Related papers: NFL: Robust Learned Index via Distribution Transfo…
Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…
As a promising paradigm federated Learning (FL) is widely used in privacy-preserving machine learning, which allows distributed devices to collaboratively train a model while avoiding data transmission among clients. Despite its immense…
Indexing large-scale databases in main memory is still challenging today. Learned index structures -- in which the core components of classical indexes are replaced with machine learning models -- have recently been suggested to…
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…
Layer normalization (LN) is a widely adopted deep learning technique especially in the era of foundation models. Recently, LN has been shown to be surprisingly effective in federated learning (FL) with non-i.i.d. data. However, exactly why…
Many machine learning algorithms have been developed under the assumption that data sets are already available in batch form. Yet in many application domains data is only available sequentially overtime via compute nodes in different…
Federated learning (FL) emerges as a popular distributed learning schema that learns a model from a set of participating users without sharing raw data. One major challenge of FL comes with heterogeneous users, who may have distributionally…
Federated learning (FL) is a distributed learning paradigm that allows multiple clients to jointly train a shared model while maintaining data privacy. Despite its great potential for domains with strict data privacy requirements, the…
Performative prediction is a framework for learning models that influence the data they intend to predict. We focus on finding classifiers that are performatively stable, i.e. optimal for the data distribution they induce. Standard…
Decision-focused learning (DFL), which differentiates through the KKT conditions, has recently emerged as a powerful approach for predict-then-optimize problems. However, under probabilistic settings, DFL faces three major bottlenecks:…
We propose a federated methodology to learn low-dimensional representations from a dataset that is distributed among several clients. In particular, we move away from the commonly-used cross-entropy loss in federated learning, and seek to…
Conventional diffusion models typically relies on a fixed forward process, which implicitly defines complex marginal distributions over latent variables. This can often complicate the reverse process' task in learning generative…
In this paper, we present FedRewind, a novel approach to decentralized federated learning that leverages model exchange among nodes to address the issue of data distribution shift. Drawing inspiration from continual learning (CL) principles…
Traditional federated optimization methods perform poorly with heterogeneous data (ie, accuracy reduction), especially for highly skewed data. In this paper, we investigate the label distribution skew in FL, where the distribution of labels…
Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some…
Federated Learning (FL) is a promising distributed learning mechanism which still faces two major challenges, namely privacy breaches and system efficiency. In this work, we reconceptualize the FL system from the perspective of network…
Federated Learning (FL) is a distributed framework for collaborative model training over large-scale distributed data, enabling higher performance while maintaining client data privacy. However, the nature of model aggregation at the…
There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such…
We develop an iterative (greedy) deep learning (DL) algorithm which is able to transform an arbitrary probability distribution function (PDF) into the target PDF. The model is based on iterative Optimal Transport of a series of 1D slices,…
This paper addresses the problem of localization, which is inherently non-convex and non-smooth in a federated setting where the data is distributed across a multitude of devices. Due to the decentralized nature of federated environments,…