scholar.google.com › citations
We propose employing a simple, general multi-task learning objective, and analyze the ability of the objective to achieve a favorable trade-off between ...
In this work, we propose using a multi-task learning objective to address the competing constraints of accuracy, fairness, and robustness in federated learning.
(PDF) Federated Multi-Task Learning for Competing Constraints
www.researchgate.net › ... › Federalism
Dec 8, 2020 · Federated learning involves training statistical models in massive, heterogeneous networks. Naively minimizing an aggregate loss function in ...
May 30, 2017 · Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices.
Missing: Competing Constraints.
In federated learning, multiple clients collaboratively train a machine learning model without sharing their local data.
In this project, we explore multi-task learning, a technique that learns separate but related models for each device in the network, as a unified approach to ...
Dec 8, 2020 · Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and ...
The proposed method outperforms a wide range of competitive baselines in both classification and regression settings ... ing with joint sparsity constraints. In ...
We propose the System Anomaly Detection and Multi-Classification based on Multi-Task Feature Fusion Federated Learning (SADMC-MT-FF-FL) framework.
MOCHA: Federated Multi-Task Learning, Smith et al, NeurIPS 2017. [White Paper] Federated Learning: Challenges, Methods, and Future Directions, Li et al,. IEEE ...