Related papers: Factored Latent Analysis for far-field tracking da…
Federated learning (FL) is a distributed machine learning approach involving multiple clients collaboratively training a shared model. Such a system has the advantage of more training data from multiple clients, but data can be…
Federated Learning (FL) has emerged as a machine learning approach able to preserve the privacy of user's data. Applying FL, clients train machine learning models on a local dataset and a central server aggregates the learned parameters…
This work introduces a neural architecture for learning forward models of stochastic environments. The task is achieved solely through learning from temporal unstructured observations in the form of images. Once trained, the model allows…
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…
This paper presents a novel learning analytics method: Transition Network Analysis (TNA), a method that integrates Stochastic Process Mining and probabilistic graph representation to model, visualize, and identify transition patterns in the…
Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of…
We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to…
Federated Learning (FL) has garnered significant attention in manufacturing for its robust model development and privacy-preserving capabilities. This paper contributes to research focused on the robustness of FL models in object detection,…
Inspired by how humans combine direct interaction with action-free experience (e.g., videos), we study world models that learn from heterogeneous data. Standard world models typically rely on action-conditioned trajectories, which limits…
Trajectory inference seeks to recover the temporal dynamics of a population from snapshots of its (uncoupled) temporal marginals, i.e. where observed particles are not tracked over time. Prior works addressed this challenging problem under…
Estimations and applications of factor models often rely on the crucial condition that the number of latent factors is consistently estimated, which in turn also requires that factors be relatively strong, data are stationary and weak…
Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. While many federated learning architectures process data in an online manner, and are hence adaptive by nature, most…
Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data…
Interpretability has become a necessary feature for machine learning models deployed in critical scenarios, e.g. legal system, healthcare. In these situations, algorithmic decisions may have (potentially negative) long-lasting effects on…
In the early observation period of a time series, there might be only a few historic observations available to learn a model. However, in cases where an existing prior set of datasets is available, Meta learning methods can be applicable.…
We present COALA, a vision-centric Federated Learning (FL) platform, and a suite of benchmarks for practical FL scenarios, which we categorize into three levels: task, data, and model. At the task level, COALA extends support from simple…
Federated Learning (FL) enables multiple institutes to train models collaboratively without sharing private data. Current FL research focuses on communication efficiency, privacy protection, and personalization and assumes that the data of…
Subgroup analysis evaluates treatment effects across multiple sub-populations. When subgroups are defined by latent memberships inferred from imperfect measurements, the analysis typically involves two inter-connected models, a latent class…
Learning efficient visual representations across heterogeneous unlabeled datasets remains a central challenge in federated learning. Effective federated representations require features that are jointly informative across clients while…
We consider the problem of learning a linear factor model. We propose a regularized form of principal component analysis (PCA) and demonstrate through experiments with synthetic and real data the superiority of resulting estimates to those…