Related papers: ModelGiF: Gradient Fields for Model Functional Dis…

When a new release of a foundation model is published, practitioners typically need to repeat fine-tuning, even if the same task was already tackled in the previous version. A promising alternative is to reuse the parameter changes (i.e.,…

Federated learning (FL) has emerged as a promising collaborative and secure paradigm for training a model from decentralized data without compromising privacy. Group fairness and client fairness are two dimensions of fairness that are…

Machine learning algorithms relying on deep neural networks recently allowed a great leap forward in artificial intelligence. Despite the popularity of their applications, the efficiency of these algorithms remains largely unexplained from…

Complex systems in science and engineering sometimes exhibit behavior that changes across different regimes. Traditional global models struggle to capture the full range of this complex behavior, limiting their ability to accurately…

The rapid proliferation of large language models (LLMs) has created an unprecedented demand for fine-tuning models for specialized domains, such as medical science. While federated learning (FL) offers a decentralized and privacy-preserving…

This paper presents a performance benchmarking study of a Gradient-Optimized Fuzzy Inference System (GF) classifier against several state-of-the-art machine learning models, including Random Forest, XGBoost, Logistic Regression, Support…

Pretrained Large Language Models (LLMs) achieve strong performance across a wide range of tasks, yet exhibit substantial variability in the various layers' training quality with respect to specific downstream applications, limiting their…

We propose a new method for learning with multi-field categorical data. Multi-field categorical data are usually collected over many heterogeneous groups. These groups can reflect in the categories under a field. The existing methods try to…

This paper discusses the estimation of the generalization gap, the difference between generalization performance and training performance, for overparameterized models including neural networks. We first show that a functional variance, a…

Automatically detecting/segmenting object(s) that blend in with their surroundings is difficult for current models. A major challenge is that the intrinsic similarities between such foreground objects and background surroundings make the…

This paper investigates the critical problem of representation similarity evolution during cross-domain transfer learning, with particular focus on understanding why pre-trained models maintain effectiveness when adapted to medical imaging…

Trajectory prediction is crucial to advance autonomous driving, improving safety, and efficiency. Although end-to-end models based on deep learning have great potential, they often do not consider vehicle dynamic limitations, leading to…

With rapid progress in deep learning, neural networks have been widely used in scientific research and engineering applications as surrogate models. Despite the great success of neural networks in fitting complex systems, two major…

Federated Inference (FI) studies how independently trained and privately owned models can collaborate at inference time without sharing data or model parameters. While recent work has explored secure and distributed inference from disparate…

A well-defined distance on the parameter space is key to evaluating estimators, ensuring consistency, and building confidence sets. While there are typically standard distances to adopt in a continuous space, this is not the case for…

A fundamental challenge in federated learning lies in mixing heterogeneous datasets and classification tasks while minimizing the high communication cost caused by clients as well as the exchange of weight updates with the server over a…

The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine…

The Fr\'echet Inception Distance (FID) has been used to evaluate hundreds of generative models. We introduce FastFID, which can efficiently train generative models with FID as a loss function. Using FID as an additional loss for Generative…

Generative models achieve remarkable results in multiple data domains, including images and texts, among other examples. Unfortunately, malicious users exploit synthetic media for spreading misinformation and disseminating deepfakes.…

Providing various machine learning (ML) applications in the real world, concerns about discrimination hidden in ML models are growing, particularly in high-stakes domains. Existing techniques for assessing the discrimination level of ML…