In this paper, we formalize the problem of meta-feature learning as a step that can be shared between all kinds of meta-tasks and asks for meta-feature extractors that combine the versatility of engineered meta-features with the expressivity obtained by learned models such as neural networks, to transfer meta-knowledge across (tabular) datasets with varying schemas (Sect. Correlation The meta-features extracted by the meta-feature extractor should correlate well with the meta-targets, i.e., improve the performance on meta-tasks such as hyperparameter optimization. Scalability The meta-feature extractor should be able to extract meta-features fast, e.g., it should not require itself some sort of training on new meta-tasks.ĭ4. Expressivity The meta-feature extractor should be able to extract meta-features for meta-tasks of varying complexity, i.e., just a handful of meta-features for simple meta-tasks, but hundreds of meta-features for more complex tasks.ĭ3. Schema Agnosticism The meta-feature extractor should be able to extract meta-features for a population of meta-tasks with varying schema, e.g., datasets containing different predictor and target variables, also having a different number of predictors and targets.ĭ2. Thus to be useful, meta-feature extractors should meet the following four desiderata:ĭ1. the same number, type, and semantics of predictors and targets. On the other hand, meta-feature extractors modeled as autoencoders can only compute meta-features for datasets having the same schema, i.e. Engineered meta-features often require expert domain knowledge and must be adjusted for each task, hence have limited expressivity. However, both approaches suffer from complementary weaknesses. More recently, unsupervised methods based on variational autoencoders (Edwards and Storkey 2017b) have been successful in learning such meta-features. Traditionally, simple, easy to compute, engineered (Edwards and Storkey 2017a) meta-features, such as the number of instances, the number of predictors, the number of targets (Bardenet et al. 2018).Īs a data-driven approach, meta-learning requires meta-features that represent the primary learning tasks or datasets to transfer knowledge across them. Domain adaptation and learning to optimize are other such meta-tasks of interest (Finn et al. Hyperparameter optimization across different datasets is a typical meta-learning task that has shown great success lately (Bardenet et al. For example, after having chosen hyperparameters for dozens of different learning tasks, one would like to learn how to choose them for the next task at hand. Meta-learning, or learning to learn, refers to any learning approach that systematically makes use of prior learning experiences to accelerate training on unseen tasks or datasets (Vanschoren 2018). In an experiment on a large-scale hyperparameter optimization task for 120 UCI datasets with varying schemas as a meta-learning task, we show that the meta-features of Dataset2Vec outperform the expert engineered meta-features and thus demonstrate the usefulness of learned meta-features for datasets with varying schemas for the first time. Second, we propose a novel auxiliary meta-learning task with abundant data called dataset similarity learning that aims to predict if two batches stem from the same dataset or different ones. as a set of predictor/target pairs, and then a DeepSet architecture is employed to regress meta-features on them. Primary learning tasks or datasets are represented as hierarchical sets, i.e., as a set of sets, esp. In this paper, first, we propose a meta-feature extractor called Dataset2Vec that combines the versatility of engineered dataset meta-features with the expressivity of meta-features learned by deep neural networks. As a data-driven approach, meta-learning requires meta-features that represent the primary learning tasks or datasets, and are estimated traditonally as engineered dataset statistics that require expert domain knowledge tailored for every meta-task. Meta-learning, or learning to learn, is a machine learning approach that utilizes prior learning experiences to expedite the learning process on unseen tasks.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |