تقرير
Towards the Reusability and Compositionality of Causal Representations
العنوان: | Towards the Reusability and Compositionality of Causal Representations |
---|---|
المؤلفون: | Talon, Davide, Lippe, Phillip, James, Stuart, Del Bue, Alessio, Magliacane, Sara |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
الوصف: | Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e.g., images. While most CRL works focus on learning causal representations in a single environment, in this work we instead propose a first step towards learning causal representations from temporal sequences of images that can be adapted in a new environment, or composed across multiple related environments. In particular, we introduce DECAF, a framework that detects which causal factors can be reused and which need to be adapted from previously learned causal representations. Our approach is based on the availability of intervention targets, that indicate which variables are perturbed at each time step. Experiments on three benchmark datasets show that integrating our framework with four state-of-the-art CRL approaches leads to accurate representations in a new environment with only a few samples. Comment: Accepted to the 3rd Conference on Causal Learning and Reasoning (CLeaR 2024) |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2403.09830 |
رقم الأكسشن: | edsarx.2403.09830 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |