Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Integration Of Evolutionary Automated Machine Learning With Structural Sensitivity Analysis For Composite Pipelines (2312.14770v1)

Published 22 Dec 2023 in cs.LG and cs.NE

Abstract: Automated machine learning (AutoML) systems propose an end-to-end solution to a given machine learning problem, creating either fixed or flexible pipelines. Fixed pipelines are task independent constructs: their general composition remains the same, regardless of the data. In contrast, the structure of flexible pipelines varies depending on the input, making them finely tailored to individual tasks. However, flexible pipelines can be structurally overcomplicated and have poor explainability. We propose the EVOSA approach that compensates for the negative points of flexible pipelines by incorporating a sensitivity analysis which increases the robustness and interpretability of the flexible solutions. EVOSA quantitatively estimates positive and negative impact of an edge or a node on a pipeline graph, and feeds this information to the evolutionary AutoML optimizer. The correctness and efficiency of EVOSA was validated in tabular, multimodal and computer vision tasks, suggesting generalizability of the proposed approach across domains.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Irina V Barabanova, Pavel Vychuzhanin and Nikolay O Nikitin “Sensitivity Analysis of the Composite Data-Driven Pipelines in the Automated Machine Learning” In Procedia Computer Science 193 Elsevier, 2021, pp. 484–493
  2. José P Cambronero, Jürgen Cito and Martin C Rinard “Ams: Generating automl search spaces from weak specifications” In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020, pp. 763–774
  3. “Ensemble Selection from Libraries of Models”, 2004
  4. “Modeling and forecasting armed conflict: AutoML with human-guided machine learning” In 2019 IEEE International Conference on Big Data (Big Data), 2019, pp. 4714–4723 IEEE
  5. “Amazon SageMaker Autopilot: a white box AutoML solution at scale” In Proceedings of the fourth international workshop on data management for end-to-end machine learning, 2020, pp. 1–7
  6. “An analysis of dimensionality reduction techniques for visualizing evolution” In Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2019, pp. 1864–1872
  7. “Trust in AutoML: exploring information needs for establishing trust in automated machine learning systems” In Proceedings of the 25th International Conference on Intelligent User Interfaces, 2020, pp. 297–307
  8. Mengnan Du, Ninghao Liu and Xia Hu “Techniques for interpretable machine learning” In Communications of the ACM 63.1 ACM New York, NY, USA, 2019, pp. 68–77
  9. “AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data” In 7th ICML Workshop on Automated Machine Learning, 2020
  10. “Autogluon-tabular: Robust and accurate automl for structured data” In arXiv preprint arXiv:2003.06505, 2020
  11. “Auto-Sklearn 2.0: The Next Generation” In arXiv, 2020, pp. 1–18 arXiv: http://arxiv.org/abs/2007.04074
  12. “Efficient and robust automated machine learning” In Advances in neural information processing systems 28, 2015
  13. Nicolo Fusi, Rishit Sheth and Melih Elibol “Probabilistic matrix factorization for automated machine learning” In Advances in neural information processing systems 31, 2018, pp. 3348–3357
  14. Pieter Gijsbers, Joaquin Vanschoren and Randal S. Olson “Layered TPOT: Speeding up Tree-based Pipeline Optimization”, 2018 URL: http://arxiv.org/abs/1801.06007
  15. “An open source AutoML benchmark” In arXiv preprint arXiv:1907.00909, 2019
  16. “Deep residual learning for image recognition” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778
  17. Xin He, Kaiyong Zhao and Xiaowen Chu “AutoML: A survey of the state-of-the-art” In Knowledge-Based Systems 212 Elsevier, 2021, pp. 106622
  18. “Auto-WEKA: Automatic model selection and hyperparameter optimization in WEKA” In Automated machine learning Springer, Cham, 2019, pp. 81–95
  19. Siddhartha Laghuvarapu, Yashaswi Pathak and U Deva Priyakumar “Band nn: A deep learning framework for energy prediction and geometry optimization of organic small molecules” In Journal of computational chemistry 41.8 Wiley Online Library, 2020, pp. 790–799
  20. Teddy Lazebnik, Amit Somech and Abraham Itzhak Weinberg “SubStrat: A Subset-Based Strategy for Faster AutoML” In arXiv preprint arXiv:2206.03070, 2022
  21. “H2O AutoML: Scalable Automatic Machine Learning” In 7th ICML Workshop on Automated Machine Learning, 2020 URL: https://www.automl.org/wp-content/uploads/2020/07/AutoML_2020_paper_61.pdf
  22. “A sensitivity analysis method for driving the Artificial Bee Colony algorithm’s search process” In Applied Soft Computing 41 Elsevier, 2016, pp. 515–531
  23. “System sensitivity and uncertainty analysis” In Water Resource Systems Planning and Management: An Introduction to Methods, Models, and Applications Springer, 2017, pp. 331–374
  24. “Automated evolutionary approach for the design of composite machine learning pipelines” In Future Generation Computer Systems 127 Elsevier, 2022, pp. 109–125
  25. Randal S Olson and Jason H Moore “TPOT: A tree-based pipeline optimization tool for automating machine learning” In Workshop on automatic machine learning, 2016, pp. 66–74 PMLR
  26. “PipelineProfiler : A Visual Analytics Tool for the Exploration of AutoML Pipelines”
  27. “Pipelineprofiler: A visual analytics tool for the exploration of automl pipelines” In IEEE Transactions on Visualization and Computer Graphics 27.2 IEEE, 2020, pp. 390–400
  28. Youngjun Park, Anne-Christin Hauschild and Dominik Heider “Transfer learning compensates limited data, batch effects and technological heterogeneity in single-cell sequencing” In NAR Genomics and Bioinformatics 3.4, 2021 DOI: 10.1093/nargab/lqab104
  29. “Scikit-learn: Machine learning in Python” In Journal of machine learning research 12.Oct, 2011, pp. 2825–2830
  30. Philipp Probst, Anne-Laure Boulesteix and Bernd Bischl “Tunability: Importance of hyperparameters of machine learning algorithms.” In J. Mach. Learn. Res. 20.53, 2019, pp. 1–32
  31. “Quantum chemistry structures and properties of 134 kilo molecules” In Scientific data 1.1 Nature Publishing Group, 2014, pp. 1–7
  32. “Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities” In Knowledge-Based Systems 263 Elsevier, 2023, pp. 110273
  33. “Sensitivity analysis: A discipline coming of age” In Environmental Modelling & Software 146 Elsevier, 2021, pp. 105226
  34. “Schnet: A continuous-filter convolutional neural network for modeling quantum interactions” In Advances in neural information processing systems 30, 2017
  35. “Quantum-chemical insights from deep tensor neural networks” In Nature communications 8.1 Nature Publishing Group, 2017, pp. 1–8
  36. “Heterogeneous molecular graph neural networks for predicting molecule properties” In 2020 IEEE International Conference on Data Mining (ICDM), 2020, pp. 492–500 IEEE
  37. “Auto-WEKA: Combined selection and hyperparameter optimization of classification algorithms” In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Part F1288, 2013, pp. 847–855 DOI: 10.1145/2487575.2487629
  38. Oliver T Unke and Markus Meuwly “PhysNet: A neural network for predicting energies, forces, dipole moments, and partial charges” In Journal of chemical theory and computation 15.6 ACS Publications, 2019, pp. 3678–3693
  39. “LightAutoML: AutoML Solution for a Large Financial Services Ecosystem” In arXiv preprint arXiv:2109.01528, 2021
  40. “Putting the Human Back in the AutoML Loop.” In EDBT/ICDT Workshops, 2020
  41. Marc-André Zöller, Tien-Dung Nguyen and Marco F Huber “Incremental Search Space Construction for Machine Learning Pipeline Synthesis” In arXiv preprint arXiv:2101.10951, 2021

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now