Related papers: CFL: On the Use of Characteristic Function Loss fo…
Variable selection poses a significant challenge in causal modeling, particularly within the social sciences, where constructs often rely on inter-related factors such as age, socioeconomic status, gender, and race. Indeed, it has been…
Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularity, it has been observed that Federated Learning yields…
This paper introduces a novel perspective about error in machine learning and proposes inverse feature learning (IFL) as a representation learning approach that learns a set of high-level features based on the representation of error for…
We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts via a differentiable density ratio…
If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem domain. However, this is often not how models are trained and…
Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed…
Federated Learning (FL) enables distributed ML model training on private user data at the global scale. Despite the potential of FL demonstrated in many domains, an in-depth view of its impact on model accuracy remains unclear. In this…
There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling. We consider this observation to be important because having the solution sampling available makes the…
Designing a registration framework for images that do not share the same probability distribution is a major challenge in modern image analytics yet trivial task for the human visual system (HVS). Discrepancies in probability distributions,…
ML models deployed in production often have to face unknown domain changes, fundamentally different from their training settings. Performance prediction models carry out the crucial task of measuring the impact of these changes on model…
Federated learning (FL) allows collaborative machine learning training without sharing private data. While most FL methods assume identical data domains across clients, real-world scenarios often involve heterogeneous data domains.…
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample domains, but where we have many samples in each domain. Our…
Domain classification is the fundamental task in natural language understanding (NLU), which often requires fast accommodation to new emerging domains. This constraint makes it impossible to retrain all previous domains, even if they are…
Machine Learning (ML) models are widely employed to drive many modern data systems. While they are undeniably powerful tools, ML models often demonstrate imbalanced performance and unfair behaviors. The root of this problem often lies in…
Distribution shifts between training and testing samples frequently occur in practice and impede model generalization performance. This crucial challenge thereby motivates studies on domain generalization (DG), which aim to predict the…
Uncertainty is a fundamental aspect of real-world scenarios, where perfect information is rarely available. Humans naturally develop complex internal models to navigate incomplete data and effectively respond to unforeseen or partially…
All famous machine learning algorithms that comprise both supervised and semi-supervised learning work well only under a common assumption: the training and test data follow the same distribution. When the distribution changes, most…
Deep Metric Learning (DML) aims to find representations suitable for zero-shot transfer to a priori unknown test distributions. However, common evaluation protocols only test a single, fixed data split in which train and test classes are…
Generalizing knowledge to unseen domains, where data and labels are unavailable, is crucial for machine learning models. We tackle the domain generalization problem to learn from multiple source domains and generalize to a target domain…
Heterogeneity across devices in federated learning (FL) typically refers to statistical (e.g., non-i.i.d. data distributions) and resource (e.g., communication bandwidth) dimensions. In this paper, we focus on another important dimension…