Global Multiclass Classification from Heterogeneous Local Models

05/21/2020
by   Surin Ahn, et al.
5

Multiclass classification problems are most often solved by either training a single centralized classifier on all K classes, or by reducing the problem to multiple binary classification tasks. This paper explores the uncharted region between these two extremes: How can we solve the K-class classification problem by combining the predictions of smaller classifiers, each trained on an arbitrary number of classes R ∈{2, 3, ..., K}? We present a mathematical framework for answering this question, and derive bounds on the number of classifiers (in terms of K and R) needed to accurately predict the true class of an unlabeled sample under both adversarial and stochastic assumptions. By exploiting a connection to the classical set cover problem in combinatorics, we produce an efficient, near-optimal scheme (with respect to the number of classifiers) for designing such configurations of classifiers, which recovers the well-known one-vs.-one strategy as a special case when R=2. Experiments with the MNIST and CIFAR-10 datasets show that our scheme is capable of matching the performance of centralized classifiers in practice. The results suggest that our approach offers a promising direction for solving the problem of data heterogeneity which plagues current federated learning methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/14/2019

Binary Classification using Pairs of Minimum Spanning Trees or N-ary Trees

One-class classifiers are trained with target class only samples. Intuit...
research
02/15/2023

FedABC: Targeting Fair Competition in Personalized Federated Learning

Federated learning aims to collaboratively train models without accessin...
research
07/01/2020

Making Use of NXt to Nothing: The Effect of Class Imbalances on DGA Detection Classifiers

Numerous machine learning classifiers have been proposed for binary clas...
research
08/16/2021

Reducing the Communication Cost of Federated Learning through Multistage Optimization

A central question in federated learning (FL) is how to design optimizat...
research
09/23/2019

Detection of Classifier Inconsistencies in Image Steganalysis

In this paper, a methodology to detect inconsistencies in classification...
research
09/26/2019

Lower Bounds on Adversarial Robustness from Optimal Transport

While progress has been made in understanding the robustness of machine ...
research
01/01/2023

Federated Learning with Client-Exclusive Classes

Existing federated classification algorithms typically assume the local ...

Please sign up or login with your details

Forgot password? Click here to reset