{"total":85,"rows":[{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491,"area":null},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360,"area":null},{"id":"2305.02997","title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","created":"2023-05-04","cited_by_count":223,"area":null},{"id":"2207.08815","title":"Why do tree-based models still outperform deep learning on tabular data?","created":"2022-07-18","cited_by_count":199,"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":"2109.06716","title":"HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO","created":"2021-09-14","cited_by_count":112,"area":null},{"id":"2106.08087","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","created":"2021-06-15","cited_by_count":101,"area":null},{"id":"2312.07577","title":"Benchmarking Distribution Shift in Tabular Data with TableShift","created":"2023-12-10","cited_by_count":66,"area":null},{"id":"2207.12560","title":"AMLB: an AutoML Benchmark","created":"2022-07-25","cited_by_count":55,"area":null},{"id":"2310.20447","title":"Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks","created":"2023-10-31","cited_by_count":37,"area":null},{"id":"2311.02971","title":"TabRepo: A Large Scale Repository of Tabular Model Evaluations and its AutoML Applications","created":"2023-11-06","cited_by_count":33,"area":null},{"id":"2109.01528","title":"LightAutoML: AutoML Solution for a Large Financial Services Ecosystem","created":"2021-09-03","cited_by_count":32,"area":null},{"id":"2306.02738","title":"A Large-Scale Study of Probabilistic Calibration in Neural Network Regression","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2111.02705","title":"Benchmarking Multimodal AutoML for Tabular Data with Text Fields","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2404.16795","title":"In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization","created":"2024-04-25","cited_by_count":26,"area":null},{"id":"2111.05850","title":"Towards Green Automated Machine Learning: Status Quo and Future Directions","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2201.00162","title":"MLOps -- Definitions, Tools and Challenges","created":"2022-01-01","cited_by_count":25,"area":null},{"id":"2210.01078","title":"Unsupervised Model Selection for Time-series Anomaly Detection","created":"2022-10-03","cited_by_count":25,"area":null},{"id":"2411.03562","title":"Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance","created":"2024-11-05","cited_by_count":25,"area":"agents"},{"id":"2106.04682","title":"Bayesian Optimization over Hybrid Spaces","created":"2021-06-08","cited_by_count":23,"area":null},{"id":"2302.00441","title":"Scaling Laws for Hyperparameter Optimization","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2510.06162","title":"TabPFN-Wide: Continued Pre-Training for Extreme Feature Counts","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2604.24658","title":"The Last Human-Written Paper: Agent-Native Research Artifacts","created":"2026-04-27","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":"2407.02112","title":"A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data","created":"2024-07-02","cited_by_count":15,"area":null},{"id":"2408.00665","title":"AutoM3L: An Automated Multimodal Machine Learning Framework with Large Language Models","created":"2024-08-01","cited_by_count":13,"area":null},{"id":"2201.09750","title":"Online AutoML: An adaptive AutoML framework for online learning","created":"2022-01-24","cited_by_count":11,"area":null},{"id":"2404.18209","title":"4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs","created":"2024-04-28","cited_by_count":11,"area":null},{"id":"2106.04618","title":"EXPObench: Benchmarking Surrogate-based Optimisation Algorithms on Expensive Black-box Functions","created":"2021-06-08","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":"2602.03018","title":"From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection","created":"2026-02-03","cited_by_count":9,"area":null},{"id":"2111.14514","title":"Naive Automated Machine Learning","created":"2021-11-29","cited_by_count":8,"area":null},{"id":"2206.03070","title":"SubStrat: A Subset-Based Strategy for Faster AutoML","created":"2022-06-07","cited_by_count":8,"area":null},{"id":"2111.00083","title":"A Scalable AutoML Approach Based on Graph Neural Networks","created":"2021-10-29","cited_by_count":7,"area":null},{"id":"2208.12754","title":"Task Selection for AutoML System Evaluation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2208.14417","title":"Fraud Dataset Benchmark and Applications","created":"2022-08-30","cited_by_count":7,"area":null},{"id":"2101.10951","title":"Incremental Search Space Construction for Machine Learning Pipeline Synthesis","created":"2021-01-26","cited_by_count":6,"area":null},{"id":"2206.03966","title":"FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization","created":"2022-06-08","cited_by_count":6,"area":null},{"id":"2305.13072","title":"Interpretable Mesomorphic Networks for Tabular Data","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2312.13038","title":"AutoXPCR: Automated Multi-Objective Model Selection for Time Series Forecasting","created":"2023-12-20","cited_by_count":6,"area":null},{"id":"2403.11964","title":"Probabilistic Calibration by Design for Neural Network Regression","created":"2024-03-18","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":"2409.01635","title":"PMLBmini: A Tabular Classification Benchmark Suite for Data-Scarce Applications","created":"2024-09-03","cited_by_count":6,"area":null},{"id":"2205.10538","title":"Automated machine learning: AI-driven decision making in business analytics","created":"2022-05-21","cited_by_count":5,"area":null},{"id":"2310.02540","title":"Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2602.09329","title":"MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection","created":"2026-02-10","cited_by_count":5,"area":null},{"id":"2106.05767","title":"Meta-Learning for Symbolic Hyperparameter Defaults","created":"2021-06-10","cited_by_count":4,"area":null},{"id":"2106.09179","title":"Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation","created":"2021-06-17","cited_by_count":4,"area":null},{"id":"2202.04137","title":"Machine Learning in Heterogeneous Porous Materials","created":"2022-02-04","cited_by_count":3,"area":null},{"id":"2204.08358","title":"AutoMLBench: A Comprehensive Experimental Evaluation of Automated Machine Learning Frameworks","created":"2022-04-18","cited_by_count":3,"area":null},{"id":"2211.00376","title":"Automated Imbalanced Learning","created":"2022-11-01","cited_by_count":3,"area":null},{"id":"2312.16930","title":"Encoding categorical data: Is there yet anything 'hotter' than one-hot encoding?","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2402.04453","title":"The Potential of AutoML for Recommender Systems","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2101.05840","title":"A Neophyte With AutoML: Evaluating the Promises of Automatic Machine Learning Tools","created":"2021-01-14","cited_by_count":2,"area":null},{"id":"2106.07317","title":"Automated Machine Learning Techniques for Data Streams","created":"2021-06-14","cited_by_count":2,"area":null},{"id":"2208.00269","title":"Automatically Categorising GitHub Repositories by Application Domain","created":"2022-07-30","cited_by_count":2,"area":null},{"id":"2304.14735","title":"Benchmarking Automated Machine Learning Methods for Price Forecasting Applications","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2305.14009","title":"Deep Pipeline Embeddings for AutoML","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2307.04849","title":"SigOpt Mulch: An Intelligent System for AutoML of Gradient Boosted Trees","created":"2023-07-10","cited_by_count":2,"area":null},{"id":"2307.10774","title":"Assessing the Use of AutoML for Data-Driven Software Engineering","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2601.12355","title":"Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH","created":"2026-01-18","cited_by_count":2,"area":null},{"id":"2103.10496","title":"Naive Automated Machine Learning -- A Late Baseline for AutoML","created":"2021-03-18","cited_by_count":1,"area":null},{"id":"2107.10495","title":"Benchmarking AutoML Frameworks for Disease Prediction Using Medical Claims","created":"2021-07-22","cited_by_count":1,"area":null},{"id":"2109.05583","title":"Automatic Componentwise Boosting: An Interpretable AutoML System","created":"2021-09-12","cited_by_count":1,"area":null},{"id":"2302.14329","title":"Towards Personalized Preprocessing Pipeline Search","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2312.14770","title":"Integration Of Evolutionary Automated Machine Learning With Structural Sensitivity Analysis For Composite Pipelines","created":"2023-12-22","cited_by_count":1,"area":null},{"id":"2402.03806","title":"Explainable Automated Machine Learning for Credit Decisions: Enhancing Human Artificial Intelligence Collaboration in Financial Engineering","created":"2024-02-06","cited_by_count":1,"area":null},{"id":"2405.15303","title":"A Trajectory-Based Bayesian Approach to Multi-Objective Hyperparameter Optimization with Epoch-Aware Trade-Offs","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2410.12841","title":"UniAutoML: A Human-Centered Framework for Unified Discriminative and Generative AutoML with Large Language Models","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2411.08932","title":"PyGen: A Collaborative Human-AI Approach to Python Package Creation","created":"2024-11-13","cited_by_count":1,"area":null},{"id":"2504.01222","title":"AutoML Benchmark with shorter time constraints and early stopping","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2504.06207","title":"An experimental survey and Perspective View on Meta-Learning for Automated Algorithms Selection and Parametrization","created":"2025-04-08","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":"2608.07303","title":"Winning by Peeking: Unenforced Budgets and Test-Set Selection Inflate Short-Budget AutoML Comparisons","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2108.12193","title":"Man versus Machine: AutoML and Human Experts' Role in Phishing Detection","created":"2021-08-27","cited_by_count":0,"area":null},{"id":"2202.00893","title":"Mold into a Graph: Efficient Bayesian Optimization over Mixed-Spaces","created":"2022-02-02","cited_by_count":0,"area":null},{"id":"2212.02704","title":"Benchmarking AutoML algorithms on a collection of synthetic classification problems","created":"2022-12-06","cited_by_count":0,"area":null},{"id":"2303.10732","title":"AutoEn: An AutoML method based on ensembles of predefined Machine Learning pipelines for supervised Traffic Forecasting","created":"2023-03-19","cited_by_count":0,"area":null},{"id":"2303.11580","title":"Efficient Multi-stage Inference on Tabular Data","created":"2023-03-21","cited_by_count":0,"area":null},{"id":"2304.08597","title":"eTOP: Early Termination of Pipelines for Faster Training of AutoML Systems","created":"2023-04-17","cited_by_count":0,"area":null},{"id":"2309.08171","title":"Unveiling Invariances via Neural Network Pruning","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2311.02278","title":"Machine learning's own Industrial Revolution","created":"2023-11-04","cited_by_count":0,"area":null},{"id":"2601.15640","title":"An Empirical Study on Ensemble-Based Transfer Learning Bayesian Optimisation with Mixed Variable Types","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.00412","title":"Robustness of AutoML on Dirty Categorical Data","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2608.18919","title":"Lost in Aggregation: How Benchmarks Overlook Irreplaceable Model Strengths","created":"2026-08-19","cited_by_count":0,"area":null}],"next_cursor":null}