{"total":132,"rows":[{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2205.15466","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","created":"2022-05-30","cited_by_count":132,"area":null},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2305.00054","title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms","created":"2023-04-28","cited_by_count":69,"area":null},{"id":"2306.10577","title":"OpenDataVal: a Unified Benchmark for Data Valuation","created":"2023-06-18","cited_by_count":55,"area":null},{"id":"2304.07718","title":"Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value","created":"2023-04-16","cited_by_count":38,"area":null},{"id":"2209.13429","title":"WeightedSHAP: analyzing and improving Shapley based feature attributions","created":"2022-09-27","cited_by_count":36,"area":null},{"id":"2211.06800","title":"CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification","created":"2022-11-13","cited_by_count":32,"area":null},{"id":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32,"area":null},{"id":"2103.11109","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2405.03875","title":"Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits","created":"2024-05-06","cited_by_count":29,"area":null},{"id":"2305.12081","title":"MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement","created":"2023-05-20","cited_by_count":24,"area":null},{"id":"2306.10165","title":"Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values","created":"2023-06-16","cited_by_count":21,"area":null},{"id":"2401.15866","title":"Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution","created":"2024-01-29","cited_by_count":21,"area":null},{"id":"2308.15709","title":"Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation","created":"2023-08-30","cited_by_count":19,"area":null},{"id":"2108.07915","title":"Data Pricing in Machine Learning Pipelines","created":"2021-08-18","cited_by_count":18,"area":null},{"id":"2401.11103","title":"Efficient Data Shapley for Weighted Nearest Neighbor Algorithms","created":"2024-01-20","cited_by_count":18,"area":null},{"id":"2410.04555","title":"$\\texttt{dattri}$: A Library for Efficient Data Attribution","created":"2024-10-06","cited_by_count":18,"area":null},{"id":"2204.11131","title":"Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines","created":"2022-04-23","cited_by_count":17,"area":null},{"id":"2304.01811","title":"HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2311.05304","title":"Data Valuation and Detections in Federated Learning","created":"2023-11-09","cited_by_count":17,"area":null},{"id":"2210.16835","title":"Variance reduced Shapley value estimation for trustworthy data valuation","created":"2022-10-30","cited_by_count":16,"area":null},{"id":"2307.02460","title":"Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources","created":"2023-07-05","cited_by_count":16,"area":null},{"id":"2402.08922","title":"The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes","created":"2024-02-14","cited_by_count":16,"area":null},{"id":"2507.05261","title":"TokenShapley: Token Level Context Attribution with Shapley Value","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2306.02071","title":"DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation","created":"2023-06-03","cited_by_count":12,"area":null},{"id":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2512.19363","title":"From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samples","created":"2025-12-22","cited_by_count":12,"area":null},{"id":"2304.04258","title":"A Note on \"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms\"","created":"2023-04-09","cited_by_count":11,"area":null},{"id":"2310.08782","title":"Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning","created":"2023-10-13","cited_by_count":11,"area":null},{"id":"2404.01676","title":"Incentives in Private Collaborative Machine Learning","created":"2024-04-02","cited_by_count":10,"area":null},{"id":"2405.03869","title":"Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2106.04384","title":"FL-Market: Trading Private Models in Federated Learning","created":"2021-06-08","cited_by_count":9,"area":null},{"id":"2311.13712","title":"Data Acquisition: A New Frontier in Data-centric AI","created":"2023-11-22","cited_by_count":9,"area":null},{"id":"2206.00511","title":"Differentially Private Shapley Values for Data Evaluation","created":"2022-06-01","cited_by_count":8,"area":null},{"id":"2106.05484","title":"A Unified Framework for Task-Driven Data Quality Management","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2303.01928","title":"Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values","created":"2023-03-03","cited_by_count":7,"area":null},{"id":"2306.10473","title":"2D-Shapley: A Framework for Fragmented Data Valuation","created":"2023-06-18","cited_by_count":7,"area":null},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2209.05424","title":"Towards More Efficient Data Valuation in Healthcare Federated Learning using Ensembling","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2212.00630","title":"Probably Approximate Shapley Fairness with Applications in Machine Learning","created":"2022-12-01","cited_by_count":6,"area":null},{"id":"2310.18970","title":"TRIAGE: Characterizing and auditing training data for improved regression","created":"2023-10-29","cited_by_count":6,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2402.01943","title":"Precedence-Constrained Winter Value for Effective Graph Data Valuation","created":"2024-02-02","cited_by_count":6,"area":null},{"id":"2403.13893","title":"DAVED: Data Acquisition via Experimental Design for Data Markets","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2407.15247","title":"TimeInf: Time Series Data Contribution via Influence Functions","created":"2024-07-21","cited_by_count":6,"area":null},{"id":"2104.11843","title":"One-Round Active Learning","created":"2021-04-23","cited_by_count":5,"area":null},{"id":"2304.10701","title":"GMValuator: Similarity-based Data Valuation for Generative Models","created":"2023-04-21","cited_by_count":5,"area":null},{"id":"2410.04386","title":"Data Distribution Valuation","created":"2024-10-06","cited_by_count":5,"area":null},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2406.11730","title":"CHG Shapley: Efficient Data Valuation and Selection towards Trustworthy Machine Learning","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2410.00759","title":"Targeted synthetic data generation for tabular data via hardness characterization","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2205.11518","title":"LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2302.04418","title":"Learning to Select Pivotal Samples for Meta Re-weighting","created":"2023-02-09","cited_by_count":3,"area":null},{"id":"2410.07523","title":"DemoShapley: Valuation of Demonstrations for In-Context Learning","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2507.16872","title":"CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2508.14648","title":"Understanding Data Influence with Differential Approximation","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2602.00329","title":"In-Run Data Shapley for Adam Optimizer","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2111.12545","title":"ModelPred: A Framework for Predicting Trained Model from Training Data","created":"2021-11-24","cited_by_count":2,"area":null},{"id":"2301.08824","title":"An Automated Vulnerability Detection Framework for Smart Contracts","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2402.04409","title":"Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learning","created":"2024-02-06","cited_by_count":2,"area":null},{"id":"2402.06030","title":"Game-theoretic Counterfactual Explanation for Graph Neural Networks","created":"2024-02-08","cited_by_count":2,"area":null},{"id":"2402.09288","title":"EcoVal: An Efficient Data Valuation Framework for Machine Learning","created":"2024-02-14","cited_by_count":2,"area":null},{"id":"2404.10758","title":"Watch Your Step: Optimal Retrieval for Continual Learning at Scale","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2405.13699","title":"Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posterior","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2406.04257","title":"Data Measurements for Decentralized Data Markets","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.02461","title":"Decentralized Intelligence Network (DIN)","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2407.17854","title":"Shapley Value-based Contrastive Alignment for Multimodal Information Extraction","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2407.19373","title":"Uncertainty Quantification of Data Shapley via Statistical Inference","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2411.09776","title":"Combining Machine Learning Defenses without Conflicts","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2412.01460","title":"A Comprehensive Study of Shapley Value in Data Analytics","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2502.04763","title":"Shapley Value Approximation Based on k-Additive Games","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2503.06602","title":"FW-Shapley: Real-time Estimation of Weighted Shapley Values","created":"2025-03-09","cited_by_count":2,"area":null},{"id":"2504.05563","title":"Do Data Valuations Make Good Data Prices?","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2504.16668","title":"Efficient Data Valuation Approximation in Federated Learning: A Sampling-based Approach","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2505.19013","title":"Faithful Group Shapley Value","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2506.05281","title":"Fast-DataShapley: Neural Modeling for Training Data Valuation","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2510.16007","title":"Layer-Aware Influence for Online Data Valuation Estimation","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2305.01660","title":"Data valuation: The partial ordinal Shapley value for machine learning","created":"2023-05-02","cited_by_count":1,"area":null},{"id":"2305.20002","title":"Representer Point Selection for Explaining Regularized High-dimensional Models","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2402.08209","title":"Thresholding Data Shapley for Data Cleansing Using Multi-Armed Bandits","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2404.19591","title":"Towards Interactively Improving ML Data Preparation Code via \"Shadow Pipelines\"","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2406.01130","title":"SAVA: Scalable Learning-Agnostic Data Valuation","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2406.02612","title":"Is Data Valuation Learnable and Interpretable?","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2406.11010","title":"WeShap: Weak Supervision Source Evaluation with Shapley Values","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2407.19469","title":"Interpretable Triplet Importance for Personalized Ranking","created":"2024-07-28","cited_by_count":1,"area":null},{"id":"2408.01365","title":"Data Debugging is NP-hard for Classifiers Trained with SGD","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2409.04407","title":"Exploiting Missing Data Remediation Strategies using Adversarial Missingness Attacks","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2411.00388","title":"Towards Data Valuation via Asymmetric Data Shapley","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2411.00745","title":"Private, Augmentation-Robust and Task-Agnostic Data Valuation Approach for Data Marketplace","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2412.04158","title":"LossVal: Efficient Data Valuation for Neural Networks","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2502.04554","title":"Unifying and Optimizing Data Values for Selection via Sequential Decision-Making","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2502.06574","title":"On the Impact of the Utility in Semivalue-based Data Valuation","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2505.08198","title":"SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2506.01290","title":"Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2506.12619","title":"Semivalue-based data valuation is arbitrary and gameable","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2506.23799","title":"KAIROS: Scalable Model-Agnostic Data Valuation","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2509.12386","title":"Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2510.12383","title":"Towards Cross-Modal Error Detection with Tables and Images","created":"2025-10-14","cited_by_count":1,"area":null}],"next_cursor":"100"}