Gated Domain Units for Multi-source Domain Generalization
The phenomenon of distribution shift (DS) occurs when a dataset at test time differs from the dataset at training time, which can significantly impair the performance of a machine learning model in practical settings due to a lack of knowledge about the data's distribution at test time. To addr...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The phenomenon of distribution shift (DS) occurs when a dataset at test time
differs from the dataset at training time, which can significantly impair the
performance of a machine learning model in practical settings due to a lack of
knowledge about the data's distribution at test time. To address this problem,
we postulate that real-world distributions are composed of latent Invariant
Elementary Distributions (I.E.D) across different domains. This assumption
implies an invariant structure in the solution space that enables knowledge
transfer to unseen domains. To exploit this property for domain generalization,
we introduce a modular neural network layer consisting of Gated Domain Units
(GDUs) that learn a representation for each latent elementary distribution.
During inference, a weighted ensemble of learning machines can be created by
comparing new observations with the representations of each elementary
distribution. Our flexible framework also accommodates scenarios where explicit
domain information is not present. Extensive experiments on image, text, and
graph data show consistent performance improvement on out-of-training target
domains. These findings support the practicality of the I.E.D assumption and
the effectiveness of GDUs for domain generalisation. |
---|---|
DOI: | 10.48550/arxiv.2206.12444 |