{"total":61,"rows":[{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674,"area":null},{"id":"2106.15147","title":"SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption","created":"2021-06-29","cited_by_count":156,"area":null},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151,"area":null},{"id":"2305.03403","title":"Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering","created":"2023-05-05","cited_by_count":127,"area":null},{"id":"2106.06257","title":"HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML","created":"2021-06-11","cited_by_count":75,"area":null},{"id":"2410.01649","title":"shapiq: Shapley Interactions for Machine Learning","created":"2024-10-02","cited_by_count":43,"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":"2503.14434","title":"LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers","created":"2025-03-18","cited_by_count":38,"area":null},{"id":"2401.12069","title":"Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles","created":"2024-01-22","cited_by_count":31,"area":null},{"id":"2405.10852","title":"KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions","created":"2024-05-17","cited_by_count":22,"area":null},{"id":"2306.16830","title":"Sampling weights of deep neural networks","created":"2023-06-29","cited_by_count":20,"area":null},{"id":"2110.09697","title":"abess: A Fast Best Subset Selection Library in Python and R","created":"2021-10-19","cited_by_count":16,"area":null},{"id":"2111.13914","title":"Fast and Informative Model Selection using Learning Curve Cross-Validation","created":"2021-11-27","cited_by_count":15,"area":null},{"id":"2402.17423","title":"Reinforced In-Context Black-Box Optimization","created":"2024-02-27","cited_by_count":14,"area":null},{"id":"2505.20003","title":"TabPFN: One Model to Rule Them All?","created":"2025-05-26","cited_by_count":14,"area":null},{"id":"2201.02354","title":"GenLabel: Mixup Relabeling using Generative Models","created":"2022-01-07","cited_by_count":10,"area":null},{"id":"2209.01939","title":"Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams","created":"2022-09-05","cited_by_count":9,"area":null},{"id":"2304.13339","title":"OpenBox: A Python Toolkit for Generalized Black-box Optimization","created":"2023-04-26","cited_by_count":9,"area":null},{"id":"2307.00285","title":"Assembled-OpenML: Creating Efficient Benchmarks for Ensembles in AutoML with OpenML","created":"2023-07-01","cited_by_count":9,"area":null},{"id":"2409.12788","title":"Optimal or Greedy Decision Trees? Revisiting their Objectives, Tuning, and Performance","created":"2024-09-19","cited_by_count":9,"area":null},{"id":"2505.08784","title":"PCS-UQ: Uncertainty Quantification via the Predictability-Computability-Stability Framework","created":"2025-05-13","cited_by_count":9,"area":null},{"id":"2206.08364","title":"Interaction-Grounded Learning with Action-inclusive Feedback","created":"2022-06-16","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":"2108.13637","title":"When are Deep Networks really better than Decision Forests at small sample sizes, and how?","created":"2021-08-31","cited_by_count":6,"area":null},{"id":"2405.03389","title":"Don't Waste Your Time: Early Stopping Cross-Validation","created":"2024-05-06","cited_by_count":6,"area":null},{"id":"2306.04262","title":"Self-Adjusting Weighted Expected Improvement for Bayesian Optimization","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2406.17322","title":"ALPBench: A Benchmark for Active Learning Pipelines on Tabular Data","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2208.01148","title":"Boosted Off-Policy Learning","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2212.04183","title":"Mind the Gap: Measuring Generalization Performance Across Multiple Objectives","created":"2022-12-08","cited_by_count":3,"area":null},{"id":"2302.05270","title":"Conceptual Views on Tree Ensemble Classifiers","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2303.01181","title":"iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams","created":"2023-03-02","cited_by_count":3,"area":null},{"id":"2311.05088","title":"Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces","created":"2023-11-09","cited_by_count":3,"area":null},{"id":"2608.06004","title":"Do Tabular Foundation Models Agree with Themselves?","created":"2026-08-06","cited_by_count":3,"area":null},{"id":"2311.15854","title":"A systematic study comparing hyperparameter optimization engines on tabular data","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2502.02345","title":"Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2505.14312","title":"MultiTab: A Comprehensive Benchmark Suite for Multi-Dimensional Evaluation in Tabular Domains","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2303.00031","title":"Tiny Classifier Circuits: Evolving Accelerators for Tabular Data","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2304.05246","title":"OpenAL: Evaluation and Interpretation of Active Learning Strategies","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2310.06380","title":"CAST: Cluster-Aware Self-Training for Tabular Data via Reliable Confidence","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2312.10494","title":"Do Bayesian Neural Networks Improve Weapon System Predictive Maintenance?","created":"2023-12-16","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":"2505.15657","title":"LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.22305","title":"Detection of Personal Data in Structured Datasets Using a Large Language Model","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2508.16604","title":"WHAR Datasets: An Open Source Library for Wearable Human Activity Recognition","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2511.15941","title":"iLTM: Integrated Large Tabular Model","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2601.07282","title":"Minimum Wasserstein distance estimator under covariate shift: closed-form, super-efficiency and irregularity","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2601.10457","title":"NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.16690","title":"Synthetic-Powered Multiple Testing with FDR Control","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2110.08483","title":"Extremely Simple Streaming Forest","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2111.02164","title":"Data structure > labels? Unsupervised heuristics for SVM hyperparameter estimation","created":"2021-11-03","cited_by_count":0,"area":null},{"id":"2309.15719","title":"Model Share AI: An Integrated Toolkit for Collaborative Machine Learning Model Development, Provenance Tracking, and Deployment in Python","created":"2023-09-27","cited_by_count":0,"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":"2501.04260","title":"Modeling All Response Surfaces in One for Conditional Search Spaces","created":"2025-01-08","cited_by_count":0,"area":null},{"id":"2504.18385","title":"Model Evaluation in the Dark: Robust Classifier Metrics with Missing Labels","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2509.09512","title":"PIPES: A Meta-dataset of Machine Learning Pipelines","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2602.00437","title":"Exact Instance Compression for Convex Empirical Risk Minimization via Color Refinement","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.07279","title":"VertCoHiRF: Decentralized Vertical Clustering Beyond k-means","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.22884","title":"Unsupervised Continual Learning for Amortized Bayesian Inference","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.05172","title":"Trainable Bitwise Soft Quantization for Input Feature Compression","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2608.17948","title":"SIGMA: SHAP-Guided Implicit-Trajectory Generation for Metadata-Free LLM-Based AutoFE","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2610.20342","title":"When Does Task-Aware Imputation Matter? An Analysis of Robustness Under Train-Test Mismatch","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}