Dataset2Vec: learning dataset meta-features
Abstract: Meta-learning, or learning to learn, is a machine learning approach that utilizes prior learning experiences to expedite the learning process on unseen tasks. 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. 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. Primary learning tasks or datasets are represented as hierarchical sets, i.e., as a set of sets, esp. as a set of predictor/target pairs, and then a DeepSet architecture is employed to regress meta-features on them. 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. 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
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Notes
-
Data mining and knowledge discovery. - 35, 3 (2021) , 964-985, ISSN: 1573-756X
- Event
-
Veröffentlichung
- (where)
-
Freiburg
- (who)
-
Universität
- (when)
-
2024
- Creator
- DOI
-
10.1007/s10618-021-00737-9
- URN
-
urn:nbn:de:bsz:25-freidok-2475975
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
-
25.03.2025, 1:53 PM CET
Data provider
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Jomaa, Hadi S.
- Schmidt-Thieme, Lars
- Grabocka, Josif
- Universität
Time of origin
- 2024
Other Objects (12)
A novel approach for reducing feature space dimensionality and developing a universal machine learning model for coated tubes in cross-flow heat exchangers
Laparoscopic video analysis using temporal, attention, and multi-feature fusion based-approaches
Refuting student teachers’ misconceptions about multimedia learning
Internet-based behavioral activation for depression: systematic review and meta-analysis
A deep learning approach for complex microstructure inference
Category learning in autistic individuals: a meta-analysis
A Pindaric feature in the poems of Callimachus
Effects of exercise training on muscle quality in older individuals: a systematic scoping review with meta-analyses
Drought catalogue dataset
The rise of the modern Leviathan : : state functions and state features
Patient groups in rheumatoid arthritis identified by deep learning respond differently to biologic or targeted synthetic DMARDs
Procedural structure and features of international criminal justice: lessons from the ICTY
A novel approach for reducing feature space dimensionality and developing a universal machine learning model for coated tubes in cross-flow heat exchangers
Laparoscopic video analysis using temporal, attention, and multi-feature fusion based-approaches
Refuting student teachers’ misconceptions about multimedia learning
Internet-based behavioral activation for depression: systematic review and meta-analysis
A deep learning approach for complex microstructure inference
Category learning in autistic individuals: a meta-analysis
A Pindaric feature in the poems of Callimachus
Effects of exercise training on muscle quality in older individuals: a systematic scoping review with meta-analyses
Drought catalogue dataset
The rise of the modern Leviathan : : state functions and state features
Patient groups in rheumatoid arthritis identified by deep learning respond differently to biologic or targeted synthetic DMARDs
Procedural structure and features of international criminal justice: lessons from the ICTY
A novel approach for reducing feature space dimensionality and developing a universal machine learning model for coated tubes in cross-flow heat exchangers
Laparoscopic video analysis using temporal, attention, and multi-feature fusion based-approaches
Refuting student teachers’ misconceptions about multimedia learning
Internet-based behavioral activation for depression: systematic review and meta-analysis
A deep learning approach for complex microstructure inference
Category learning in autistic individuals: a meta-analysis
A Pindaric feature in the poems of Callimachus
Effects of exercise training on muscle quality in older individuals: a systematic scoping review with meta-analyses
Drought catalogue dataset
The rise of the modern Leviathan : : state functions and state features
Patient groups in rheumatoid arthritis identified by deep learning respond differently to biologic or targeted synthetic DMARDs