OOD Generalization

OOD: Out-of-Distribution

Out-of-distribution generalization asks whether models learn patterns that transfer beyond the data they were trained on, such as to new hospitals, locations, time periods, molecular structures, or task compositions. Common approaches include causal and invariant representation learning, domain-generalization methods such as GroupDRO, targeted data augmentation, and physics-informed or compositional models that encode structure. Other strategies adapt models at test time or use prompts, retrieval, uncertainty estimates, and validation proxies to select or adjust predictions under shift. Across vision, language, graphs, science, and robotics, strong in-distribution scores and larger pretraining sets often fail to ensure transfer, leaving realistic shift evaluation and the trade-off between adaptation and preserving useful prior knowledge as central challenges.

Latest papers

399 papers45 papers in the last four weeks, up 29% on the four weeks before. 0.3% of all new papers.

On the Safety of Graph Representation Learning
May 7, 2026Xiaoguang Guo, Zehong Wang, Ziming Li +5Graph Representation Learning Algorithmic Fairness
University of Connecticut · University of Notre Dame
Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models
May 7, 2026Xin Wang, Haibo Chen, Wenxuan Liu +1OOD Generalization Agentic AI
Tsinghua University
Learning beyond Site Bias for OOD Generalization in Brain Networks
May 7, 2026Yingxu Wang, Kunyu Zhang, Yanwu Yang +5Functional Connectivity Domain Generalization
Zhengzhou University · City University of Hong Kong
EGA: Adapting Frozen Encoders for Vector Search with Bounded Out-of-Distribution Degradation
May 7, 2026Dongfang ZhaoOOD Generalization Vision Foundation Model Adaptation
Tacoma School of Engineering and Technology University of Washington
CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
May 6, 2026Yu-Hsi Chen, Abd-Krim SeghouanePrincipal Component Analysis Domain Generalization
The University of Melbourne
Replay-Based Continual Learning for Physics-Informed Neural Operators
May 6, 2026Yizheng Wang, Mohammad Sadegh Eshaghi, Xiaoying Zhuang +2OOD Generalization Replay-Based Continual Learning
Department of Engineering Mechanics, Tsinghua University, Beijing 100084, China · Institute of Photonics, Department of Mathematics and Physics, Leibniz University Hannover, Germany · Institute of Structural Mechanics, Bauhaus-Universität Weimar, Marienstr. 15, D-99423 Weimar, Germany
Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize
May 6, 2026Sarwan AliDeep Learning Optimization Weight Decay
Columbia University, Irving Medical Center, NY, USA
Perturbation is All You Need for Extrapolating Language Models
May 5, 2026Zetai Cen, Jin Zhu, Xinwei Shen +1OOD Generalization Autoregressive Language Modeling
School of Mathematics, University of Bristol · School of Mathematics, University of Birmingham · Department of Statistics, University of Washington +1
Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers
May 5, 2026Hao Yan, Haolin Yang, Yiqiao ZhongTransformer Interpretability Neural Representation Geometry
University of Wisconsin–Madison · University of Chicago
RFPrompt: Prompt-Based Expert Adaptation of the Large Wireless Model for Modulation Classification
May 5, 2026Md Raihan Uddin, Tolunay Seyfi, Fatemeh AfghahWireless Foundation Models Automatic Modulation Classification
Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA
Extrapolation in Statistical Learning with Extreme Value Theory
May 3, 2026Sebastian Engelke, Nicola Gnecco, Anne SabourinOOD Generalization Statistical Learning Theory
Research Institute for Statistics and Information Science, University of Geneva, Switzerland · Department of Mathematics, Imperial College London, United Kingdom · Université Paris Cité, Université Paris-Saclay, ENS Paris-Saclay, CNRS, SSA, INSERM, Centre Borelli, France
Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection
May 2, 2026Tianxiao Li, Zhenglin Huang, Haiquan Wen +10Multimodal Deepfake Detection Explainable Deepfake Detection
University of Liverpool · University of Exeter · The Chinese University of Hong Kong, Shenzhen +1
Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy
May 2, 2026Eleanor QuintDistribution Shift Robustness Ensemble Learning
Department of Computing University of Nebraska–Lincoln Lincoln, NE 68508, USA
Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis
Apr 30, 2026Henrik Voigt, Michael Habeck, Joachim GiesenOOD Generalization LLM-Based Program Synthesis
Friedrich Schiller University · Jena, Germany
Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
Apr 30, 2026Haiyang ZhaoDistribution Shift Robustness OOD Generalization
University of Georgia United States
Diffusion Reconstruction towards Generalizable Audio Deepfake Detection
Apr 29, 2026Bo Cheng, Songjun Cao, Xiaoming Zhang +3Audio Deepfake Detection OOD Generalization
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China · Tencent Youtu Lab, China
SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring
Apr 28, 2026Hector G. Rodriguez, Marcus RohrbachVisual Question Answering VLM Robustness
TU Darmstadt & hessian.AI, Germany
Geometry-free prediction of inertial lift forces in microfluidic devices using deep learning
Apr 27, 2026Jesse Ward-Bond, Ali Mashadian, Timothy C. Y. Chan +1Neural Surrogate Modeling OOD Generalization
aDepartment of Mechanical & Industrial Engineering, University of Toronto · bMechanical Engineering, Purdue University · cDepartment of Materials Science & Engineering, University of Toronto +1
Useful nonrobust features are ubiquitous in biomedical images
Apr 24, 2026Coenraad Mouton, Randle Rabe, Niklas C. Koser +4Healthcare Neural Network Robustness
Section Biomedical Imaging, Department of Radiology and Neuroradiology, University Hospital Schleswig-Holstein, Kiel University · Faculty of Engineering, North-West University, South Africa
Robust Out-of-Distribution Stochastic Optimization
Apr 22, 2026Xianyu Li, Huan Xu, Xiaolin Huang +1Stochastic Optimization OOD Generalization
Department of Automation, Tsinghua University · Antai College of Economics & Management, Shanghai Jiao Tong University · Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
Apr 21, 2026Jeongwhan Choi, Jongwoo Kim, Woosung Kang +1Synthetic Data Pretraining OOD Generalization
KAIST Daejeon, Republic of Korea
Superficial Success vs. Internal Breakdown: An Empirical Study of Generalization in Adaptive Multi-Agent Systems
Apr 21, 2026Namyoung So, Seokgyu Jang, Taeuk KimMulti-Agent Coordination OOD Generalization
Department of Computer Science, Hanyang University, Seoul, Republic of Korea
TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning
Apr 18, 2026Siyang Li, Yize Chen, Zijie Zhu +4Time Series Forecasting OOD Generalization
HKUST(GZ) Guangzhou, China · University of Alberta Edmonton, Canada · Alibaba Cloud Guangzhou, China +3
Late Fusion Neural Operators for Extrapolation Across Parameter Space in Partial Differential Equations
Apr 17, 2026Eva van Tegelen, Taniya Kapoor, George A. K. van Voorn +2Surrogate Modeling PDE Surrogate Modeling
Artificial Intelligence Group, Wageningen University and Research, Netherlands · Mathematical and Statistical Methods, Wageningen University and Research, Netherlands
Autonomous Vehicle Collision Avoidance With Racing Parameterized Deep Reinforcement Learning
Apr 17, 2026Shathushan Sivashangaran, Vihaan Dutta, Apoorva Khairnar +2OOD Generalization Autonomous Driving
Virginia Commonwealth University, Richmond, VA 23284, USA · University of Michigan, Ann Arbor, MI 48109, USA · Virginia Tech, Blacksburg, VA 24061, USA
Spotlights and Blindspots: Evaluating Machine-Generated Text Detection
Apr 17, 2026Kevin Stowe, Kailash PatilAI-Generated Text Detection Language Model Generation Evaluation
Pindrop
OT on the Map: Quantifying Domain Shifts in Geographic Space
Apr 17, 2026Haoran Zhang, Livia Betti, Konstantin Klemmer +2Distribution Shift Geospatial Representation Learning
Harvard University · University of Colorado Boulder · LGND AI, Inc. +3
Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval
Apr 13, 2026Hao Xu, Rite Bo, Fausto Giunchiglia +2In-Context Learning Language Model Robustness
College of Computer Science and Technology, Jilin University, China · Department of Information Engineering and Computer Science, University of Trento, Italy
Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
Apr 10, 2026Huanran Chen, Huaqing Zhang, Xiao Li +3Language Model Pretraining Neural Network Generalization
Tsinghua University · ByteDance Seed
On the Role of DAG topology in Energy-Aware Cloud Scheduling : A GNN-Based Deep Reinforcement Learning Approach
Apr 10, 2026Anas Hattay, Fred Ngole Mboula, Eric Gascard +1Cloud Computing Reinforcement Learning
CEA, List, Université Paris-Saclay, France · Université Grenoble Alpes, CNRS, Grenoble INP, G-SCOP, France

May 7, 2026J/K move · Enter open · S save

On the Safety of Graph Representation Learning

Xiaoguang Guo, Zehong Wang, Ziming Li, Shawn Spitzel+4

University of Connecticut · University of Notre Dame

Graph Representation Learning Algorithmic Fairness OOD Generalization Graph Robustness

Open paper AskPDF arXiv

Graph representation learning (GRL) has evolved from topology-only graph embeddings to task-specific supervised GNNs, and more recently to reusable representations and graph foundation models (GFMs). However, existing evaluations mainly measure clean transfer, adaptation, and task coverage. It remains unclear whether GRL methods stay reliable when deployment stresses affect graph signals, graph contexts, label support, structural groups, or predictive evidence. We introduce GRL-Safety, a multi-axis safety evaluation benchmark for GRL. GRL-Safety evaluates twelve representative methods, spanning topology-only embedding methods, supervised GNNs, self-supervised graph models, and GFMs, on twenty-five graph datasets under standardized evaluation conditions while preserving method-native adaptation. The evaluation covers five safety axes: corruption robustness, OOD generalization, class imbalance, fairness, and interpretation, with per-axis and sub-condition reporting rather than a single aggregate score. Our analysis yields three cross-axis insights that can inspire future research. First, safety behavior is shaped by the interaction between representation design and the stressed graph factor, rather than by method family alone. Second, foundation-era methods show axis-specific strengths rather than broad safety dominance. Third, several deployment regimes remain difficult even for the best evaluated method, revealing capability gaps that require new robustness, adaptation, or training objectives beyond model selection. The benchmark, evaluation protocols, and code are available at: https://github.com/GXG-CS/GRL-Safety.