Conformal prediction guarantees degrade under distribution shift. We study this using COVID-19 as a natural experiment across 8 supply chain tasks. Despite identical severe feature turnover (Jaccard approximately 0), coverage drops vary from 0% to 86.7%, spanning two orders of magnitude. Using SHapley Additive exPlanations (SHAP) analysis, we find catastrophic failures correlate with single-feature dependence (rho = 0.714, p = 0.047). Catastrophic tasks concentrate importance in one feature (4.5x increase), while robust tasks redistribute across many (10-20x). Quarterly retraining restores catastrophic task coverage from 22% to 41% (+19 pp, p = 0.04), but provides no benefit for robust tasks (99.8% coverage). Exploratory analysis of 4 additional tasks with moderate feature stability (Jaccard 0.13-0.86) reveals feature stability, not concentration, determines robustness, suggesting concentration effects apply specifically to severe shifts. We provide a decision framework: monitor SHAP concentration before deployment; retrain quarterly if vulnerable (>40% concentration); skip retraining if robust.

While tabular machine learning has achieved remarkable success, temporal distribution shifts pose significant challenges in real-world deployment, as the relationships between features and labels continuously evolve. Static models assume fixed mappings to ensure generalization, whereas adaptive models may overfit to transient patterns, creating a dilemma between robustness and adaptability. In this paper, we analyze key factors essential for constructing an effective dynamic mapping for temporal tabular data. We discover that evolving feature semantics-particularly objective and subjective meanings-introduce concept drift over time. Crucially, we identify that feature transformation strategies are able to mitigate discrepancies in feature representations across temporal stages. Motivated by these insights, we propose a feature-aware temporal modulation mechanism that conditions feature representations on temporal context, modulating statistical properties such as scale and skewness. By aligning feature semantics across time, our approach achieves a lightweight yet powerful adaptation, effectively balancing generalizability and adaptability. Benchmark evaluations validate the effectiveness of our method in handling temporal shifts in tabular data.

Time-series forecasting finds broad applications in real-world scenarios. Due to the dynamic nature of time series data, it is important for time-series forecasting models to handle potential distribution shifts over time. In this paper, we initially identify two types of distribution shifts in time series: concept drift and temporal shift. We acknowledge that while existing studies primarily focus on addressing temporal shift issues in time series forecasting, designing proper concept drift methods for time series forecasting has received comparatively less attention. Motivated by the need to address potential concept drift, while conventional concept drift methods via invariant learning face certain challenges in time-series forecasting, we propose a soft attention mechanism that finds invariant patterns from both lookback and horizon time series. Additionally, we emphasize the critical importance of mitigating temporal shifts as a preliminary to addressing concept drift. In this context, we introduce ShifTS, a method-agnostic framework designed to tackle temporal shift first and then concept drift within a unified approach. Extensive experiments demonstrate the efficacy of ShifTS in consistently enhancing the forecasting accuracy of agnostic models across multiple datasets, and outperforming existing concept drift, temporal shift, and combined baselines.

Conformers have shown great results in speech processing due to their ability to capture both local and global interactions. In this work, we utilize a self-supervised contrastive learning framework to train conformer-based encoders that are capable of generating unique embeddings for small segments of audio, generalizing well to previously unseen data. We achieve state-of-the-art results for audio retrieval tasks while using only 3 seconds of audio to generate embeddings. Our models are almost completely immune to temporal misalignments and achieve state-of-the-art results in cases of other audio distortions such as noise, reverb or extreme temporal stretching. Code and models are made publicly available and the results are easy to reproduce as we train and test using popular and freely available datasets of different sizes.

Deep tabular models have demonstrated remarkable success on i.i.d. data, excelling in a variety of structured data tasks. However, their performance often deteriorates under temporal distribution shifts, where trends and periodic patterns are present in the evolving data distribution over time. In this paper, we explore the underlying reasons for this failure in capturing temporal dependencies. We begin by investigating the training protocol, revealing a key issue in how model selection perform. While existing approaches use temporal ordering for splitting validation set, we show that even a random split can significantly improve model performance. By minimizing the time lag between training data and test time, while reducing the bias in validation, our proposed training protocol significantly improves generalization across various methods. Furthermore, we analyze how temporal data affects deep tabular representations, uncovering that these models often fail to capture crucial periodic and trend information. To address this gap, we introduce a plug-and-play temporal embedding method based on Fourier series expansion to learn and incorporate temporal patterns, offering an adaptive approach to handle temporal shifts. Our experiments demonstrate that this temporal embedding, combined with the improved training protocol, provides a more effective and robust framework for learning from temporal tabular data.

For medical imaging AI models to be clinically impactful, they must generalize. However, this goal is hindered by (i) diverse types of distribution shifts, such as temporal, demographic, and label shifts, and (ii) limited diversity in datasets that are siloed within single medical institutions. While these limitations have spurred interest in federated learning, current evaluation benchmarks fail to evaluate different shifts simultaneously. However, in real healthcare settings, multiple types of shifts co-exist, yet their impact on medical imaging performance remains unstudied. In response, we introduce FedMedICL, a unified framework and benchmark to holistically evaluate federated medical imaging challenges, simultaneously capturing label, demographic, and temporal distribution shifts. We comprehensively evaluate several popular methods on six diverse medical imaging datasets (totaling 550 GPU hours). Furthermore, we use FedMedICL to simulate COVID-19 propagation across hospitals and evaluate whether methods can adapt to pandemic changes in disease prevalence. We find that a simple batch balancing technique surpasses advanced methods in average performance across FedMedICL experiments. This finding questions the applicability of results from previous, narrow benchmarks in real-world medical settings.

Benchmarks that closely reflect downstream application scenarios are essential for the streamlined adoption of new research in tabular machine learning (ML). In this work, we examine existing tabular benchmarks and find two common characteristics of industry-grade tabular data that are underrepresented in the datasets available to the academic community. First, tabular data often changes over time in real-world deployment scenarios. This impacts model performance and requires time-based train and test splits for correct model evaluation. Yet, existing academic tabular datasets often lack timestamp metadata to enable such evaluation. Second, a considerable portion of datasets in production settings stem from extensive data acquisition and feature engineering pipelines. For each specific dataset, this can have a different impact on the absolute and relative number of predictive, uninformative, and correlated features, which in turn can affect model selection. To fill the aforementioned gaps in academic benchmarks, we introduce TabReD -- a collection of eight industry-grade tabular datasets covering a wide range of domains from finance to food delivery services. We assess a large number of tabular ML models in the feature-rich, temporally-evolving data setting facilitated by TabReD. We demonstrate that evaluation on time-based data splits leads to different methods ranking, compared to evaluation on random splits more common in academic benchmarks. Furthermore, on the TabReD datasets, MLP-like architectures and GBDT show the best results, while more sophisticated DL models are yet to prove their effectiveness.

Membership inference (MI) attacks try to determine if a data sample was used to train a machine learning model. For foundation models trained on unknown Web data, MI attacks can be used to detect copyrighted training materials, measure test set contamination, or audit machine unlearning. Unfortunately, we find that evaluations of MI attacks for foundation models are flawed, because they sample members and non-members from different distributions. For 8 published MI evaluation datasets, we show that blind attacks -- that distinguish the member and non-member distributions without looking at any trained model -- outperform state-of-the-art MI attacks. Existing evaluations thus tell us nothing about membership leakage of a foundation model's training data.