DIGIC: Domain Generalizable Imitation Learning by Causal Discovery
- URL: http://arxiv.org/abs/2402.18910v1
- Date: Thu, 29 Feb 2024 07:09:01 GMT
- Title: DIGIC: Domain Generalizable Imitation Learning by Causal Discovery
- Authors: Yang Chen, Yitao Liang, Zhouchen Lin
- Abstract summary: Causality has been combined with machine learning to produce robust representations for domain generalization.
We make a different attempt by leveraging the demonstration data distribution to discover causal features for a domain generalizable policy.
We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution.
- Score: 69.13526582209165
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Causality has been combined with machine learning to produce robust
representations for domain generalization. Most existing methods of this type
require massive data from multiple domains to identify causal features by
cross-domain variations, which can be expensive or even infeasible and may lead
to misidentification in some cases. In this work, we make a different attempt
by leveraging the demonstration data distribution to discover the causal
features for a domain generalizable policy. We design a novel framework, called
DIGIC, to identify the causal features by finding the direct cause of the
expert action from the demonstration data distribution via causal discovery.
Our framework can achieve domain generalizable imitation learning with only
single-domain data and serve as a complement for cross-domain variation-based
methods under non-structural assumptions on the underlying causal models. Our
empirical study in various control tasks shows that the proposed framework
evidently improves the domain generalization performance and has comparable
performance to the expert in the original domain simultaneously.
Related papers
- Fine-Tuning Pre-trained Language Models for Robust Causal Representation Learning [26.29386609645171]
Fine-tuning of pre-trained language models (PLMs) has been shown to be effective across various domains.
We show that a robust representation can be derived through a so-called causal front-door adjustment, based on a decomposition assumption.
Our work thus sheds light on the domain generalization problem by introducing links between fine-tuning and causal mechanisms into representation learning.
arXiv Detail & Related papers (2024-10-18T11:06:23Z) - Domain Generalization via Causal Adjustment for Cross-Domain Sentiment
Analysis [59.73582306457387]
We focus on the problem of domain generalization for cross-domain sentiment analysis.
We propose a backdoor adjustment-based causal model to disentangle the domain-specific and domain-invariant representations.
A series of experiments show the great performance and robustness of our model.
arXiv Detail & Related papers (2024-02-22T13:26:56Z) - Normalization Perturbation: A Simple Domain Generalization Method for
Real-World Domain Shifts [133.99270341855728]
Real-world domain styles can vary substantially due to environment changes and sensor noises.
Deep models only know the training domain style.
We propose Normalization Perturbation to overcome this domain style overfitting problem.
arXiv Detail & Related papers (2022-11-08T17:36:49Z) - Gated Domain Units for Multi-source Domain Generalization [14.643490853965385]
Distribution shift (DS) occurs when a dataset at test time differs from the dataset at training time.
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.
arXiv Detail & Related papers (2022-06-24T18:12:38Z) - Decompose to Adapt: Cross-domain Object Detection via Feature
Disentanglement [79.2994130944482]
We design a Domain Disentanglement Faster-RCNN (DDF) to eliminate the source-specific information in the features for detection task learning.
Our DDF method facilitates the feature disentanglement at the global and local stages, with a Global Triplet Disentanglement (GTD) module and an Instance Similarity Disentanglement (ISD) module.
By outperforming state-of-the-art methods on four benchmark UDA object detection tasks, our DDF method is demonstrated to be effective with wide applicability.
arXiv Detail & Related papers (2022-01-06T05:43:01Z) - META: Mimicking Embedding via oThers' Aggregation for Generalizable
Person Re-identification [68.39849081353704]
Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time.
This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
arXiv Detail & Related papers (2021-12-16T08:06:50Z) - Unsupervised Domain Generalization for Person Re-identification: A
Domain-specific Adaptive Framework [50.88463458896428]
Domain generalization (DG) has attracted much attention in person re-identification (ReID) recently.
Existing methods usually need the source domains to be labeled, which could be a significant burden for practical ReID tasks.
We propose a simple and efficient domain-specific adaptive framework, and realize it with an adaptive normalization module.
arXiv Detail & Related papers (2021-11-30T02:35:51Z) - Towards Data-Free Domain Generalization [12.269045654957765]
How can knowledge contained in models trained on different source data domains be merged into a single model that generalizes well to unseen target domains?
Prior domain generalization methods typically rely on using source domain data, making them unsuitable for private decentralized data.
We propose DEKAN, an approach that extracts and fuses domain-specific knowledge from the available teacher models into a student model robust to domain shift.
arXiv Detail & Related papers (2021-10-09T11:44:05Z) - Learning causal representations for robust domain adaptation [31.261956776418618]
In many real-world applications, target domain data may not always be available.
In this paper, we study the cases where at the training phase the target domain data is unavailable.
We propose a novel Causal AutoEncoder (CAE), which integrates deep autoencoder and causal structure learning into a unified model.
arXiv Detail & Related papers (2020-11-12T11:24:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.