Out-of-distribution (OOD) generalization is an important issue for Graph Neural Networks (GNNs). Recent works employ different graph editions to generate augmented environments and learn an invariant GNN for generalization. However, the label shift usually occurs in augmentation since graph structural edition inevitably alters the graph label. This brings inconsistent predictive relationships among augmented environments, which is harmful to generalization. To address this issue, we propose \textbf{LiSA}, which generates label-invariant augmentations to facilitate graph OOD generalization. Instead of resorting to graph editions, LiSA exploits \textbf{L}abel-\textbf{i}nvariant \textbf{S}ubgraphs of the training graphs to construct \textbf{A}ugmented environments. Specifically, LiSA first designs the variational subgraph generators to extract locally predictive patterns and construct multiple label-invariant subgraphs efficiently. Then, the subgraphs produced by different generators are collected to build different augmented environments. To promote diversity among augmented environments, LiSA further introduces a tractable energy-based regularization to enlarge pair-wise distances between the distributions of environments. In this manner, LiSA generates diverse augmented environments with a consistent predictive relationship and facilitates learning an invariant GNN. Extensive experiments on node-level and graph-level OOD benchmarks show that LiSA achieves impressive generalization performance with different GNN backbones. Code is available on \url{https://github.com/Samyu0304/LiSA}.
Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization
Department of Computer Science, Purdue University(普渡大学计算机科学系);Department of Computer Science and Engineering, The Ohio State University(俄亥俄州立大学计算机科学与工程系);Department of Industrial and Systems Engineering, The Ohio State University(俄亥俄州立大学工业与系统工程系)
Score-based Conditional Out-of-Distribution Augmentation for Graph Covariate Shift
Institute for Clarity in Documentation(文档清晰研究所);Inria Paris-Rocquencourt(巴黎-罗克琴堡研究所);Rajiv Gandhi University(拉贾·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕勒姆研究实验室);The Pennsylvania State University(宾夕法尼亚州立大学)
Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic Graphs
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);Beijing Wuzi University(北京武术大学)
Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching
Department of Computer Science, University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校计算机科学系);Eshelman School of Pharmacy, University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校埃舍尔曼药学院)
Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
University of British Columbia(不列颠哥伦比亚大学);Google Research(谷歌研究院)
在本文中,我们研究了神经算法推理任务的OOD泛化,其目标是学习算法(例如,排序、广度优先搜索和深度优先搜索)。首先,我们认为,在这种情况下,面向对象的泛化是显着不同的普通OOD设置。例如,在OOD的图像分类,如\emph{accuracy on the line}一般化的一些现象,这里没有观察到,和技术,如数据增强方法没有帮助的假设,许多增强技术往往被违反。其次,我们分析了主要挑战(例如,输入分布偏移、非代表性数据生成和无信息的验证度量),即,CLRS \citep{deepmind2021clrs},包含30个算法推理任务。我们提出了几种解决方案,包括一个简单而有效的修复输入分布偏移和改进的数据生成。最后,我们提出了一个基于注意力的2 WL-图神经网络(GNN)处理器,它补充了消息传递GNN,因此它们的组合在所有算法上平均优于最先进的模型3%。我们的代码可在:\url{https://github.com/smahdavi4/clrs} .
Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
Chair of Cognitive Science, ETH Zürich(认知科学教授职位,苏黎世联邦理工学院);Centre for Human and Machine Intelligence, Frankfurt School(人机智能中心,法兰克福学校);Aisot Technologies AG, D-GESS, ETH Zürich(Aisot技术公司,D-GESS,苏黎世联邦理工学院)
COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
Aalborg University(奥尔堡大学);ENSTA, Institut Polytechnique de Paris(法国国立高等先进技术学校,巴黎综合理工学院);University of Barcelona(巴塞罗那大学);Computer Vision Center(计算机视觉中心)
Harnessing Out-Of-Distribution Examples via Augmenting Content and Style
The University of Sydney(悉尼大学);JD Explore Academy(京东探索研究院);Hong Kong Baptist University(香港浸会大学);The University of Melbourne(墨尔本大学);Nanjing University of Science and Technology(南京理工大学)
Handling Geometric Domain Shifts in Semantic Segmentation of Surgical RGB and Hyperspectral Images
German Cancer Research Center (DKFZ)(德国癌症研究中心);Helmholtz Information and Data Science School for Health(亥姆霍兹健康信息与数据科学学院);Heidelberg University(海德堡大学);National Center for Tumor Diseases (NCT)(国家肿瘤疾病中心);Heidelberg University Hospital(海德堡大学医院);Medical Faculty, Heidelberg University(海德堡大学医学院)
Semantic segmentation of surgical hyperspectral images under geometric domain shifts
German Cancer Research Center (DKFZ)(德国癌症研究中心);Heidelberg University(海德堡大学);National Center for Tumor Diseases (NCT)(国家肿瘤疾病中心);Heidelberg University Hospital(海德堡大学医院)