Metalearning Using Structure-rich Pipeline Representations for Better AutoML
Automatic machine learning (AutoML) systems have been shown to perform better when they learn from past experience. Examples include Auto-sklearn, which warm-starts the ML pipeline search using existing programs known to perform well on "similar" tasks, and AlphaD3M, which uses online reinforcement learning to search the ML pipeline space. These metalearning approaches, as well as many others, depend on simplifying assumptions about the pipeline search space and/or the pipeline representation. We show that we can estimate ML pipeline performance without simplifying the representation of the pipeline structure. We evaluate this approach on tabular classification tasks and find that it produces the best estimates of pipeline performance and yields pipeline rankings with the highest normalized discounted cumulative gain (nDCG) and the lowest regret.
Code (0)
등록된 구현이 없습니다.
Tasks
AutoMLreinforcement-learningReinforcement Learning (RL)tabular-classificationSimilar Papers 제목 키워드 기반
Preprocessor Selection for Machine Learning Pipelines
Much of the work in metalearning has focused on classifier selection, combined more recently with hyperparameter optimization, with little concern for data preprocessing. Yet, it is generally well accepted that machine l…
BIG-bench Machine LearningHyperparameter OptimizationMetalearning with Hebbian Fast Weights
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a singl…
One-Shot LearningOptimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization
Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research. Loss functions are a type of metaknowledge that is crucial to effective training of DNNs,…
Metalearning for Feature Selection
A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated program learning and other cases. A novel…
Classificationfeature selectionGeneral Classificationtext-classification+1Optimizing Reusable Knowledge for Continual Learning via Metalearning
When learning tasks over time, artificial neural networks suffer from a problem known as Catastrophic Forgetting (CF). This happens when the weights of a network are overwritten during the training of a new task causing …
Continual Learning