English
Related papers

Related papers: Graphs Generalization under Distribution Shifts

200 papers

Living in a complex world like ours makes it unacceptable that a practical implementation of a machine learning system assumes a closed world. Therefore, it is necessary for such a learning-based system in a real world environment, to be…

Computer Vision and Pattern Recognition · Computer Science 2020-03-05 Jens Bayer , David Münch , Michael Arens

Transfer learning refers to the transfer of knowledge or information from a relevant source domain to a target domain. However, most existing transfer learning theories and algorithms focus on IID tasks, where the source/target samples are…

Machine Learning · Computer Science 2023-03-21 Jun Wu , Jingrui He , Elizabeth Ainsworth

We study the problem of lifelong graph learning in an open-world scenario, where a model needs to deal with new tasks and potentially unknown classes. We utilize Out-of-Distribution (OOD) detection methods to recognize new classes and adapt…

Machine Learning · Computer Science 2023-10-20 Marcel Hoffmann , Lukas Galke , Ansgar Scherp

Deep network models perform excellently on In-Distribution (ID) data, but can significantly fail on Out-Of-Distribution (OOD) data. While developing methods focus on improving OOD generalization, few attention has been paid to evaluating…

Machine Learning · Computer Science 2021-11-22 Rui Hu , Jitao Sang , Jinqiang Wang , Rui Hu , Chaoquan Jiang

Real-world machine learning applications often face simultaneous covariate and semantic shifts, challenging traditional domain generalization and out-of-distribution (OOD) detection methods. We introduce Meta-learned Across Domain…

Machine Learning · Computer Science 2024-11-06 Haoliang Wang , Chen Zhao , Feng 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

Out-of-distribution (OOD) detection is important for deploying machine learning models in the real world, where test data from shifted distributions can naturally arise. While a plethora of algorithmic approaches have recently emerged for…

Machine Learning · Computer Science 2021-12-03 Peyman Morteza , Yixuan Li

In the field of Machine Learning (ML) and data-driven applications, one of the significant challenge is the change in data distribution between the training and deployment stages, commonly known as distribution shift. This paper outlines…

Machine Learning · Computer Science 2025-07-30 Lakpa Tamang , Mohamed Reda Bouadjenek , Richard Dazeley , Sunil Aryal

In real-world applications, it is important and desirable to learn a model that performs well on out-of-distribution (OOD) data. Recently, causality has become a powerful tool to tackle the OOD generalization problem, with the idea resting…

Machine Learning · Statistics 2022-03-25 Ruoyu Wang , Mingyang Yi , Zhitang Chen , Shengyu Zhu

Deploying machine learning in open environments presents the challenge of encountering diverse test inputs that differ significantly from the training data. These out-of-distribution samples may exhibit shifts in local or global features…

Machine Learning · Computer Science 2024-03-19 Jiawei Li , Sitong Li , Shanshan Wang , Yicheng Zeng , Falong Tan , Chuanlong Xie

It is common practice of the outlier mining community to repurpose classification datasets toward evaluating various detection models. To that end, often a binary classification dataset is used, where samples from one of the classes is…

Machine Learning · Computer Science 2021-05-20 Lingxiao Zhao , Leman Akoglu

We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD algorithms either rely on restricted assumptions or fail to exploit environment information in training data. In this work, we propose to…

Machine Learning · Computer Science 2023-11-02 Shurui Gui , Meng Liu , Xiner Li , Youzhi Luo , Shuiwang Ji

Large language models (LLMs) such as GPT-4 sometimes appear to be creative, solving novel tasks often with a few demonstrations in the prompt. These tasks require the models to generalize on distributions different from those from training…

Computation and Language · Computer Science 2024-12-31 Jiajun Song , Zhuoyan Xu , Yiqiao Zhong

Graph Neural Network-based methods face privacy leakage risks due to the introduction of topological structures about the targets, which allows attackers to bypass the target's prior knowledge of the sensitive attributes and realize…

Machine Learning · Computer Science 2025-05-27 Jinyan Wang , Liu Yang , Yuecen Wei , Jiaxuan Si , Chenhao Guo , Qingyun Sun , Xianxian Li , Xingcheng Fu

Out-of-distribution generalization (OODG) is a longstanding challenge for neural networks. This challenge is quite apparent in tasks with well-defined variables and rules, where explicit use of the rules could solve problems independently…

Machine Learning · Computer Science 2022-12-14 Andrew J. Nam , Mustafa Abdool , Trevor Maxfield , James L. McClelland

Machine learning models often degrade when deployed on data distributions different from their training data. Challenging conventional validation paradigms, we demonstrate that higher in-distribution (ID) bias can lead to better…

Machine Learning · Computer Science 2025-06-03 Ruixuan Chen , Wentao Li , Jiahui Xiao , Yuchen Li , Yimin Tang , Xiaonan Wang

Existing methods for graph out-of-distribution (OOD) detection typically depend on training graph neural network (GNN) classifiers using a substantial amount of labeled in-distribution (ID) data. However, acquiring high-quality labeled…

Machine Learning · Computer Science 2025-03-31 Haoyan Xu , Zhengtao Yao , Yushun Dong , Ziyi Wang , Ryan A. Rossi , Mengyuan Li , Yue Zhao

Gradient-based meta-learning (GBML) algorithms are able to fast adapt to new tasks by transferring the learned meta-knowledge, while assuming that all tasks come from the same distribution (in-distribution, ID). However, in the real world,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Min Zhang , Zifeng Zhuang , Zhitao Wang , Donglin Wang , Wenbin Li

The existing methods learn geographic network representations through deep graph neural networks (GNNs) based on the i.i.d. assumption. However, the spatial heterogeneity and temporal dynamics of geographic data make the out-of-distribution…

Machine Learning · Computer Science 2025-03-26 Yuhan Wang , Silu He , Qinyao Luo , Hongyuan Yuan , Ling Zhao , Jiawei Zhu , Haifeng Li

Graph Transformer has demonstrated impressive capabilities in the field of graph representation learning. However, existing approaches face two critical challenges: (1) most models suffer from exponentially increasing computational…

‹ Prev 1 4 5 6 7 8 10 Next ›