The generalization of machine learning (ML) models to out-of-distribution
(OOD) examples remains a key challenge in extracting information from upcoming
astronomical surveys. Interpretability approaches are a natural way to gain
insights into the OOD generalization problem. We use Centered Kernel Alignment
(CKA), a similarity measure metric of neural network representations, to
examine the relationship between representation similarity and performance of
pre-trained Convolutional Neural Networks (CNNs) on the CAMELS Multifield
Dataset. We find that when models are robust to a distribution shift, they
produce substantially different representations across their layers on OOD
data. However, when they fail to generalize, these representations change less
from layer to layer on OOD data. We discuss the potential application of
similarity representation in guiding model design, training strategy, and
mitigating the OOD problem by incorporating CKA as an inductive bias during
training.

机器学习模型在处理来自未来天文调查的离域样本时依然面临挑战，解释性方法通过使用相似性度量来检查预训练卷积神经网络在中心核对齐方面的性能与表示相似性之间的关系，发现当模型对分布变化具有稳健性时，在离域数据上，图像在网络层之间的表示会有较大变化；然而，当模型无法泛化时，在离域数据上，这些表示在网络层之间的变化较小。讨论了这种相似性表示在模型设计、训练策略以及通过在训练过程中加入中心核对齐作为归纳偏差来缓解离域问题方面的潜在应用。

大规模天文调查中的样本外泛化：健壮网络学习相似表示

Towards out-of-distribution generalization in large-scale astronomical  surveys: robust networks learn similar representations

The problem of interpreting the decisions of machine learning is a
well-researched and important. We are interested in a specific type of machine
learning model that deals with graph data called graph neural networks.
Evaluating interpretability approaches for graph neural networks (GNN)
specifically are known to be challenging due to the lack of a commonly accepted
benchmark. Given a GNN model, several interpretability approaches exist to
explain GNN models with diverse (sometimes conflicting) evaluation
methodologies. In this paper, we propose a benchmark for evaluating the
explainability approaches for GNNs called Bagel. In Bagel, we firstly propose
four diverse GNN explanation evaluation regimes -- 1) faithfulness, 2)
sparsity, 3) correctness. and 4) plausibility. We reconcile multiple evaluation
metrics in the existing literature and cover diverse notions for a holistic
evaluation. Our graph datasets range from citation networks, document graphs,
to graphs from molecules and proteins. We conduct an extensive empirical study
on four GNN models and nine post-hoc explanation approaches for node and graph
classification tasks. We open both the benchmarks and reference implementations
and make them available at this https URL.

本文提出了一个叫做 Bagel 的基准来评估解释 graph neural networks 的取向，并通过使用多样的图数据集和解释方法来阐述四种不同的解释评估体系 -- 准确性、连通性、正确性和可能性。