Search Results for author:
Found 20 papers, 7 papers with code
Evaluating the Energy Consumption of Machine Learning: Systematic Literature Review and Experiments
Monitoring, understanding, and optimizing the energy consumption of Machine Learning (ML) are various reasons why it is necessary to evaluate the energy usage of ML.
Federated Learning for Collaborative Inference Systems: The Case of Early Exit Networks
As Internet of Things (IoT) technology advances, end devices like sensors and smartphones are progressively equipped with AI models tailored to their local memory and computational constraints.
FedStale: leveraging stale client updates in federated learning
Federated learning algorithms, such as FedAvg, are negatively affected by data heterogeneity and partial client participation.
An Online Gradient-Based Caching Policy with Logarithmic Complexity and Regret Guarantees
Recently, a new class of policies has emerged that are robust to varying traffic patterns.
Scalable Decentralized Algorithms for Online Personalized Mean Estimation
In numerous settings, agents lack sufficient data to directly learn a model.
A Cautionary Tale: On the Role of Reference Data in Empirical Privacy Defenses
Within the realm of privacy-preserving machine learning, empirical privacy defenses have been proposed as a solution to achieve satisfactory levels of training data privacy without a significant drop in model utility.
No-Regret Caching with Noisy Request Estimates
Online learning algorithms have been successfully used to design caching policies with regret guarantees.
FedDec: Peer-to-peer Aided Federated Learning
We analyze the convergence of FedDec under the assumptions of non-iid data distribution, partial device participation, and smooth and strongly convex costs, and show that inter-agent communication alleviates the negative impact of infrequent communication rounds with the server by reducing the dependence on the number of local updates $H$ from $O(H^2)$ to $O(H)$.
Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
On the contrary, we show, for convex, strongly convex and non-convex functions, that D-SGD can always recover generalization bounds analogous to those of classical SGD, suggesting that the choice of graph does not matter.
Federated Learning under Heterogeneous and Correlated Client Availability
To this purpose, CA-Fed dynamically adapts the weight given to each client and may ignore clients with low availability and large correlation.
Federated Learning for Data Streams
Federated learning (FL) is an effective solution to train machine learning models on the increasing amount of data generated by IoT devices and smartphones while keeping such data localized.
Local Model Reconstruction Attacks in Federated Learning and their Uses
Additionally, we propose a novel model-based attribute inference attack in federated learning leveraging the local model reconstruction attack.
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
In this work, we propose a novel cross-silo dataset suite focused on healthcare, FLamby (Federated Learning AMple Benchmark of Your cross-silo strategies), to bridge the gap between theory and practice of cross-silo FL.
Personalized Federated Learning through Local Memorization
Federated learning allows clients to collaboratively learn statistical models while keeping their data local.
Efficient passive membership inference attack in federated learning
In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally.
Federated Multi-Task Learning under a Mixture of Distributions
The increasing size of data generated by smartphones and IoT devices motivated the development of Federated Learning (FL), a framework for on-device collaborative training of machine learning models.
Content Placement in Networks of Similarity Caches
Similarity caching systems have recently attracted the attention of the scientific community, as they can be profitably used in many application contexts, like multimedia retrieval, advertising, object recognition, recommender systems and online content-match applications.
Throughput-Optimal Topology Design for Cross-Silo Federated Learning
Federated learning usually employs a client-server architecture where an orchestrator iteratively aggregates model updates from remote clients and pushes them back a refined model.
Dynamic backup workers for parallel machine learning
This paradigm consists of $n$ workers, which iteratively compute updates of the model parameters, and a stateful PS, which waits and aggregates all updates to generate a new estimate of model parameters and sends it back to the workers for a new iteration.
Decentralized gradient methods: does topology matter?
Consensus-based distributed optimization methods have recently been advocated as alternatives to parameter server and ring all-reduce paradigms for large scale training of machine learning models.
