English
Related papers

Related papers: Assaying Out-Of-Distribution Generalization in Tra…

200 papers

Ensuring generalization to unseen environments remains a challenge. Domain shift can lead to substantially degraded performance unless shifts are well-exercised within the available training environments. We introduce a simple robust…

Machine Learning · Computer Science 2021-10-20 Yilun Xu , Tommi Jaakkola

Data fusion and transfer learning are rapidly growing fields that enhance model performance for a target population by leveraging other related data sources or tasks. The challenges lie in the various potential heterogeneities between the…

Machine Learning · Statistics 2025-08-19 Jing Wang , HaiYing Wang , Kun Chen

Systematic, compositional generalization beyond the training distribution remains a core challenge in machine learning -- and a critical bottleneck for the emergent reasoning abilities of modern language models. This work investigates…

Machine Learning · Computer Science 2025-10-17 Awni Altabaa , Siyu Chen , John Lafferty , Zhuoran Yang

Machine learning algorithms typically assume that training and test examples are drawn from the same distribution. However, distribution shift is a common problem in real-world applications and can cause models to perform dramatically worse…

Machine Learning · Computer Science 2022-06-22 Huaxiu Yao , Yu Wang , Sai Li , Linjun Zhang , Weixin Liang , James Zou , Chelsea Finn

Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three…

Computation and Language · Computer Science 2024-10-15 Xinzhe Li , Ming Liu , Shang Gao , Wray Buntine

Detecting out-of-distribution (OOD) instances is crucial for the reliable deployment of machine learning models in real-world scenarios. OOD inputs are commonly expected to cause a more uncertain prediction in the primary task; however,…

Machine Learning · Computer Science 2024-05-22 Mohammad Azizmalayeri , Ameen Abu-Hanna , Giovanni Cinà

Generalization beyond the training distribution is a core challenge in machine learning. The common practice of mixing and shuffling examples when training neural networks may not be optimal in this regard. We show that partitioning the…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Damien Teney , Ehsan Abbasnejad , Anton van den Hengel

"Effective robustness" measures the extra out-of-distribution (OOD) robustness beyond what can be predicted from the in-distribution (ID) performance. Existing effective robustness evaluations typically use a single test set such as…

Machine Learning · Computer Science 2023-10-31 Zhouxing Shi , Nicholas Carlini , Ananth Balashankar , Ludwig Schmidt , Cho-Jui Hsieh , Alex Beutel , Yao Qin

Deep neural networks tend to make overconfident predictions and often require additional detectors for misclassifications, particularly for safety-critical applications. Existing detection methods usually only focus on adversarial attacks…

Machine Learning · Computer Science 2023-07-07 Julia Lust , Alexandru P. Condurache

Adversarial training may be regarded as standard training with a modified loss function. But its generalization error appears much larger than standard training under standard loss. This phenomenon, known as robust overfitting, has…

Machine Learning · Computer Science 2024-02-13 Runzhi Tian , Yongyi Mao

Failure of machine learning models to generalize to new data is a core problem limiting the reliability of AI systems, partly due to the lack of simple and robust methods for comparing new data to the original training dataset. We propose a…

Machine Learning · Computer Science 2025-02-26 W. Max Schreyer , Christopher Anderson , Reid F. Thompson

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

Most research designing novel predictive models, or employing existing ones, assumes that training and testing data are independent and identically distributed. In practice, the data encountered at serving time often deviate from the…

Machine Learning · Computer Science 2026-03-30 Hanyu Duan , Yi Yang , Ahmed Abbasi , Kar Yan Tam

Data modification, either via additional training datasets, data augmentation, debiasing, and dataset filtering, has been proposed as an effective solution for generalizing to out-of-domain (OOD) inputs, in both natural language processing…

Computation and Language · Computer Science 2022-03-16 Tejas Gokhale , Swaroop Mishra , Man Luo , Bhavdeep Singh Sachdeva , Chitta Baral

Adversarial robustness continues to be a major challenge for deep learning. A core issue is that robustness to one type of attack often fails to transfer to other attacks. While prior work establishes a theoretical trade-off in robustness…

Machine Learning · Computer Science 2023-06-27 Adam Ibrahim , Charles Guille-Escuret , Ioannis Mitliagkas , Irina Rish , David Krueger , Pouya Bashivan

Detecting test-time distribution shift has emerged as a key capability for safely deployed machine learning models, with the question being tackled under various guises in recent years. In this paper, we aim to provide a consolidated view…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Hongjun Wang , Sagar Vaze , Kai Han

Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This…

Machine Learning · Computer Science 2018-12-31 Rowan McAllister , Gregory Kahn , Jeff Clune , Sergey Levine

We propose a regularisation strategy of classical machine learning algorithms rooted in causality that ensures robustness against distribution shifts. Building upon the anchor regression framework, we demonstrate how incorporating a…

Machine Learning · Statistics 2025-03-12 Homer Durand , Gherardo Varando , Nathan Mankovich , Gustau Camps-Valls

Scientific machine learning (ML) endeavors to develop generalizable models with broad applicability. However, the assessment of generalizability is often based on heuristics. Here, we demonstrate in the materials science setting that…

Recent studies have addressed the concern of detecting and rejecting the out-of-distribution (OOD) samples as a major challenge in the safe deployment of deep learning (DL) models. It is desired that the DL model should only be confident…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Umar Khalid , Ashkan Esmaeili , Nazmul Karim , Nazanin Rahnavard