{"total":20,"rows":[{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116,"area":null},{"id":"2203.11852","title":"Representation Bias in Data: A Survey on Identification and Resolution Techniques","created":"2022-03-22","cited_by_count":37,"area":null},{"id":"2112.09745","title":"Interpretable Data-Based Explanations for Fairness Debugging","created":"2021-12-17","cited_by_count":30,"area":null},{"id":"2103.09055","title":"OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learning","created":"2021-03-13","cited_by_count":18,"area":null},{"id":"2203.04706","title":"Data Representativity for Machine Learning and AI Systems","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2402.12789","title":"Fairness Without Harm: An Influence-Guided Active Sampling Approach","created":"2024-02-20","cited_by_count":12,"area":null},{"id":"2307.02726","title":"Through the Fairness Lens: Experimental Analysis and Evaluation of Entity Matching","created":"2023-07-06","cited_by_count":9,"area":null},{"id":"2101.11358","title":"Detecting discriminatory risk through data annotation based on Bayesian inferences","created":"2021-01-27","cited_by_count":7,"area":null},{"id":"2402.01071","title":"Chameleon: Foundation Models for Fairness-aware Multi-modal Data Augmentation to Enhance Coverage of Minorities","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2204.06664","title":"Achieving Representative Data via Convex Hull Feasibility Sampling Algorithms","created":"2022-04-13","cited_by_count":2,"area":null},{"id":"2301.10319","title":"Designing Data: Proactive Data Collection and Iteration for Machine Learning","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2303.17566","title":"Non-Invasive Fairness in Learning through the Lens of Data Drift","created":"2023-03-30","cited_by_count":2,"area":null},{"id":"2212.09633","title":"Towards Assessing Data Bias in Clinical Trials","created":"2022-12-19","cited_by_count":1,"area":null},{"id":"2109.07908","title":"Auditing the Imputation Effect on Fairness of Predictive Analytics in Higher Education","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2209.06316","title":"Optimizing SLAM Evaluation Footprint Through Dynamic Range Coverage Analysis of Datasets","created":"2022-09-13","cited_by_count":0,"area":null},{"id":"2301.00719","title":"Detection of Groups with Biased Representation in Ranking","created":"2022-12-30","cited_by_count":0,"area":null},{"id":"2407.00170","title":"Dataset Representativeness and Downstream Task Fairness","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2408.01375","title":"Adaptive Recruitment Resource Allocation to Improve Cohort Representativeness in Participatory Biomedical Datasets","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2507.22186","title":"SourceSplice: Source Selection for Machine Learning Tasks","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2606.20461","title":"Data Bias Mitigation under Coverage Constraints & The Price of Fairness","created":"2026-06-18","cited_by_count":0,"area":null}],"next_cursor":null}