna Fariha

Rohan Bavishi, Harshit Joshi, José Pablo Cambronero Sánchez et al. · stanford

Most users of low-code platforms, such as Excel and PowerApps, write programs in domain-specific formula languages to carry out nontrivial tasks. Often users can write most of the program they want, but introduce small mistakes that yield broken formulas. These mistakes, which can be both syntactic and semantic, are hard for low-code users to identify and fix, even though they can be resolved with just a few edits. We formalize the problem of producing such edits as the last-mile repair problem. To address this problem, we developed LaMirage, a LAst-MIle RepAir-engine GEnerator that combines symbolic and neural techniques to perform last-mile repair in low-code formula languages. LaMirage takes a grammar and a set of domain-specific constraints/rules, which jointly approximate the target language, and uses these to generate a repair engine that can fix formulas in that language. To tackle the challenges of localizing the errors and ranking the candidate repairs, LaMirage leverages neural techniques, whereas it relies on symbolic methods to generate candidate repairs. This combination allows LaMirage to find repairs that satisfy the provided grammar and constraints, and then pick the most natural repair. We compare LaMirage to state-of-the-art neural and symbolic approaches on 400 real Excel and PowerFx formulas, where LaMirage outperforms all baselines. We release these benchmarks to encourage subsequent work in low-code domains.

Whanhee Cho, Kuangfei Long, Mahmood Jasim et al.

Selecting a bundle of items that collectively satisfies constraints is a fundamental task across databases, recommender systems, and text summarization. Unlike traditional retrieval that returns individual or top-k items, bundle retrieval is inherently combinatorial and, in general, NP-hard. Although package queries can efficiently retrieve bundles given a well-formed query, two key user-centric challenges remain: (1) expressing and tuning multi-dimensional bundle intent through a user-friendly interface, and (2) ensuring feasibility when the query yields empty results. We introduce Ex2Bundle, an Example-driven Bundle retrieval framework that enables users to specify their intent through example bundles and automatically synthesizes package queries that capture the intent implicit in those example bundles via aggregate constraints. Ex2Bundle also addresses a challenge unique to bundle retrieval: when inferred aggregate constraints are infeasible over the target data, our data-aware constraint relaxation minimally adjusts the constraint bounds while preserving alignment with user intent. We instantiate a specific application of focused text snippet extraction by example to demonstrate the efficacy of the Ex2Bundle framework. Extensive experiments over real-world datasets and a user study demonstrate that Ex2Bundle improves usability and consistently returns intent-aligned bundles even under distributional shifts of the target database.

Anirudh Kamath, Dustin Maas, Jacobus Van der Merwe et al.

Data wrangling continues to be the most time-consuming task in the data science pipeline and wireless network data is no exception. Prior approaches for automatic or assisted data-wrangling primarily target unordered, single-table data. However, unlike traditional datasets where rows in a table are unordered and assumed to be independent of each other, wireless network datasets are often collected across multiple measurement devices, producing multiple, temporally ordered tables that must be integrated for obtaining the complete dataset. For instance, to create a dataset of the signal quality of 5G cell towers within a geographic region, GPS data collected by cellphones must be joined with radio frequency measurements of the corresponding cell towers. However, the join key timestamp typically exhibits mismatched sampling periods, causing a misalignment. Data wrangling techniques for generic time-series datasets also fail here, since they lack knowledge of domain-specific data semantics, which are often defined by network protocols and system configurations. To aid in wrangling wireless network datasets, we demonstrate WN-Wrangle, an interactive wrangling assistant, tailored to the wireless network domain that suggests the top-k next-best wrangling operations, along with rich, domain-specific explanations. Under the hood, WN-Wrangle enforces temporal constraints- and a wireless network semantics-aware mechanism to score and rank an extended set of wrangling operators to improve the data quality. We demonstrate how WN-Wrangle identifies elusive data-quality issues specific to the wireless network domain and suggests accurate wrangling steps over datasets obtained from the widely used POWDER city-scale wireless testbed.

Rania Saber, Anna Fariha

This formative study investigates the impact of data quality on AI-assisted data visualizations, focusing on how uncleaned datasets influence the outcomes of these tools. By generating visualizations from datasets with inherent quality issues, the research aims to identify and categorize the specific visualization problems that arise. The study further explores potential methods and tools to address these visualization challenges efficiently and effectively. Although tool development has not yet been undertaken, the findings emphasize enhancing AI visualization tools to handle flawed data better. This research underscores the critical need for more robust, user-friendly solutions that facilitate quicker and easier correction of data and visualization errors, thereby improving the overall reliability and usability of AI-assisted data visualization processes.

Maliha Tashfia Islam, Anna Fariha, Alexandra Meliou et al.

Classification, a heavily-studied data-driven machine learning task, drives an increasing number of prediction systems involving critical human decisions such as loan approval and criminal risk assessment. However, classifiers often demonstrate discriminatory behavior, especially when presented with biased data. Consequently, fairness in classification has emerged as a high-priority research area. Data management research is showing an increasing presence and interest in topics related to data and algorithmic fairness, including the topic of fair classification. The interdisciplinary efforts in fair classification, with machine learning research having the largest presence, have resulted in a large number of fairness notions and a wide range of approaches that have not been systematically evaluated and compared. In this paper, we contribute a broad analysis of 13 fair classification approaches and additional variants, over their correctness, fairness, efficiency, scalability, robustness to data errors, sensitivity to underlying ML model, data efficiency, and stability using a variety of metrics and real-world datasets. Our analysis highlights novel insights on the impact of different metrics and high-level approach characteristics on different aspects of performance. We also discuss general principles for choosing approaches suitable for different practical settings, and identify areas where data-management-centric solutions are likely to have the most impact.

Anna Fariha, Lucy Cousins, Narges Mahyar et al.

Traditional data systems require specialized technical skills where users need to understand the data organization and write precise queries to access data. Therefore, novice users who lack technical expertise face hurdles in perusing and analyzing data. Existing tools assist in formulating queries through keyword search, query recommendation, and query auto-completion, but still require some technical expertise. An alternative method for accessing data is Query by Example (QBE), where users express their data exploration intent simply by providing examples of their intended data. We study a state-of-the-art QBE system called SQuID, and contrast it with traditional SQL querying. Our comparative user studies demonstrate that users with varying expertise are significantly more effective and efficient with SQuID than SQL. We find that SQuID eliminates the barriers in studying the database schema, formalizing task semantics, and writing syntactically correct SQL queries, and thus, substantially alleviates the need for technical expertise in data exploration.

Anna Fariha, Suman Nath, Alexandra Meliou

Runtime nondeterminism is a fact of life in modern database applications. Previous research has shown that nondeterminism can cause applications to intermittently crash, become unresponsive, or experience data corruption. We propose Adaptive Interventional Debugging (AID) for debugging such intermittent failures. AID combines existing statistical debugging, causal analysis, fault injection, and group testing techniques in a novel way to (1) pinpoint the root cause of an application's intermittent failure and (2) generate an explanation of how the root cause triggers the failure. AID works by first identifying a set of runtime behaviors (called predicates) that are strongly correlated to the failure. It then utilizes temporal properties of the predicates to (over)-approximate their causal relationships. Finally, it uses fault injection to execute a sequence of interventions on the predicates and discover their true causal relationships. This enables AID to identify the true root cause and its causal relationship to the failure. We theoretically analyze how fast AID can converge to the identification. We evaluate AID with six real-world applications that intermittently fail under specific inputs. In each case, AID was able to identify the root cause and explain how the root cause triggered the failure, much faster than group testing and more precisely than statistical debugging. We also evaluate AID with many synthetically generated applications with known root causes and confirm that the benefits also hold for them.