mlsanityData to 7 Oct 2026

AlphaD3M: Machine Learning Pipeline Synthesis

arXiv 2111.02508 ↗First posted 3 Nov 2021cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

We introduce AlphaD3M, an automatic machine learning (AutoML) system based on meta reinforcement learning using sequence models with self play. AlphaD3M is based on edit operations performed over machine learning pipeline primitives providing explainability. We compare AlphaD3M with state-of-the-art AutoML systems: Autosklearn, Autostacker, and TPOT, on OpenML datasets. AlphaD3M achieves competitive performance while being an order of magnitude faster, reducing computation time from hours to minutes, and is explainable by design.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 8 of its 16 references that are in the map. First posted on arXiv 3 Nov 2021.

Builds on

8 of 16 references.

References · 8

  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  2. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  3. 2014OpenML: networked science in machine learningcited by 523
  4. 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
  5. 2017PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparisoncited by 139
  6. 2017Generating Sentences by Editing Prototypescited by 88
  7. 2018Autostacker: A Compositional Evolutionary Learning Systemcited by 18
  8. 2018Solving the Rubik's Cube Without Human Knowledgecited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 4; 2024: 3; 2025: 3; 2026: 6.

24 papers.

Sort:

By area:

  1. 2023Data-centric Artificial Intelligence: A Surveycited by 202
  2. 2022AMLB: an AutoML Benchmarkcited by 55
  3. 2025AutoPDL: Automatic Prompt Optimization for LLM Agentscited by 27
  4. 2022DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programscited by 16
  5. 2022DreamShard: Generalizable Embedding Table Placement for Recommender Systemscited by 14
  6. 2022XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learningcited by 8
  7. 2022SubStrat: A Subset-Based Strategy for Faster AutoMLcited by 8
  8. 2025SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Sciencecited by 7
  9. 2022Task Selection for AutoML System Evaluationcited by 6
  10. 2025LLM-Guided Evolution: An Autonomous Model Optimization for Object Detectioncited by 5
  11. 2022Review of the state of the art in autonomous artificial intelligencecited by 3
  12. 2024Statistical Test for Feature Selection Pipelines by Selective Inferencecited by 3
12 more
  1. 2023Deep Pipeline Embeddings for AutoMLcited by 2
  2. 2026Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASHcited by 2
  3. 2023Towards Personalized Preprocessing Pipeline Searchcited by 1
  4. 2023auto-sktime: Automated Time Series Forecastingcited by 1
  5. 2024Pulling the Carpet Below the Learner's Feet: Genetic Algorithm To Learn Ensemble Machine Learning Model During Concept Driftcited by 1
  6. 2022Efficient End-to-End AutoML via Scalable Search Space Decompositioncited by 0
  7. 2024Integrating Hyperparameter Search into Model-Free AutoML with Context-Free Grammarscited by 0
  8. 2026CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimizationcited by 0
  9. 2026Integrating Meta-Features with Knowledge Graph Embeddings for Meta-Learningcited by 0
  10. 2026Model-Aware Data Cleaning for Tabular Foundation Modelscited by 0
  11. 2026Candidate-Fate Accounting for Transparent Sensor Diagnostic Pipeline Searchcited by 0
  12. 2026SAGE-Loop: Reliable Closed-Loop LLM-Driven AutoML with Trial-and-Correction and Adaptive Ensemblingcited by 0