{"total":119,"rows":[{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"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":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2306.10577","title":"OpenDataVal: a Unified Benchmark for Data Valuation","created":"2023-06-18","cited_by_count":55,"area":null},{"id":"2402.10086","title":"Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2302.00736","title":"Approximating the Shapley Value without Marginal Contributions","created":"2023-02-01","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":"2405.03875","title":"Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits","created":"2024-05-06","cited_by_count":29,"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":"2410.03055","title":"Permissive Information-Flow Analysis for Large Language Models","created":"2024-10-04","cited_by_count":22,"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":"2312.05327","title":"Better, Not Just More: Data-Centric Machine Learning for Earth Observation","created":"2023-12-08","cited_by_count":19,"area":null},{"id":"2506.11849","title":"Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values","created":"2025-06-13","cited_by_count":19,"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":"2311.05304","title":"Data Valuation and Detections in Federated Learning","created":"2023-11-09","cited_by_count":17,"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":"2404.05779","title":"Data Readiness for AI: A 360-Degree Survey","created":"2024-04-08","cited_by_count":15,"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":"2402.02631","title":"Learning to Understand: Identifying Interactions via the M\\\"obius Transform","created":"2024-02-04","cited_by_count":13,"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":"2502.13870","title":"SPEX: Scaling Feature Interaction Explanations for LLMs","created":"2025-02-19","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":"2403.04551","title":"Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2403.10923","title":"Interpretable Machine Learning for TabPFN","created":"2024-03-16","cited_by_count":11,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","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":"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":"2601.18608","title":"PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression","created":"2026-01-26","cited_by_count":7,"area":null},{"id":"2207.07038","title":"SHAP-XRT: The Shapley Value Meets Conditional Independence Testing","created":"2022-07-14","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":"2410.09940","title":"Generalized Group Data Attribution","created":"2024-10-13","cited_by_count":6,"area":null},{"id":"2301.13336","title":"The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning","created":"2023-01-30","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":"2405.17293","title":"Efficient Ensembles Improve Training Data Attribution","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2410.04386","title":"Data Distribution Valuation","created":"2024-10-06","cited_by_count":5,"area":null},{"id":"2412.01335","title":"A Versatile Influence Function for Data Attribution with Non-Decomposable Loss","created":"2024-12-02","cited_by_count":5,"area":null},{"id":"2412.03906","title":"Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2501.06261","title":"CAMs as Shapley Value-based Explainers","created":"2025-01-09","cited_by_count":5,"area":null},{"id":"2602.01399","title":"An Odd Estimator for Shapley Values","created":"2026-02-01","cited_by_count":5,"area":null},{"id":"2405.17489","title":"On the Inflation of KNN-Shapley Value","created":"2024-05-25","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":"2511.13254","title":"Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2310.09983","title":"Farzi Data: Autoregressive Data Distillation","created":"2023-10-15","cited_by_count":3,"area":null},{"id":"2312.11413","title":"DeRDaVa: Deletion-Robust Data Valuation for Machine Learning","created":"2023-12-18","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":"2602.07203","title":"Exactly Computing do-Shapley Values","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2312.04604","title":"Transferable Candidate Proposal with Bounded Uncertainty","created":"2023-12-07","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":"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":"2407.19373","title":"Uncertainty Quantification of Data Shapley via Statistical Inference","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2409.05657","title":"Adversarial Attacks on Data Attribution","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2410.08336","title":"Kernel Banzhaf: A Fast and Robust Estimator for Banzhaf Values","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2410.09348","title":"BANGS: Game-Theoretic Node Selection for Graph Self-Training","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2501.02356","title":"When is the Computation of a Feature Attribution Method Tractable?","created":"2025-01-04","cited_by_count":2,"area":null},{"id":"2502.16152","title":"DUPRE: Data Utility Prediction for Efficient Data Valuation","created":"2025-02-22","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":"2506.00175","title":"Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2509.03749","title":"Mapping on a Budget: Optimizing Spatial Data Collection for ML","created":"2025-09-03","cited_by_count":2,"area":null},{"id":"2509.11196","title":"Federated Recommender System with Data Valuation for E-commerce Platform","created":"2025-09-14","cited_by_count":2,"area":null},{"id":"2602.09326","title":"Priority-Aware Shapley Value","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2605.04497","title":"Quadrature-TreeSHAP: Depth-Independent TreeSHAP and Shapley Interactions","created":"2026-05-06","cited_by_count":2,"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":"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":"2412.17008","title":"Data value estimation on private gradients","created":"2024-12-22","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":"2503.18195","title":"Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2504.08364","title":"DRIP: DRop unImportant data Points -- Enhancing Machine Learning Efficiency with Grad-CAM-Based Real-Time Data Prioritization for On-Device Training","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2505.21438","title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2505.23223","title":"Daunce: Data Attribution through Uncertainty Estimation","created":"2025-05-29","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":"2509.19921","title":"On the Fragility of Contribution Score Computation in Federated Learning","created":"2025-09-24","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},{"id":"2602.21721","title":"Private and Robust Contribution Evaluation in Federated Learning","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.00342","title":"Challenges in Enabling Private Data Valuation","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2604.08438","title":"Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.07663","title":"Quotient Semivalues for False-Name-Resistant Data Attribution","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.01635","title":"AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.15959","title":"Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2404.19557","title":"Neural Dynamic Data Valuation via Stochastic State-Adjoint Trajectories","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2405.17464","title":"Data Valuation by Fusing Global and Local Statistical Information","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2502.00494","title":"Data Overvaluation Attack and Truthful Data Valuation in Federated Learning","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2502.10489","title":"LiveVal: Time-aware Data Valuation via Adaptive Reference Points","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2503.08381","title":"InfluenceNet: AI Models for Banzhaf and Shapley Value Prediction","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2506.23349","title":"A case for data valuation transparency via DValCards","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2508.05089","title":"Integrated Influence: Data Attribution with Baseline","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2508.21261","title":"Owen Sampling Accelerates Contribution Estimation in Federated Learning","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.10825","title":"CUBE: Contrastive Understanding by Balanced Experiments","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2509.12581","title":"Exploring Training Data Attribution under Limited Access Constraints","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.20463","title":"Efficiently Attacking Memorization Scores","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.10510","title":"f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2510.13261","title":"A Ratio-Based Shapley Value for Collaborative Machine Learning - Extended Version","created":"2025-10-15","cited_by_count":0,"area":null}],"next_cursor":"100"}