In this paper we present a world model, which learns causal features using
the invariance principle. In particular, we use contrastive unsupervised
learning to learn the invariant causal features, which enforces invariance
across augmentations of irrelevant parts or styles of the observation. The
world-model-based reinforcement learning methods independently optimize
representation learning and the policy. Thus naive contrastive loss
implementation collapses due to a lack of supervisory signals to the
representation learning module. We propose an intervention invariant auxiliary
task to mitigate this issue. Specifically, we utilize depth prediction to
explicitly enforce the invariance and use data augmentation as style
intervention on the RGB observation space. Our design leverages unsupervised
representation learning to learn the world model with invariant causal
features. Our proposed method significantly outperforms current
state-of-the-art model-based and model-free reinforcement learning methods on
out-of-distribution point navigation tasks on the iGibson dataset. Moreover,
our proposed model excels at the sim-to-real transfer of our perception
learning module. Finally, we evaluate our approach on the DeepMind control
suite and enforce invariance only implicitly since depth is not available.
Nevertheless, our proposed model performs on par with the state-of-the-art
counterpart.

运用不变性原则的世界模型，通过对比非相关部分或观察风格的差异性，使用对比无监督学习，学习不变因果特点，提出了一个新的改进型辅助任务方法，取得了 iGibson 数据集上优秀的表现

具有不变因果特征的世界模型对比无监督学习

Contrastive Unsupervised Learning of World Model with Invariant Causal Features

Despite recent success in using the invariance principle for
out-of-distribution (OOD) generalization on Euclidean data (e.g., images),
studies on graph data are still limited. Different from images, the complex
nature of graphs poses unique challenges to adopting the invariance principle.
In particular, distribution shifts on graphs can appear in a variety of forms
such as attributes and structures, making it difficult to identify the
invariance. Moreover, domain or environment partitions, which are often
required by OOD methods on Euclidean data, could be highly expensive to obtain
for graphs. To bridge this gap, we propose a new framework, called Causality
Inspired Invariant Graph LeArning (CIGA), to capture the invariance of graphs
for guaranteed OOD generalization under various distribution shifts.
Specifically, we characterize potential distribution shifts on graphs with
causal models, concluding that OOD generalization on graphs is achievable when
models focus only on subgraphs containing the most information about the causes
of labels. Accordingly, we propose an information-theoretic objective to
extract the desired subgraphs that maximally preserve the invariant intra-class
information. Learning with these subgraphs is immune to distribution shifts.
Extensive experiments on 16 synthetic or real-world datasets, including a
challenging setting -- DrugOOD, from AI-aided drug discovery, validate the
superior OOD performance of CIGA.

该研究提出了一种新的框架，Causality Inspired Invariant Graph LeArning (CIGA)，通过使用因果模型来确定图表上的潜在分布偏移，从而捕获图表的不变性，以在各种分布偏移下保证 OOD 泛化性能。

学习因果不变表示以实现图上的跨分布泛化

Learning Causally Invariant Representations for Out-of-Distribution  Generalization on Graphs

The invariance principle from causality is at the heart of notable approaches
such as invariant risk minimization (IRM) that seek to address
out-of-distribution (OOD) generalization failures. Despite the promising
theory, invariance principle-based approaches fail in common classification
tasks, where invariant (causal) features capture all the information about the
label. Are these failures due to the methods failing to capture the invariance?
Or is the invariance principle itself insufficient? To answer these questions,
we revisit the fundamental assumptions in linear regression tasks, where
invariance-based approaches were shown to provably generalize OOD. In contrast
to the linear regression tasks, we show that for linear classification tasks we
need much stronger restrictions on the distribution shifts, or otherwise OOD
generalization is impossible. Furthermore, even with appropriate restrictions
on distribution shifts in place, we show that the invariance principle alone is
insufficient. We prove that a form of the information bottleneck constraint
along with invariance helps address key failures when invariant features
capture all the information about the label and also retains the existing
success when they do not. We propose an approach that incorporates both of
these principles and demonstrate its effectiveness in several experiments.

通过在线性分类任务中的实验证明了仅仅使用不变性原理是不够的，利用信息瓶颈限制的形式加入不变性原则可以解决当因果特征占据标签信息的时候分类模型的失效问题。

不变性原理遇见信息瓶颈：超出分布泛化

Invariance Principle Meets Information Bottleneck for  Out-of-Distribution Generalization

In this paper we study functions with low influences on product probability
spaces. The analysis of boolean functions with low influences has become a
central problem in discrete Fourier analysis. It is motivated by fundamental
questions arising from the construction of probabilistically checkable proofs
in theoretical computer science and from problems in the theory of social
choice in economics.
We prove an invariance principle for multilinear polynomials with low
influences and bounded degree; it shows that under mild conditions the
distribution of such polynomials is essentially invariant for all product
spaces. Ours is one of the very few known non-linear invariance principles. It
has the advantage that its proof is simple and that the error bounds are
explicit. We also show that the assumption of bounded degree can be eliminated
if the polynomials are slightly ``smoothed''; this extension is essential for
our applications to ``noise stability''-type problems.
In particular, as applications of the invariance principle we prove two
conjectures: the ``Majority Is Stablest'' conjecture from theoretical computer
science, which was the original motivation for this work, and the ``It Ain't
Over Till It's Over'' conjecture from social choice theory.

研究了在积概率空间中具有低影响力函数的问题，证明了具有低影响力和有界次数的多线性多项式的不变性原理，且边际条件下的分布在所有乘积空间中实质上是不变的，从而解决了在理论计算机科学中构建概率可检验证明和经济社会选择理论中的问题。