Domain generalization (DG) is essentially an out-of-distribution problem, aiming to generalize the knowledge learned from multiple source domains to an unseen target domain. The mainstream is to leverage statistical models to model the dependence between data and labels, intending to learn representations independent of domain. Nevertheless, the statistical models are superficial descriptions of reality since they are only required to model dependence instead of the intrinsic causal mechanism. When the dependence changes with the target distribution, the statistic models may fail to generalize. In this regard, we introduce a general structural causal model to formalize the DG problem. Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments. Our goal is to extract the causal factors from inputs and then reconstruct the invariant causal mechanisms. However, the theoretical idea is far from practical of DG since the required causal/non-causal factors are unobserved. We highlight that ideal causal factors should meet three basic properties: separated from the non-causal ones, jointly independent, and causally sufficient for the classification. Based on that, we propose a Causality Inspired Representation Learning (CIRL) algorithm that enforces the representations to satisfy the above properties and then uses them to simulate the causal factors, which yields improved generalization ability. Extensive experimental results on several widely used datasets verify the effectiveness of our approach.
Max-Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);ETH Zurich(苏黎世联邦理工学院);Google Research Amsterdam(谷歌研究院阿姆斯特丹分部);Mila(米拉研究所);University of Montreal(蒙特利尔大学)
A Shift in Perspective on Causality in Domain Generalization
CHAI Hub(CHAI中心);The University of Edinburgh(爱丁堡大学);University of Manchester(曼彻斯特大学);Archimedes, Athena Research Center(阿奇米德与雅典研究所);King's College London(伦敦国王学院);University College London(伦敦大学学院);National and Kapodistrian University of Athens(雅典国家与卡波迪斯蒂亚纳大学)
Robust Residual Correction via Selective Deployment for Time Series Forecasting
University of New South Wales(新南威尔士大学);University of Science and Technology of China(中国科学技术大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
CausalAdv: Adversarial Robustness through the Lens of Causality
University of Science and Technology of China(中国科学技术大学);Hong Kong Baptist University(香港浸会大学);The University of Melbourne(墨尔本大学);The University of Sydney(悉尼大学);RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Carnegie Mellon University(卡内基梅隆大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Emerging Synergies in Causality and Deep Generative Models: A Survey
University of New South Wales(新南威尔士大学);Carnegie Mellon University(卡内基梅隆大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);University of California, San Diego(加利福尼亚大学圣迭戈分校);CSIRO’s Data61(澳大利亚联邦科学与工业研究组织Data61研究院)
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
McGill University(麦吉尔大学);Microsoft Research Montreal(微软研究院蒙特利尔分部);Université de Montréal(蒙特利尔大学);Mila(米拉研究所);Sony AI(索尼人工智能公司);Google DeepMind(谷歌DeepMind)
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Tsinghua-Berkeley Shenzhen Institute(清华-伯克利深圳学院);Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);Graduate School, Tsinghua University(清华大学研究生院)
Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems
King’s College London(伦敦国王学院);Eindhoven University of Technology(埃因霍温理工大学);University of California, San Diego(加州大学圣地亚哥分校);The Alan Turing Institute(艾伦·图灵研究所)
Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations
Shanghai Jiao Tong University(上海交通大学);University of California San Diego(加利福尼亚大学圣迭戈分校);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Feedback System Neural Networks for Inferring Causality in Directed Cyclic Graphs
University of Bergen(卑尔根大学);isee systems inc.(isee系统公司)
本文提出了一种新的因果网络学习算法(FSNN,Feedback System神经网络),它是在构造和分析非线性常微分方程组的基础上提出的。所构建的系统提供了对负责生成动态系统的过去和潜在未来行为的机制的洞察。它也可以用真实的系统变量来解释,提供了一个整体的,因果准确的,系统的理解现实生活中的相互作用,控制观察到的现象。本文演示了一个n维常微分方程模型,可以参数化,以适应测量数据,使用标准的数值优化技术的生成。该模型利用前馈人工神经网络来捕捉非线性,但在复杂系统中的因果关系网络是一个简约和可解释的表示。所生成的模型可以容易且快速地进行实验和分析,以使用循环重要方法(Schoenberg et. al 2019)。该方法的实用性和适用性的演示给出,表明它产生一个准确的,因果关系正确的模型为三状态,非线性,复杂的动态系统的已知来源。推广到其他动态系统与其他数据源,然后讨论。
Higher order definition of causality by optimally conditioned transfer entropy
Institute of Computer Science of the Czech Academy of Sciences(捷克科学院计算机科学研究所);Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University(捷克技术大学核科学与物理工程系);National Institute of Mental Health(国家心理健康研究所)