{"total":258,"rows":[{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2110.14049","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","created":"2021-10-26","cited_by_count":165,"area":null},{"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":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2202.05594","title":"The Shapley Value in Machine Learning","created":"2022-02-11","cited_by_count":98,"area":null},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"area":null},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2109.02053","title":"GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning","created":"2021-09-05","cited_by_count":74,"area":null},{"id":"2203.00870","title":"Faith-Shap: The Faithful Shapley Interaction Index","created":"2022-03-02","cited_by_count":69,"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":"2111.01872","title":"Towards Fairness-Aware Federated Learning","created":"2021-11-02","cited_by_count":58,"area":null},{"id":"2303.16520","title":"Fair Federated Medical Image Segmentation via Client Contribution Estimation","created":"2023-03-29","cited_by_count":52,"area":null},{"id":"2303.01179","title":"SHAP-IQ: Unified Approximation of any-order Shapley Interactions","created":"2023-03-02","cited_by_count":51,"area":null},{"id":"2206.10013","title":"Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments","created":"2022-06-20","cited_by_count":50,"area":null},{"id":"2304.12205","title":"Synthetic Datasets for Autonomous Driving: A Survey","created":"2023-04-24","cited_by_count":48,"area":null},{"id":"2111.11850","title":"Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective","created":"2021-11-20","cited_by_count":47,"area":null},{"id":"2306.09345","title":"Evaluating Data Attribution for Text-to-Image Models","created":"2023-06-15","cited_by_count":45,"area":null},{"id":"2103.03228","title":"One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning","created":"2021-03-04","cited_by_count":39,"area":null},{"id":"2207.04557","title":"Mechanisms that Incentivize Data Sharing in Federated Learning","created":"2022-07-10","cited_by_count":39,"area":null},{"id":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"area":null},{"id":"2106.15406","title":"A Comprehensive Survey of Incentive Mechanism for Federated Learning","created":"2021-06-27","cited_by_count":38,"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":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"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":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","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":"2104.08312","title":"Data Shapley Valuation for Efficient Batch Active Learning","created":"2021-04-16","cited_by_count":27,"area":null},{"id":"2207.04806","title":"Repairing Neural Networks by Leaving the Right Past Behind","created":"2022-07-11","cited_by_count":27,"area":null},{"id":"2105.15013","title":"SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning","created":"2021-05-31","cited_by_count":26,"area":null},{"id":"2101.02153","title":"The Shapley Value of Classifiers in Ensemble Games","created":"2021-01-06","cited_by_count":23,"area":null},{"id":"2206.09811","title":"Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search","created":"2022-06-20","cited_by_count":23,"area":null},{"id":"2210.01072","title":"Understanding Influence Functions and Datamodels via Harmonic Analysis","created":"2022-10-03","cited_by_count":23,"area":null},{"id":"2410.01917","title":"Provably Accurate Shapley Value Estimation via Leverage Score Sampling","created":"2024-10-02","cited_by_count":23,"area":null},{"id":"2109.09046","title":"Improving Fairness for Data Valuation in Horizontal Federated Learning","created":"2021-09-19","cited_by_count":22,"area":null},{"id":"2410.03055","title":"Permissive Information-Flow Analysis for Large Language Models","created":"2024-10-04","cited_by_count":22,"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":"2112.09327","title":"Incentivizing Collaboration in Machine Learning via Synthetic Data Rewards","created":"2021-12-17","cited_by_count":20,"area":null},{"id":"2208.12354","title":"Fundamentals of Task-Agnostic Data Valuation","created":"2022-08-25","cited_by_count":19,"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":"2201.02658","title":"Fair and efficient contribution valuation for vertical federated learning","created":"2022-01-07","cited_by_count":18,"area":null},{"id":"2311.10609","title":"Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks","created":"2023-11-17","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":"2404.13964","title":"An Economic Solution to Copyright Challenges of Generative AI","created":"2024-04-22","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":"2406.00569","title":"Redefining Contributions: Shapley-Driven Federated Learning","created":"2024-06-01","cited_by_count":17,"area":null},{"id":"2101.10572","title":"Transparent Contribution Evaluation for Secure Federated Learning on Blockchain","created":"2021-01-26","cited_by_count":16,"area":null},{"id":"2110.11589","title":"Text Counterfactuals via Latent Optimization and Shapley-Guided Search","created":"2021-10-22","cited_by_count":16,"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":"2205.07855","title":"Decentral and Incentivized Federated Learning Frameworks: A Systematic Literature Review","created":"2022-05-07","cited_by_count":15,"area":null},{"id":"2309.10979","title":"Towards Data-centric Graph Machine Learning: Review and Outlook","created":"2023-09-20","cited_by_count":15,"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":"2106.02310","title":"FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learning","created":"2021-06-04","cited_by_count":14,"area":null},{"id":"2304.02846","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","created":"2023-04-06","cited_by_count":14,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2107.06336","title":"Improving Cooperative Game Theory-based Data Valuation via Data Utility Learning","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2107.11927","title":"On Blame Attribution for Accountable Multi-Agent Sequential Decision Making","created":"2021-07-26","cited_by_count":13,"area":null},{"id":"2206.08529","title":"Accelerating Shapley Explanation via Contributive Cooperator Selection","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2402.02631","title":"Learning to Understand: Identifying Interactions via the M\\\"obius Transform","created":"2024-02-04","cited_by_count":13,"area":null},{"id":"2405.15018","title":"What Variables Affect Out-of-Distribution Generalization in Pretrained Models?","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2203.08926","title":"Synthetic Question Value Estimation for Domain Adaptation of Question Answering","created":"2022-03-16","cited_by_count":12,"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":"2302.11431","title":"A Note on \"Towards Efficient Data Valuation Based on the Shapley Value''","created":"2023-02-22","cited_by_count":11,"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":"2106.02938","title":"Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning","created":"2021-06-05","cited_by_count":10,"area":null},{"id":"2108.10623","title":"Data-Free Evaluation of User Contributions in Federated Learning","created":"2021-08-24","cited_by_count":10,"area":null},{"id":"2112.02230","title":"SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning","created":"2021-12-04","cited_by_count":10,"area":null},{"id":"2302.04075","title":"Best Practices in Active Learning for Semantic Segmentation","created":"2023-02-08","cited_by_count":10,"area":null},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2403.17691","title":"Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes","created":"2024-03-26","cited_by_count":10,"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":"2106.00162","title":"HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations","created":"2021-06-01","cited_by_count":9,"area":null},{"id":"2110.03524","title":"Data-Driven Methods for Balancing Fairness and Efficiency in Ride-Pooling","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2209.09775","title":"FedToken: Tokenized Incentives for Data Contribution in Federated Learning","created":"2022-09-20","cited_by_count":9,"area":null},{"id":"2212.00261","title":"Task Discovery: Finding the Tasks that Neural Networks Generalize on","created":"2022-12-01","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":"2410.23808","title":"One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2505.21692","title":"What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2112.02870","title":"A Marketplace for Trading AI Models based on Blockchain and Incentives for IoT Data","created":"2021-12-06","cited_by_count":8,"area":null},{"id":"2206.00511","title":"Differentially Private Shapley Values for Data Evaluation","created":"2022-06-01","cited_by_count":8,"area":null},{"id":"2306.05592","title":"Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning","created":"2023-06-08","cited_by_count":8,"area":null},{"id":"2312.13306","title":"Towards Fair Graph Federated Learning via Incentive Mechanisms","created":"2023-12-20","cited_by_count":8,"area":null},{"id":"2411.11667","title":"Dissecting Representation Misalignment in Contrastive Learning via Influence Function","created":"2024-11-18","cited_by_count":8,"area":null}],"next_cursor":"100"}