OOD Generalization

A key challenge in Few-Shot Recognition (FSR) is the scarcity of labeled task-specific data for training. Contemporary methods mitigate this challenge by exploiting pretrained Vision-Language Models (VLMs) for their learned transferable features. Some recent ones augment the scarce data by retrieving relevant yet out-of-distribution (OOD) examples from external data sources. However, they largely overlook an equally fundamental challenge: the absence of validation data for model selection and hyperparameter tuning. As a result, the adapted VLMs overfit the few-shot training data and generalize poorly to OOD test data. We show that retrieved data provide a natural source of validation, but their direct use creates a fundamental paradox. Since the retrieved samples are inherently OOD w.r.t the few-shot ID training data, adapting a VLM to the ID data constantly degrades its performance on the retrieved data. Consequently, conventional validation relying on the accuracy of retrieved data favors no adaptation and prevents improved generalization. To resolve this dilemma, we formulate validation as a multi-objective optimization (MOO) problem between performance gains on the few-shot ID data and the performance preservation on the retrieved data. We introduce a simple yet effective validation strategy by choosing an operating point on the Pareto front of the MOO problem. This strategy enables hyperparameter tuning, which had been unrealistically done by using test data, thereby mitigating overfitting and improving generalization. We integrate it into a stage-wise finetuning pipeline, termed Validation-Enabled Stage-wise Tuning (VEST). Extensive experiments on five established benchmarks show that VEST consistently outperforms existing approaches on both ID and OOD test data.

Predictors often exploit spurious correlations that fail under distribution shift, undermining out-of-distribution (OOD) robustness. Invariant pairs, such as the same object photographed against different backgrounds, directly indicate which variation should not affect prediction. Yet real pair collections are finite and noisy, so they can miss relevant variation or lead a learner to discard predictive information. To learn from such collections, we propose Geometric Robustness Invariant Training (GRIT), which estimates an unstable subspace from the covariance of pair differences in fixed pretrained features and projects it out before fitting a predictor. Because pair processing is separate from predictor fitting, the same projection can accompany ERM or other robustness objectives. Unlike quadratic prediction consistency, which penalizes variation along every direction with nonzero pair covariance, including variation introduced by pair noise, GRIT enforces exact invariance only to the estimated subspace. We bound GRIT's target risk in terms of pair count, noise relative to the weakest clean signal, and selected rank, assuming that the label distribution given a linear projection of the features is invariant across environments. Empirically, GRIT improves the mean OOD accuracy of each of eight learning objectives on ColoredMNIST-INV and Waterbirds-INV and has higher mean accuracy than a prediction-consistency penalty using the same pairs in 15 of 16 settings. On UrbanCars, combining pairs that vary the background with pairs that vary a co-occurring object raises worst-group accuracy above that of either pair type alone.

Out-of-distribution (OOD) generalisation through composition requires a system to discover invariant properties from input-output associations and transfer them to novel inputs and unseen tasks. We argue that confirming compositional learning requires more than OOD evaluation alone: one must also verify that the learned features are genuinely compositional and that the system encodes their compositional rules. We demonstrate this through two tasks with clearly defined OOD metrics, generated via composable high-level abstractions, on which three standard architectures (MLP, CNN, Transformer) and an object-centric, slot-based architecture fail to generalise OOD. We pair these tasks with two novel attention-based architectures featuring an interpretable final hidden layer designed to expose whether compositional representations emerge. One architecture carries an engineered inductive bias that enables near-perfect OOD performance on one task. Our results show that even with appropriate biases and near-perfect OOD accuracy, a model can fail to learn the compositional feature structures necessary for systematic generalisation. The interpretable layer reveals that successful OOD performance is driven by task-specific biases rather than the discovery of reusable compositional primitives. These findings indicate that OOD benchmarks alone are insufficient for evaluating compositionality in neural networks.

Data-driven molecular discovery leverages artificial intelligence/machine learning (AI/ML) and generative modeling to filter and design novel molecules. Discovering novel molecules requires accurate out-of-distribution (OOD) predictions, but ML models struggle to generalize OOD. Currently, no systematic benchmarks exist for molecular OOD prediction tasks. We present $\mathbf{BOOM}$, $\mathbf{b}$enchmarks for $\mathbf{o}$ut-$\mathbf{o}$f-distribution $\mathbf{m}$olecular property predictions: a chemically-informed benchmark for OOD performance on common molecular property prediction tasks. We evaluate over 150 model-task combinations to benchmark deep learning models on OOD performance. Overall, we find that no existing model achieves strong generalization across all tasks: even the top-performing model exhibited an average OOD error 3x higher than in-distribution. Current chemical foundation models do not show strong OOD extrapolation, while models with high inductive bias can perform well on OOD tasks with simple, specific properties. We perform extensive ablation experiments, highlighting how data generation, pre-training, hyperparameter optimization, model architecture, and molecular representation impact OOD performance. Developing models with strong OOD generalization is a new frontier challenge in chemical ML. This open-source benchmark is available at https://github.com/FLASK-LLNL/BOOM

Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the properties of the structures represented in the training distribution. We find that this limitation arises not only from the molecule generation process itself, but also from the poor generalization capabilities of molecular property predictors. We address this challenge by creating a closed-loop molecule generation pipeline with iterative retraining on new quantum chemical simulation data. Compared against static, single-pass generative modeling approaches, only our closed-loop iterative workflow generates molecules with properties extending beyond the training distribution (up to 0.44 standard deviations beyond the original range) and achieves a 79% improvement in out-of-distribution molecule classification accuracy. Furthermore, by conditioning molecular generation on thermodynamic stability data obtained during the iterative loop, the proportion of stable and hence potentially synthesizable molecules generated is 3.5x higher than the next-best model.

Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of maintaining the general performance of the model while allowing it to gain new skills. A valuable goal for all such models is robustness: the ability to perform well on out-of-distribution (OOD) tasks. We assess whether fine-tuning preserves the overall robustness of the pretrained model in image classification, and observed that models pretrained on large datasets exhibited strong catastrophic forgetting and loss of OOD generalization. To systematically assess robustness preservation in fine-tuned models, we propose the Robustness Inheritance Benchmark (ImageNet-RIB). The benchmark, which can be applied to any pretrained model, consists of a set of related but distinct OOD (downstream) tasks and involves fine-tuning on one of the OOD tasks in the set then testing on the rest. We find that though continual learning methods help, fine-tuning reduces robustness across pretrained models. Surprisingly, models pretrained on the largest and most diverse datasets (e.g., LAION-2B) exhibit both larger robustness losses and lower absolute robustness after fine-tuning on small datasets, relative to models pretrained on smaller datasets. We observe this collapse in contrastively pretrained (CLIP) models and their fine-tuned variants, where it grows with pretraining scale; the supervised models we test do not exhibit it. These findings suggest that starting with the strongest foundation model is not necessarily the best approach for performance on specialist tasks. https://jd730.github.io/projects/ImageNet-RIB

This paper establishes the generalization error of pooled min-$\ell_2$-norm interpolation in transfer learning, where data from diverse distributions are available. Min-norm interpolators arise naturally as implicit regularized limits of modern machine learning algorithms. Prior work has characterized their out-of-distribution risk when samples from the test distribution are unavailable during training. In many applications, however, limited test samples may be available at training time, yet properties of min-norm interpolation in this regime remain poorly understood. We address this gap by characterizing the bias and variance of pooled min-$\ell_2$-norm interpolation under both covariate shift and model shift. Our results yield several important implications. In certain cases under model shift, we show that adding data always hurts when the signal-to-noise ratio (SNR) is low. At higher SNR levels, transfer learning is beneficial provided the shift-to-signal ratio falls below a threshold that we characterize explicitly. Under covariate shift, we find that when the source sample size is small relative to the dimension, greater heterogeneity between domains reduces risk, and vice versa. While our model shift results are initially established for Gaussian designs, we extend them to more general designs through a universality argument. To illustrate the broader applicability of our technical tools beyond interpolation learning, we characterize the risk of a bias-corrected estimator that uses the pooled interpolator as an initialization and corrects the resulting bias with target data. On the technical side, we develop a novel anisotropic local law and a Lindeberg-swapping argument, yielding tools that may be of independent interest in random matrix theory and universality analysis. Finally, we supplement our theory with simulations demonstrating the finite-sample efficacy of our results.

Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems. However, most existing CTDG representation learning methods are tailored to in-distribution settings and exhibit limited robustness under out-of-distribution (OOD) shifts. Although recent causal approaches learn invariant representations via interventions, they are primarily designed for static or discrete-time graphs and become computationally prohibitive for CTDGs due to the combinatorial explosion of structural and temporal variations. To address these challenges, we propose CIR, a framework grounded in a novel structural causal model termed the ICCM. To avoid exhaustive interventions, we leverage the Normalized Weighted Geometric Mean (NWGM) to efficiently approximate interventional predictions. We further instantiate ICCM within a practical deep learning architecture that jointly captures invariant structural and temporal patterns through dedicated subgraph extractors, and maintains an environment memory bank to model distributional shifts across evolving contexts. Extensive experiments demonstrate that CIR consistently outperforms existing methods under diverse OOD scenarios.

Invariance to diverse types of image corruption, such as noise, blurring, or colour shifts, is essential to establish robust models in computer vision. Data augmentation has been the major approach in improving the robustness against common corruptions. However, the samples produced by popular augmentation strategies deviate significantly from the underlying data manifold. As a result, performance is skewed toward certain types of corruption. To address this issue, we propose a multi-source vicinal transfer augmentation (VITA) method for generating diverse on-manifold samples. The proposed VITA consists of two complementary parts: tangent transfer and integration of multi-source vicinal samples. The tangent transfer creates initial augmented samples for improving corruption robustness. The integration employs a generative model to characterize the underlying manifold built by vicinal samples, facilitating the generation of on-manifold samples. Our proposed VITA significantly outperforms the current state-of-the-art augmentation methods, demonstrated in extensive experiments on corruption benchmarks. Code: https://github.com/MinghuiChen43/VITA.