D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning

Anne-Marie Kermarrec, Erick Lavoie
2022
Conference paper

Abstract

The convergence speed of machine learning models trained with Federated Learning is significantly affected by non-independent and identically distributed (non-IID) data partitions, even more so in a fully decentralized setting without a central server. In this paper, we show that the impact of local class bias, an important type of data non-IIDness, can be significantly reduced by carefully designing the underlying communication topology. We present D-Cliques, a novel topology that reduces gradient bias by grouping nodes in interconnected cliques such that the local joint distribution in a clique is representative of the global class distribution. We also show how to adapt the updates of decentralized SGD to obtain unbiased gradients and implement an effective momentum with D-Cliques. Our empirical evaluation on MNIST and CIFAR10 demonstrates that our approach provides similar convergence speed as a fully-connected topology with a significant reduction in the number of edges and messages. In a 1000-node topology, D-Cliques requires 98% less edges and 96% less total messages, with further possible gains using a small-world topology across cliques.

Official source

https://infoscience.epfl.ch/record/294834?ln=en

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related concepts

Related publications

Stochastic distributed learning with gradient quantization and double-variance reduction

Konstantin Mishchenko, Sebastian Urban Stich

We consider distributed optimization over several devices, each sending incremental model updates to a central server. This setting is considered, for instance, in federated learning. Various schemes have been designed to compress the model updates in order to reduce the overall communication cost. However, existing methods suffer from a significant slowdown due to additional variance omega > 0 coming from the compression operator and as a result, only converge sublinearly. What is needed is a variance reduction technique for taming the variance introduced by compression. We propose the first methods that achieve linear convergence for arbitrary compression operators. For strongly convex functions with condition number kappa, distributed among n machines with a finite-sum structure, each worker having less than in components, we also (i) give analysis for the weakly convex and the non-convex cases and (ii) verify in experiments that our novel variance reduced schemes are more efficient than the baselines. Moreover, we show theoretically that as the number of devices increases, higher compression levels are possible without this affecting the overall number of communications in comparison with methods that do not perform any compression. This leads to a significant reduction in communication cost. Our general analysis allows to pick the most suitable compression for each problem, finding the rig ht balance between additional variance and communication savings. Finally, we also (iii) give analysis for arbitrary quantized updates.

TAYLOR & FRANCIS LTD2022

Detection of curvilinear structures has long been of interest due to its wide range of applications. Large amounts of imaging data could be readily used in many fields, but it is practically not possible to analyze them manually. Hence, the need for automated delineation approaches. In the recent years Computer Vision witnessed a paradigm shift from mathematical modelling to data-driven methods based on Machine Learning. This led to improvements in performance and robustness of the detection algorithms. Nonetheless, most Machine Learning methods are general-purpose and they do not exploit the specificity of the delineation problem. In this thesis, we present learning methods suited for this task and we apply them to various kinds of microscopic and natural images, proving the general applicability of the presented solutions. First, we introduce a topology loss - a new training loss term, which captures higher-level features of curvilinear networks such as smoothness, connectivity and continuity. This is in contrast to most Deep Learning segmentation methods that do not take into account the geometry of the resulting prediction. In order to compute the new loss term, we extract topology features of prediction and ground-truth using a pre-trained network, whose filters are activated by structures at different scales and orientations. We show that this approach yields better results in terms of conventional segmentation metrics and overall topology of the resulting delineation. Although segmentation of curvilinear structures provides useful information, it is not always sufficient. In many cases, such as neuroscience and cartography, it is crucial to estimate the network connectivity. In order to find the graph representation of the structure depicted in the image, we propose an approach for joint segmentation and connection classification. Apart from pixel probabilities, this approach also returns the likelihood of a proposed path being a part of the reconstructed network. We show that segmentation and path classification are closely related tasks and can benefit from the synergy. The aforementioned methods rely on Machine Learning, which requires significant amounts of annotated ground-truth data to train models. The labelling process often requires expertise, it is costly and tiresome. To alleviate this problem, we introduce an Active Learning method that significantly decreases the time spent on annotating images. It queries the annotator only about the most informative examples, in this case the hypothetical paths belonging to the structure of interest. Contrary to conventional Active Learning methods, our approach exploits local consistency of linear paths to pick the ones that stand out from their neighborhood. Our final contribution is a method suited for both Active Learning and proofreading the result, which often requires more time than the automated delineation itself. It investigates edges of the delineation graph and determines the ones that are especially significant for the global reconstruction by perturbing their weights. Our Active Learning and proofreading strategies are combined with a new efficient formulation of an optimal subgraph computation and reduce the annotation effort by up to 80%.

EPFL2019

Designing Augmented Reality for the Classroom

Quentin Bonnard, Sébastien Cuendet, Pierre Dillenbourg

Augmented reality (AR) has recently received a lot of attention in education. Multiple AR systems for learning have been developed and tested through empirical studies often conducted in lab settings. While lab studies can be insightful, they leave out the complexity of a classroom environment. We developed three AR learning environments that have been used in genuine classroom contexts, some of them being now part of classroom regular practices. These systems and the learning activities they provide have been co-designed with teachers, for their own classrooms, through multiple cycles of prototyping and testing. We present here the features that emerged from these co-design cycles and abstract them into design principles. (C) 2013 Elsevier Ltd. All rights reserved.

Elsevier2013

EPFL2019