English
Related papers

Related papers: Learning Causally Invariant Representations for Ou…

200 papers

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As…

Machine Learning · Computer Science 2023-11-21 Haonan Yuan , Qingyun Sun , Xingcheng Fu , Ziwei Zhang , Cheng Ji , Hao Peng , Jianxin Li

Recently, there has been a surge of interest in developing graph neural networks that utilize the invariance principle on graphs to generalize the out-of-distribution (OOD) data. Due to the limited knowledge about OOD data, existing…

Machine Learning · Computer Science 2024-07-17 Tianjun Yao , Yongqiang Chen , Zhenhao Chen , Kai Hu , Zhiqiang Shen , Kun Zhang

Out-of-distribution (OOD) generalization remains a central challenge in deploying deep learning models to real-world scenarios, particularly in domains such as biomedical images, where distribution shifts are both subtle and pervasive.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Haoran Pei , Yuguang Yang , Kexin Liu , Baochang Zhang

Out-of-distribution (OOD) detection poses a significant challenge for Graph Neural Networks (GNNs), particularly in open-world scenarios with varying distribution shifts. Most existing OOD detection methods on graphs primarily focus on…

Machine Learning · Computer Science 2024-10-24 Zhixia He , Chen Zhao , Minglai Shao , Yujie Lin , Dong Li , Qin Tian

Most existing deep learning models are trained based on the closed-world assumption, where the test data is assumed to be drawn i.i.d. from the same distribution as the training data, known as in-distribution (ID). However, when models are…

Machine Learning · Computer Science 2022-11-09 Yixin Liu , Kaize Ding , Huan Liu , Shirui Pan

Out-of-distribution (OOD) generalization in the graph domain is challenging due to complex distribution shifts and a lack of environmental contexts. Recent methods attempt to enhance graph OOD generalization by generating flat environments.…

Machine Learning · Computer Science 2024-06-04 Yinhua Piao , Sangseon Lee , Yijingxiu Lu , Sun Kim

Graph-level representation learning is important in a wide range of applications. Existing graph-level models are generally built on i.i.d. assumption for both training and testing graphs. However, in an open world, models can encounter…

Machine Learning · Computer Science 2024-07-19 Zhihao Ding , Jieming Shi , Shiqi Shen , Xuequn Shang , Jiannong Cao , Zhipeng Wang , Zhi Gong

In this work, we investigate the problem of out-of-distribution (OOD) generalization for unsupervised learning methods on graph data. This scenario is particularly challenging because graph neural networks (GNNs) have been shown to be…

Machine Learning · Computer Science 2023-08-03 Yun Zhu , Haizhou Shi , Zhenshuo Zhang , Siliang Tang

Out-of-distribution (OOD) generalization deals with the prevalent learning scenario where test distribution shifts from training distribution. With rising application demands and inherent complexity, graph OOD problems call for specialized…

Machine Learning · Computer Science 2024-06-06 Xiner Li , Shurui Gui , Youzhi Luo , Shuiwang Ji

This paper introduces a new framework for recovering causal graphs from observational data, leveraging the observation that the distribution of an effect, conditioned on its causes, remains invariant to changes in the prior distribution of…

Machine Learning · Computer Science 2026-02-04 Nang Hung Nguyen , Phi Le Nguyen , Thao Nguyen Truong , Trong Nghia Hoang , Masashi Sugiyama

The inability of deep learning models to handle data drawn from unseen distributions has sparked much interest in unsupervised out-of-distribution (U-OOD) detection, as it is crucial for reliable deep learning models. Despite considerable…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Lars Doorenbos , Raphael Sznitman , Pablo Márquez-Neila

A key challenge in graph out-of-distribution (OOD) detection lies in the absence of ground-truth OOD samples during training. Existing methods are typically optimized to capture features within the in-distribution (ID) data and calculate…

Machine Learning · Computer Science 2025-11-25 Yue Hou , Ruomei Liu , Yingke Su , Junran Wu , Ke Xu

Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to handle distribution shifts, which naturally exist in dynamic…

Machine Learning · Computer Science 2024-03-11 Zeyang Zhang , Xin Wang , Ziwei Zhang , Haoyang Li , Wenwu Zhu

Graph neural networks (GNNs) have achieved impressive performance when testing and training graph data come from identical distribution. However, existing GNNs lack out-of-distribution generalization abilities so that their performance…

Machine Learning · Computer Science 2021-12-15 Haoyang Li , Xin Wang , Ziwei Zhang , Wenwu Zhu

In the context of modern machine learning, models deployed in real-world scenarios often encounter diverse data shifts like covariate and semantic shifts, leading to challenges in both out-of-distribution (OOD) generalization and detection.…

Machine Learning · Computer Science 2024-09-30 Han Wang , Yixuan Li

Causal discovery from i.i.d. observational data is known to be generally ill-posed. We demonstrate that if we have access to the distribution {induced} by a structural causal model, and additional data from (in the best case) \textit{only…

Machine Learning · Statistics 2026-05-15 Francesco Montagna

Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features. Our main observation is that image classifiers may perform poorly on out-of-distribution samples because spurious…

Computer Vision and Pattern Recognition · Computer Science 2022-04-27 Chengzhi Mao , Kevin Xia , James Wang , Hao Wang , Junfeng Yang , Elias Bareinboim , Carl Vondrick

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation…

Machine Learning · Computer Science 2025-03-06 Yiming Xu , Bin Shi , Zhen Peng , Huixiang Liu , Bo Dong , Chen Chen

Graph Out-of-Distribution (OOD), requiring that models trained on biased data generalize to the unseen test data, has a massive of real-world applications. One of the most mainstream methods is to extract the invariant subgraph by aligning…

Machine Learning · Computer Science 2024-02-15 Xuexin Chen , Ruichu Cai , Kaitao Zheng , Zhifan Jiang , Zhengting Huang , Zhifeng Hao , Zijian Li

Graph invariant learning (GIL) seeks invariant relations between graphs and labels under distribution shifts. Recent works try to extract an invariant subgraph to improve out-of-distribution (OOD) generalization, yet existing approaches…

Machine Learning · Computer Science 2026-01-22 Junchi Yan , Fangyu Ding , Jiawei Sun , Zhaoping Hu , Yunyi Zhou , Lei Zhu