In federated learning, heterogeneity in the clients' local datasets and computation speeds results in large variations in the number of local updates performed by each client in each communication round. Naive weighted aggregation of such models causes objective inconsistency, that is, the global model converges to a stationary point of a mismatched objective function which can be arbitrarily different from the true objective. This paper provides a general framework to analyze the convergence of federated heterogeneous optimization algorithms. It subsumes previously proposed methods such as FedAvg and FedProx and provides the first principled understanding of the solution bias and the convergence slowdown due to objective inconsistency. Using insights from this analysis, we propose FedNova, a normalized averaging method that eliminates objective inconsistency while preserving fast error convergence.

The Abstraction and Reasoning Corpus (ARC) is a challenging benchmark, introduced to foster AI research towards human-level intelligence. It is a collection of unique tasks about generating colored grids, specified by a few examples only. In contrast to the transformation-based programs of existing work, we introduce object-centric models that are in line with the natural programs produced by humans. Our models can not only perform predictions, but also provide joint descriptions for input/output pairs. The Minimum Description Length (MDL) principle is used to efficiently search the large model space. A diverse range of tasks are solved, and the learned models are similar to the natural programs. We demonstrate the generality of our approach by applying it to a different domain.

The efficiency of Federated Learning (FL) is often affected by both data and device heterogeneities. Data heterogeneity is defined as the heterogeneity of data distributions on different clients. Device heterogeneity is defined as the clients' variant latencies in uploading their local model updates due to heterogeneous conditions of local hardware resources, and causes the problem of staleness when being addressed by asynchronous FL. Traditional schemes of tackling the impact of staleness consider data and device heterogeneities as two separate and independent aspects in FL, but this assumption is unrealistic in many practical FL scenarios where data and device heterogeneities are intertwined. In these cases, traditional schemes of weighted aggregation in FL have been proved to be ineffective, and a better approach is to convert a stale model update into a non-stale one. In this paper, we present a new FL framework that leverages the gradient inversion technique for such conversion, hence efficiently tackling unlimited staleness in clients' model updates. Our basic idea is to use gradient inversion to get estimations of clients' local training data from their uploaded stale model updates, and use these estimations to compute non-stale client model updates. In this way, we address the problem of possible data quality drop when using gradient inversion, while still preserving the clients' local data privacy. We compared our approach with the existing FL strategies on mainstream datasets and models, and experiment results demonstrate that when tackling unlimited staleness, our approach can significantly improve the trained model accuracy by up to 20% and speed up the FL training progress by up to 35%.

Federated learning (FL) is a privacy-preserving paradigm for collaboratively training a global model from decentralized clients. However, the performance of FL is hindered by non-independent and identically distributed (non-IID) data and device heterogeneity. In this work, we revisit this key challenge through the lens of gradient conflicts on the server side. Specifically, we first investigate the gradient conflict phenomenon among multiple clients and reveal that stronger heterogeneity leads to more severe gradient conflicts. To tackle this issue, we propose FedGH, a simple yet effective method that mitigates local drifts through Gradient Harmonization. This technique projects one gradient vector onto the orthogonal plane of the other within conflicting client pairs. Extensive experiments demonstrate that FedGH consistently enhances multiple state-of-the-art FL baselines across diverse benchmarks and non-IID scenarios. Notably, FedGH yields more significant improvements in scenarios with stronger heterogeneity. As a plug-and-play module, FedGH can be seamlessly integrated into any FL framework without requiring hyperparameter tuning.

Since the last decade, it is becoming increasingly clear that Artificial Intelligence is going to be the central technology around which all other advanced technologies will revolve and co-exist. Artificial Intelligence, in simplest terms, refers to'smart' machines or'intelligent' systems which perform tasks that are usually associated with human intelligence and reasoning. Artificial Intelligence (AI), in order to maximize its utility, has been paired with robotics, machine learning, Internet of Things (IoT), and many such technologies. Edge AI computing is one such example of integration of two technologies. As said earlier, edge AI is the combination of two technologies, viz., Edge computing and Artificial Intelligence.

International Men's Health Week is observed in several countries during the week leading up to and including Father's Day. The main goal of this health campaign's annual celebration is to increase awareness of preventable health issues (both physical and emotional) among men and boys, as well as to encourage early disease detection and treatment. This year's Men's Health Week will take place from June 10 to 16. This is a great time for all males to think about their health. Diabetes is a condition in which blood glucose levels in the body grow to dangerously high levels.

Machine learning is no longer seen as something from science fiction, but a tool that can enable significant innovation and one that provides new solutions to some of the world's greatest challenges. As the underlying technology behind intelligent systems, machine learning can be leveraged to build sustainability in the cloud and better understand issues like climate change; offer companies and individuals new financial opportunities; and change lives for the better through network building. Download this whitepaper to learn more about how machine learning is making a significant impact in the work, and how your organisation can bring your machine learning initiatives to life.

Adobe's PDF format has entrenched itself so deeply in US government document pipelines that the number of state-issued documents currently in existence is conservatively estimated to be in the hundreds of millions. Often opaque and lacking metadata, these PDFs – many created by automated systems – collectively tell no stories or sagas; if you don't know exactly what you're looking for, you'll probably never find a pertinent document. And if you did know, you probably didn't need the search. However a new project is using computer vision and other machine learning approaches to change this almost unapproachable mountain of data into a valuable and explorable resource for researchers, historians, journalists and scholars. When the US government discovered Adobe's Portable Document Format (PDF) in the 1990s, it decided that it liked it.

Deep learning is solving biology's deepest secrets at breathtaking speed. Just a month ago, DeepMind cracked a 50-year-old grand challenge: protein folding. A week later, they produced a totally transformative database of more than 350,000 protein structures, including over 98 percent of known human proteins. Structure is at the heart of biological functions. The data dump, set to explode to 130 million structures by the end of the year, allows scientists to foray into previous "dark matter"--proteins unseen and untested--of the human body's makeup.

Through these sophisticated AI and machine learning technologies, the seven-minute film shows how thoroughly convincing deepfakes can be.