Decentralized deep learning requires dealing with non-iid data across clients, which may also change over time due to temporal shifts.
To the best of our knowledge, we are the first to tackle the task of dense water flow intensity prediction; earlier works have considered predicting flow intensities at a sparse set of locations at a time.
In this paper, we propose a novel approach for privacy-preserving node selection in personalized decentralized learning, which we refer to as Private Personalized Decentralized Learning (PPDL).
This is an even harder problem when the data is decentralized over several clients in a federated learning setup, as problems such as client drift and non-iid data make it hard for federated averaging to converge.
We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks.
We tackle the non-convex problem of learning a personalized deep learning model in a decentralized setting.
We perform an extensive sweep over the number of clients, ranging up to 32, to evaluate the impact of distributed compute on task performance in the federated averaging setting.
In this paper, we propose a federated learning framework using a mixture of experts to balance the specialist nature of a locally trained model with the generalist knowledge of a global model in a federated learning setting.
In federated learning, clients share a global model that has been trained on decentralized local client data.
The model is trained in two steps: first to filter sensitive information in the spectrogram domain, and then to generate new and private information independent of the filtered one.
Data privacy is an increasingly important aspect of many real-world Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods often fail to produce convincing output.
We also show that using the auxiliary task of learning the relation type speeds up convergence and improves the prediction accuracy for the word generation task.
We propose an approach for named entity recognition in medical data, using a character-based deep bidirectional recurrent neural network.
Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks.