Federated Learning using the Federated Averaging algorithm has shown great advantages for large-scale applications that rely on collaborative learning, especially when the training data is either unbalanced or inaccessible due to privacy constraints. We hypothesize that Federated Averaging underestimates the full extent of heterogeneity of data when the aggregation is performed. We propose Precision-weighted Federated Learning 1 a novel algorithm that takes into account the second raw moment (uncentered variance) of the stochastic gradient when computing the weighted average of the parameters of independent models trained in a Federated Learning setting. With Precision-weighted Federated Learning, we address the communication and statistical challenges for the training of distributed models with private data and provide an alternate averaging scheme that leverages the heterogeneity of the data when it has a large diversity of features in its composition. Our method was evaluated using three standard image classification datasets (MNIST, Fashion-MNIST, and CIFAR) with two different data partitioning strategies (independent and identically distributed (IID), and non-identical and non-independent (non-IID)) to measure the performance and speed of our method in resource-constrained environments, such as mobile and IoT devices. The experimental results demonstrate that we can obtain a good balance between computational efficiency and convergence rates with Precision-weighted Federated Learning. Our performance evaluations show 9% better predictions with MNIST, 18% with Fashion-MNIST, and 5% with CIFAR-10 in the non-IID setting. Further reliability evaluations ratify the stability in our method by reaching a 99% reliability index with IID partitions and 96% with non-IID partitions. In addition, we obtained a 20𝑥 speedup on Fashion-MNIST with only 10 clients and up to 37𝑥 with 100 clients participating in the aggregation concurrently per communication round. The results indicate that Precision-weighted Federated Learning is an effective and faster alternative approach for aggregating private data, especially in domains where data is highly heterogeneous.
In image-guided neurosurgery, a registration between the patient and their pre-operative images and the tracking of surgical tools enables GPS-like guidance to the surgeon. However, factors such as brainshift, image distortion, and registration error cause the patient-to-image alignment accuracy to degrade throughout the surgical procedure no longer providing accurate guidance. The authors present a gesture-based method for manual registration correction to extend the usage of augmented reality (AR) neuronavigation systems. The authors’ method, which makes use of the touchscreen capabilities of a tablet on which the AR navigation view is presented, enables surgeons to compensate for the effects of brainshift, misregistration, or tracking errors. They tested their system in a laboratory user study with ten subjects and found that they were able to achieve a median registration RMS error of 3.51 mm on landmarks around the craniotomy of interest. This is comparable to the level of accuracy attainable with previously proposed methods and currently available commercial systems while being simpler and quicker to use. The method could enable surgeons to quickly and easily compensate for most of the observed shift. Further advantages of their method include its ease of use, its small impact on the surgical workflow and its small-time requirement.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.