Mostafa Milani

Dr. Mostafa Milani

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 May 2024 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
APAlireza Pirhadi
Alireza Pirhadi
MMMohammad Hossein Moslemi
Mohammad Hossein Moslemi
ACAlexander Cloninger
Alexander Cloninger
MMMostafa Milani
Mostafa Milani
BSBabak Salimi
Babak Salimi
Ensuring Conditional Independence (CI) constraints is pivotal for the development of fair and trustworthy machine learning models. In this paper, we introduce OTClean, a framework that harnesses optimal transport theory for data repair under CI constraints. Optimal transport theory provides a rigorous framework for measuring the discrepancy between probability distributions, thereby ensuring control over data utility. We formulate the data repair problem concerning CIs as a Quadratically Constrained Linear Program (QCLP) and propose an alternating method for its solution. However, this approach faces scalability issues due to the computational cost associated with computing optimal transport distances, such as the Wasserstein distance. To overcome these scalability challenges, we reframe our problem as a regularized optimization problem, enabling us to develop an iterative algorithm inspired by Sinkhorn's matrix scaling algorithm, which efficiently addresses high-dimensional and large-scale data. Through extensive experiments, we demonstrate the efficacy and efficiency of our proposed methods, showcasing their practical utility in real-world data cleaning and preprocessing tasks. Furthermore, we provide comparisons with traditional approaches, highlighting the superiority of our techniques in terms of preserving data utility while ensuring adherence to the desired CI constraints.

1 December 2020 in Information Systems
Verified
Journal Article
Closed access
YHYu Huang
Yu Huang
MMMostafa Milani
Mostafa Milani
FCFei Chiang
Fei Chiang

30 November 2021 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
MMMostafa Milani
Mostafa Milani
YHYu Huang
Yu Huang
FCFei Chiang
Fei Chiang
Recent privacy legislation has aimed to restrict and control the amount of personal data published by companies and shared with third parties. Much of this real data is not only sensitive requiring anonymization but also contains characteristic details from a variety of individuals. This diversity is desirable in many applications ranging from Web search to drug and product development. Unfortunately, data anonymization techniques have largely ignored diversity in its published result. This inadvertently propagates underlying bias in subsequent data analysis. We study the problem of finding a diverse anonymized data instance where diversity is measured via a set of diversity constraints. We formalize diversity constraints, and study their fundamental problems of satisfiability, implication, and validation. We show that determining the existence of a diverse, anonymized instance can be done in PTIME, and we present a clustering-based algorithm, along with optimizations to improve performance. We conduct extensive experiments using real and synthetic data showing the effectiveness of our techniques, and improvement over existing baselines. Our work aligns with recent trends towards responsible data science by coupling diversity with privacy-preserving data publishing.

9 June 2024
Verified
Conference Paper
Open access
MMMohammad Hossein Moslemi
Mohammad Hossein Moslemi
MMMostafa Milani
Mostafa Milani
Entity Matching (EM) is a critical task in numerous fields, such as healthcare, finance, and public administration, as it identifies records that refer to the same entity within or across different databases. EM faces considerable challenges, particularly with false positives and negatives. These are typically addressed by generating matching scores and apply thresholds to balance false positives and negatives in various contexts.However, adjusting these thresholds can affect the fairness of the outcomes, a critical factor that remains largely overlooked in current fair EM research. The existing body of research on fair EM tends to concentrate on static thresholds, neglecting their critical impact on fairness. To address this, we introduce a new approach in EM using recent metrics for evaluating biases in score-based binary classification, particularly through the lens of distributional parity. This approach enables the application of various bias metrics—like equalized odds, equal opportunity, and demographic parity—without depending on threshold settings. Our experiments with leading matching methods reveal potential biases, and by applying a calibration technique for EM scores using Wasserstein barycenters, we not only mitigate these biases but also preserve accuracy across real-world datasets. This paper contributes to the field of fairness in data cleaning, especially within EM, which is a central task in data cleaning, by promoting a method for generating matching scores that reduce biases across different thresholds.

10 April 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
OAOmar AlOmeir
Omar AlOmeir
ELEugenie Y. Lai
Eugenie Y. Lai
MMMostafa Milani
Mostafa Milani
RPRachel Pottinger
Rachel Pottinger
Data provenance is any information about the origin of a piece of data and the process that led to its creation. Most database provenance work has focused on creating models and semantics to query and generate this provenance information. While comprehensive, provenance information remains large and overwhelming, making it hard for data provenance systems to support data exploration. We present a new approach to provenance exploration that builds on data summarization techniques. We contribute novel summarization schemes for the provenance of aggregation queries and techniques for the fast generation of these summarization schemes. We introduce two types of summaries for aggregate queries. Impact summaries take into account the impact of specific groups of tuples in the provenance of the query on an aggregate result, and comparative summaries allow users to compare the provenance of two aggregate results. We also present algorithms for efficient computation of these summaries, implement optimizations using data sampling and feature selection, and conduct experiments and a user survey to show the feasibility and relevance of our approaches.

14 October 2024 in arXiv
Verified
Preprint
Open access
PDF file
ARAnanya Rahaman
Ananya Rahaman
AZAnny Zheng
Anny Zheng
MMMostafa Milani
Mostafa Milani
FCFei Chiang
Fei Chiang
RPRachel Pottinger
Rachel Pottinger
The rise of large language models (LLMs) has significantly impacted various domains, including natural language processing (NLP) and image generation, by making complex computational tasks more accessible. While LLMs demonstrate impressive generative capabilities, there is an ongoing debate about their level of "understanding," particularly in structured domains like SQL. In this paper, we evaluate the extent to which LLMs "understand" SQL by testing them on a series of key SQL tasks. These tasks, such as syntax error detection, missing token identification, query performance prediction, query equivalence checking, and query explanation, assess the models' proficiency in recognition, context awareness, semantics, and coherence, which are essential skills for SQL understanding. We generate labeled datasets from well-known workloads, and evaluate the latest LLMs, focusing on how query complexity and syntactic features influence performance. Our results indicate that while GPT4 excels at tasks requiring recognition and context, all models struggle with deeper semantic understanding and coherence, especially in query equivalence and performance estimation, revealing the limitations of current LLMs in achieving full SQL comprehension.