{"total":116,"rows":[{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220,"area":null},{"id":"2201.12872","title":"Discovering Invariant Rationales for Graph Neural Networks","created":"2022-01-30","cited_by_count":188,"area":null},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2202.02466","title":"Handling Distribution Shifts on Graphs: An Invariance Perspective","created":"2022-02-05","cited_by_count":164,"area":null},{"id":"2102.10395","title":"On Calibration and Out-of-domain Generalization","created":"2021-02-20","cited_by_count":134,"area":null},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"area":null},{"id":"2106.04496","title":"Towards a Theoretical Framework of Out-of-Distribution Generalization","created":"2021-06-08","cited_by_count":94,"area":null},{"id":"2111.13839","title":"Towards Principled Disentanglement for Domain Generalization","created":"2021-11-27","cited_by_count":91,"area":null},{"id":"2106.06333","title":"Invariant Information Bottleneck for Domain Generalization","created":"2021-06-11","cited_by_count":86,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2111.10657","title":"Generalizing Graph Neural Networks on Out-Of-Distribution Graphs","created":"2021-11-20","cited_by_count":71,"area":null},{"id":"2202.06856","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","created":"2022-02-14","cited_by_count":69,"area":null},{"id":"2206.02013","title":"Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis","created":"2022-06-04","cited_by_count":55,"area":null},{"id":"2303.13662","title":"Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment","created":"2023-03-23","cited_by_count":48,"area":null},{"id":"2203.11528","title":"Out-of-distribution Generalization with Causal Invariant Transformations","created":"2022-03-22","cited_by_count":45,"area":null},{"id":"2102.12353","title":"Nonlinear Invariant Risk Minimization: A Causal Approach","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2106.12108","title":"Near-Optimal Linear Regression under Distribution Shift","created":"2021-06-23","cited_by_count":42,"area":null},{"id":"2310.19035","title":"Does Invariant Graph Learning via Environment Augmentation Learn Invariance?","created":"2023-10-29","cited_by_count":42,"area":null},{"id":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41,"area":null},{"id":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41,"area":null},{"id":"2206.07766","title":"Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2211.02843","title":"Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift","created":"2022-11-05","cited_by_count":38,"area":null},{"id":"2304.11327","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","created":"2023-04-22","cited_by_count":35,"area":null},{"id":"2203.15516","title":"Rich Feature Construction for the Optimization-Generalization Dilemma","created":"2022-03-24","cited_by_count":34,"area":null},{"id":"2103.11163","title":"An Empirical Framework for Domain Generalization in Clinical Settings","created":"2021-03-20","cited_by_count":32,"area":null},{"id":"2201.12919","title":"Provable Domain Generalization via Invariant-Feature Subspace Recovery","created":"2022-01-30","cited_by_count":32,"area":null},{"id":"2202.05436","title":"Minimax Regret Optimization for Robust Machine Learning under Distribution Shift","created":"2022-02-11","cited_by_count":31,"area":null},{"id":"2106.09913","title":"Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2201.07708","title":"Debiased Graph Neural Networks with Agnostic Label Selection Bias","created":"2022-01-19","cited_by_count":25,"area":null},{"id":"2504.06969","title":"Towards LLMs Robustness to Changes in Prompt Format Styles","created":"2025-04-09","cited_by_count":21,"area":null},{"id":"2103.02477","title":"Regularizing towards Causal Invariance: Linear Models with Proxies","created":"2021-03-03","cited_by_count":20,"area":null},{"id":"2206.05263","title":"Causal Balancing for Domain Generalization","created":"2022-06-10","cited_by_count":20,"area":null},{"id":"2105.14529","title":"On the benefits of representation regularization in invariance based domain generalization","created":"2021-05-30","cited_by_count":17,"area":null},{"id":"2303.03092","title":"Environment Invariant Linear Least Squares","created":"2023-03-06","cited_by_count":17,"area":null},{"id":"2109.11990","title":"Optimization-based Causal Estimation from Heterogenous Environments","created":"2021-09-24","cited_by_count":16,"area":null},{"id":"2211.00184","title":"FL Games: A Federated Learning Framework for Distribution Shifts","created":"2022-10-31","cited_by_count":14,"area":null},{"id":"2310.12803","title":"Data Augmentations for Improved (Large) Language Model Generalization","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2404.04669","title":"Domain Generalisation via Imprecise Learning","created":"2024-04-06","cited_by_count":14,"area":null},{"id":"2106.12124","title":"Secure Domain Adaptation with Multiple Sources","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2106.09777","title":"On Invariance Penalties for Risk Minimization","created":"2021-06-17","cited_by_count":10,"area":null},{"id":"2106.11560","title":"Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge","created":"2021-06-22","cited_by_count":10,"area":null},{"id":"2303.02343","title":"What Is Missing in IRM Training and Evaluation? Challenges and Solutions","created":"2023-03-04","cited_by_count":10,"area":null},{"id":"2412.13573","title":"Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2205.14546","title":"The Missing Invariance Principle Found -- the Reciprocal Twin of Invariant Risk Minimization","created":"2022-05-29","cited_by_count":8,"area":null},{"id":"2305.01134","title":"PGrad: Learning Principal Gradients For Domain Generalization","created":"2023-05-02","cited_by_count":8,"area":null},{"id":"2103.12947","title":"Meta-Learned Invariant Risk Minimization","created":"2021-03-24","cited_by_count":7,"area":null},{"id":"2405.04715","title":"Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning","created":"2024-05-07","cited_by_count":7,"area":null},{"id":"2410.23889","title":"GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning","created":"2024-10-31","cited_by_count":7,"area":null},{"id":"2106.08112","title":"Contextualizing Meta-Learning via Learning to Decompose","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2208.06987","title":"The Causal Structure of Domain Invariant Supervised Representation Learning","created":"2022-08-15","cited_by_count":5,"area":null},{"id":"2212.09082","title":"On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization","created":"2022-12-18","cited_by_count":5,"area":null},{"id":"2301.12067","title":"Learning Optimal Features via Partial Invariance","created":"2023-01-28","cited_by_count":5,"area":null},{"id":"2309.10301","title":"Prominent Roles of Conditionally Invariant Components in Domain Adaptation: Theory and Algorithms","created":"2023-09-19","cited_by_count":5,"area":null},{"id":"2312.03580","title":"Invariance & Causal Representation Learning: Prospects and Limitations","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2404.19644","title":"MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2411.02444","title":"MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learning","created":"2024-11-02","cited_by_count":5,"area":null},{"id":"2208.10027","title":"Learning Invariant Representations under General Interventions on the Response","created":"2022-08-22","cited_by_count":4,"area":null},{"id":"2211.11243","title":"Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning","created":"2022-11-21","cited_by_count":4,"area":null},{"id":"2402.02851","title":"Enhancing Compositional Generalization via Compositional Feature Alignment","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2410.23461","title":"Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2503.00429","title":"DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing","created":"2025-03-01","cited_by_count":4,"area":null},{"id":"2201.10460","title":"Conditional entropy minimization principle for learning domain invariant representation features","created":"2022-01-25","cited_by_count":3,"area":null},{"id":"2305.05087","title":"Large-Scale Study of Temporal Shift in Health Insurance Claims","created":"2023-05-08","cited_by_count":3,"area":null},{"id":"2307.00558","title":"Conditionally Invariant Representation Learning for Disentangling Cellular Heterogeneity","created":"2023-07-02","cited_by_count":3,"area":null},{"id":"2406.09745","title":"How Does Distribution Matching Help Domain Generalization: An Information-theoretic Analysis","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2502.02710","title":"Achievable distributional robustness when the robust risk is only partially identified","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2505.21626","title":"Learning where to learn: Training data distribution optimization for scientific machine learning","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2202.02150","title":"Correcting Confounding via Random Selection of Background Variables","created":"2022-02-04","cited_by_count":2,"area":null},{"id":"2309.09555","title":"Multi-dimensional domain generalization with low-rank structures","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2310.15766","title":"Robust Learning via Conditional Prevalence Adjustment","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2403.01420","title":"The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing","created":"2024-03-03","cited_by_count":2,"area":null},{"id":"2407.18428","title":"Weighted Risk Invariance: Domain Generalization under Invariant Feature Shift","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2412.11850","title":"Causal Invariance Learning via Efficient Nonconvex Optimization","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2502.10716","title":"Why Domain Generalization Fail? A View of Necessity and Sufficiency","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2504.02996","title":"Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.07378","title":"Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2509.23095","title":"Causally-Enhanced Reinforcement Policy Optimization","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2606.01092","title":"A Fiber Criterion for Representation Identifiability in Supervised Learning","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2112.09346","title":"Balancing Fairness and Robustness via Partial Invariance","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2203.15549","title":"Invariance Learning based on Label Hierarchy","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2205.15196","title":"PAC Generalization via Invariant Representations","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2210.15000","title":"Trade-off between reconstruction loss and feature alignment for domain generalization","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2307.11972","title":"Out-of-Distribution Optimality of Invariant Risk Minimization","created":"2023-07-22","cited_by_count":1,"area":null},{"id":"2309.13377","title":"Learning Invariant Representations with a Nonparametric Nadaraya-Watson Head","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2311.00966","title":"Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2312.09758","title":"Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2502.12413","title":"DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2507.03146","title":"Set Valued Predictions For Robust Domain Generalization","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2507.04006","title":"Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing","created":"2025-07-05","cited_by_count":1,"area":null},{"id":"2106.03234","title":"A call for better unit testing for invariant risk minimisation","created":"2021-06-06","cited_by_count":0,"area":null},{"id":"2109.05934","title":"Task Guided Compositional Representation Learning for ZDA","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2205.11101","title":"FL Games: A federated learning framework for distribution shifts","created":"2022-05-23","cited_by_count":0,"area":null},{"id":"2207.12876","title":"Repeated Environment Inference for Invariant Learning","created":"2022-07-26","cited_by_count":0,"area":null},{"id":"2207.13865","title":"Diversity Boosted Learning for Domain Generalization with Large Number of Domains","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2208.07798","title":"Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization","created":"2022-08-16","cited_by_count":0,"area":null},{"id":"2210.16034","title":"A Survey on Causal Representation Learning and Future Work for Medical Image Analysis","created":"2022-10-28","cited_by_count":0,"area":null}],"next_cursor":"100"}