Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder

05/16/2022
by   Tiexin Qin, et al.
0

Domain generalization aims to improve the generalization capability of machine learning systems to out-of-distribution (OOD) data. Existing domain generalization techniques embark upon stationary and discrete environments to tackle the generalization issue caused by OOD data. However, many real-world tasks in non-stationary environments (e.g. self-driven car system, sensor measures) involve more complex and continuously evolving domain drift, which raises new challenges for the problem of domain generalization. In this paper, we formulate the aforementioned setting as the problem of evolving domain generalization. Specifically, we propose to introduce a probabilistic framework called Latent Structure-aware Sequential Autoencoder (LSSAE) to tackle the problem of evolving domain generalization via exploring the underlying continuous structure in the latent space of deep neural networks, where we aim to identify two major factors namely covariate shift and concept shift accounting for distribution shift in non-stationary environments. Experimental results on both synthetic and real-world datasets show that LSSAE can lead to superior performances based on the evolving domain generalization setting.

READ FULL TEXT
research
04/17/2022

NICO++: Towards Better Benchmarking for Domain Generalization

Despite the remarkable performance that modern deep neural networks have...
research
05/01/2023

Dynamic Transfer Learning across Graphs

Transferring knowledge across graphs plays a pivotal role in many high-s...
research
03/09/2020

Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay

Learning in non-stationary environments is one of the biggest challenges...
research
11/05/2022

Adversarial Causal Augmentation for Graph Covariate Shift

Out-of-distribution (OOD) generalization on graphs is drawing widespread...
research
02/03/2023

Learning to Decouple Complex Systems

A complex system with cluttered observations may be a coupled mixture of...
research
04/01/2022

Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes

Learning on synthetic data and transferring the resulting properties to ...
research
08/03/2022

Equivariant Disentangled Transformation for Domain Generalization under Combination Shift

Machine learning systems may encounter unexpected problems when the data...

Please sign up or login with your details

Forgot password? Click here to reset