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
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Anmerkungen
-
Data mining and knowledge discovery. - 35, 3 (2021) , 964-985, ISSN: 1573-756X
- Ereignis
-
Veröffentlichung
- (wo)
-
Freiburg
- (wer)
-
Universität
- (wann)
-
2024
- Urheber
- DOI
-
10.1007/s10618-021-00737-9
- URN
-
urn:nbn:de:bsz:25-freidok-2475975
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
25.03.2025, 13:53 MEZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Jomaa, Hadi S.
- Schmidt-Thieme, Lars
- Grabocka, Josif
- Universität
Entstanden
- 2024
Ähnliche Objekte (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
A Pindaric feature in the poems of Callimachus
Category learning in autistic individuals: a meta-analysis
Effects of exercise training on muscle quality in older individuals: a systematic scoping review with meta-analyses
The rise of the modern Leviathan : : state functions and state features
Drought catalogue dataset
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
A Pindaric feature in the poems of Callimachus
Category learning in autistic individuals: a meta-analysis
Effects of exercise training on muscle quality in older individuals: a systematic scoping review with meta-analyses
The rise of the modern Leviathan : : state functions and state features
Drought catalogue dataset
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
A Pindaric feature in the poems of Callimachus
Category learning in autistic individuals: a meta-analysis
Effects of exercise training on muscle quality in older individuals: a systematic scoping review with meta-analyses
The rise of the modern Leviathan : : state functions and state features
Drought catalogue dataset
Patient groups in rheumatoid arthritis identified by deep learning respond differently to biologic or targeted synthetic DMARDs