English
Related papers

Related papers: Graph Out-of-Distribution Generalization with Cont…

200 papers

Background. Commonly, Deep Neural Networks (DNNs) generalize well on samples drawn from a distribution similar to that of the training set. However, DNNs' predictions are brittle and unreliable when the test samples are drawn from a…

Machine Learning · Computer Science 2022-04-01 Matan Haroush , Tzviel Frostig , Ruth Heller , Daniel Soudry

Graphs are a fundamental data structure for representing relational information in domains such as social networks, molecular systems, and knowledge graphs. However, graph learning models often suffer from limited generalization when…

Machine Learning · Computer Science 2026-01-30 Haoyang Li , Haibo Chen , Xin Wang , Wenwu Zhu

This work provides the first theoretical study on the ability of graph Message Passing Neural Networks (gMPNNs) -- such as Graph Neural Networks (GNNs) -- to perform inductive out-of-distribution (OOD) link prediction tasks, where…

Machine Learning · Computer Science 2022-10-11 Yangze Zhou , Gitta Kutyniok , Bruno Ribeiro

With the capacity to capture high-order collaborative signals, Graph Neural Networks (GNNs) have emerged as powerful methods in Recommender Systems (RS). However, their efficacy often hinges on the assumption that training and testing data…

Information Retrieval · Computer Science 2024-02-22 Bohao Wang , Jiawei Chen , Changdong Li , Sheng Zhou , Qihao Shi , Yang Gao , Yan Feng , Chun Chen , Can Wang

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

Machine Learning · Computer Science 2024-07-23 Xuexin Chen , Ruichu Cai , Kaitao Zheng , Zhifan Jiang , Zhengting Huang , Zhifeng Hao , Zijian Li

Graph machine learning has witnessed rapid growth, driving advancements across diverse domains. However, the in-distribution assumption, where training and testing data share the same distribution, often breaks in real-world scenarios,…

Machine Learning · Computer Science 2025-02-13 Tingyi Cai , Yunliang Jiang , Yixin Liu , Ming Li , Changqin Huang , Shirui Pan

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

There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight. Nonetheless, current endeavors mostly focus on Euclidean…

Machine Learning · Computer Science 2024-08-19 Qitian Wu , Hengrui Zhang , Junchi Yan , David Wipf

Distribution shifts between training and testing datasets significantly impair the model performance on graph learning. A commonly-taken causal view in graph invariant learning suggests that stable predictive features of graphs are causally…

Machine Learning · Computer Science 2025-12-10 Bohan Wang , Yurui Chang , Wei Jin , Lu Lin

In recent years, Graph Convolutional Networks (GCNs) have achieved great success in learning from graph-structured data. With the growing tendency of graph nodes and edges, GCN training by single processor cannot meet the demand for time…

Machine Learning · Computer Science 2021-10-08 Taige Zhao , Xiangyu Song , Jianxin Li , Wei Luo , Imran Razzak

This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Xiang Fang , Arvind Easwaran , Blaise Genest , Ponnuthurai Nagaratnam Suganthan

Graph Neural Networks (GNNs) often encounter significant performance degradation under distribution shifts between training and test data, hindering their applicability in real-world scenarios. Recent studies have proposed various methods…

Machine Learning · Computer Science 2025-09-09 Tianjun Yao , Haoxuan Li , Yongqiang Chen , Tongliang Liu , Le Song , Eric Xing , Zhiqiang Shen

This paper studies a novel problem of out-of-distribution graph models merging, which aims to construct a generalized model from multiple graph models pre-trained on different domains with distribution discrepancy. This problem is…

Machine Learning · Computer Science 2026-03-18 Yidi Wang , Ziyue Qiao , Jiawei Gu , Xubin Zheng , Pengyang Wang , Xiaobing Pei , Xiao Luo

Graph Neural Networks (GNNs) have shown great promise in tasks like node and graph classification, but they often struggle to generalize, particularly to unseen or out-of-distribution (OOD) data. These challenges are exacerbated when…

Graph Neural Networks (GNNs) are susceptible to distribution shifts, creating vulnerability and security issues in critical domains. There is a pressing need to enhance the generalizability of GNNs on out-of-distribution (OOD) test data.…

Machine Learning · Computer Science 2024-10-29 Xiaoxue Han , Huzefa Rangwala , Yue Ning

Classification tasks present challenges due to class imbalances and evolving data distributions. Addressing these issues requires a robust method to handle imbalances while effectively detecting out-of-distribution (OOD) samples not…

Machine Learning · Computer Science 2024-09-05 Priyanka Chudasama , Anil Surisetty , Aakarsh Malhotra , Alok Singh

In general, graph representation learning methods assume that the train and test data come from the same distribution. In this work we consider an underexplored area of an otherwise rapidly developing field of graph representation learning:…

Machine Learning · Computer Science 2021-12-08 Beatrice Bevilacqua , Yangze Zhou , Bruno Ribeiro

Graph Neural Networks (GNNs) have shown remarkable performance on graph-structured data. However, recent empirical studies suggest that GNNs are very susceptible to distribution shift. There is still significant ambiguity about why…

Machine Learning · Computer Science 2023-06-07 Qi Zhu , Yizhu Jiao , Natalia Ponomareva , Jiawei Han , Bryan Perozzi

Detecting out-of-distribution (OOD) data is essential for safe deployment of deep neural networks (DNNs). This problem becomes particularly challenging in the presence of long-tailed in-distribution (ID) datasets, often leading to high…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Nimeshika Udayangani , Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Graph neural networks (GNN) have recently emerged as a vehicle for applying deep network architectures to graph and relational data. However, given the increasing size of industrial datasets, in many practical situations the message passing…

Machine Learning · Computer Science 2021-11-16 Qingru Zhang , David Wipf , Quan Gan , Le Song