5 papers
Practical Validity Conditions for Byzantine-Tolerant Federated Learning
Mélanie Cambus, Darya Melnyk, Tijana MilentijeviÄ +1
Robust aggregation is the core operation in Byzantine-tolerant federated learning. To ensure the quality of aggregation independently of data distribution or attacks, validity cond…
Centroid Approximation with Multidimensional Approximate Agreement Protocols
Melanie Cambus, Darya Melnyk
In this paper, we present distributed fault-tolerant algorithms that approximate the centroid (i.e., the average) of a set of data points in . Our work falls into…
Centroid Approximation for Byzantine-Tolerant Federated Learning
Mélanie Cambus, Darya Melnyk, Tijana MilentijeviÄ +1
Federated learning allows each client to keep its data locally when training machine learning models in a distributed setting. Significant recent research established the requireme…
Approximate Agreement Algorithms for Byzantine Collaborative Learning
Mélanie Cambus, Darya Melnyk, Tijana MilentijeviÄ +1
In Byzantine collaborative learning, clients in a peer-to-peer network collectively learn a model without sharing their data by exchanging and aggregating stochastic gradient e…
A -Approximate Correlation Clustering Algorithm in Dynamic Streams
Mélanie Cambus, Fabian Kuhn, Etna Lindy +2
Grouping together similar elements in datasets is a common task in data mining and machine learning. In this paper, we study streaming algorithms for correlation clustering, where…