Gaze estimation methods have significantly matured in recent years, but the large number of eye images required to train deep learning models poses significant privacy risks. In addition, the heterogeneous data distribution across different users can...
The increasing volume and importance of research data leads to the emergence of research data infrastructures in which data management plays an important role. As a consequence, practices at digital archives and libraries change. In this paper, we fo...
Feature engineering is the process of using domain knowledge to extract features from raw data via data mining techniques and is a key step to improve the performance of machine learning algorithms. In the multi-party feature engineering scenario (fe...
In the past few decades, machine learning has revolutionized data processing for large scale applications. Simultaneously, increasing privacy threats in trending applications led to the redesign of classical data training models. In particular, class...
An Industrial Grade Federated Learning Framework (⭐ 6050)
Federated Optimization in Heterogeneous Networks (MLSys '20) (⭐ 723)
An easy-to-use federated learning platform (⭐ 1516)
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, T…
Leveraging real-world health data for machine learning tasks requires addressing many practical challenges, such as distributed data silos, privacy concerns with creating a centralized database from person-specific sensitive data, resource constraint...
This paper introduces Flamingo, a system for secure aggregation of data across a large set of clients. In secure aggregation, a server sums up the private inputs of clients and obtains the result without learning anything about the individual inputs...
Wider adoption of the Grid concept has led to an increasing amount of federated computational, storage and visualisation resources being available to scientists and researchers. Distributed and heterogeneous nature of these resources renders most o...
Calgon Carbon (industrial) Consol Energy (energy) Duolingo (technology) DynaVox (technology) EQT Corporation (Energy) Federated Investors (financial) F
Federated Learning (FL) has recently become an effective approach for cyberattack detection systems, especially in Internet-of-Things (IoT) networks. By distributing the learning process across IoT gateways, FL can improve learning efficiency, reduce...
Flower: A Friendly Federated AI Framework (⭐ 6680)
⚔️ Blades: A Unified Benchmark Suite for Attacks and Defenses in Federated Learning (⭐ 156)
RISSIntel permits federated searching across many systems without requiring the RISSNET user to have a separate user account for each partner system. Millions of intelligence records are available …
Personalized federated learning codebase for research (⭐ 412)
Intelligent Transportation Systems (ITS) leverage Integrated Sensing and Communications (ISAC) to enhance data exchange between vehicles and infrastructure in the Internet of Vehicles (IoV). This integration inevitably increases computing demands, ri...
Research code that accompanies the paper FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity. (⭐ 21)
Federated Knowledge Extraction Framework (⭐ 193)