Search Results for author: Olof Mogren

Found 19 papers, 7 papers with code

Concept-aware clustering for decentralized deep learning under temporal shift

no code implementations22 Jun 2023 Marcus Toftås, Emilie Klefbom, Edvin Listo Zec, Martin Willbo, Olof Mogren

Decentralized deep learning requires dealing with non-iid data across clients, which may also change over time due to temporal shifts.


Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas

1 code implementation4 Apr 2023 Aleksis Pirinen, Olof Mogren, Mårten Västerdal

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.

Private Node Selection in Personalized Decentralized Learning

no code implementations30 Jan 2023 Edvin Listo Zec, Johan Östman, Olof Mogren, Daniel Gillblad

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).

Privacy Preserving

EFFGAN: Ensembles of fine-tuned federated GANs

no code implementations23 Jun 2022 Ebba Ekblom, Edvin Listo Zec, Olof Mogren

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.

Federated Learning

Decentralized adaptive clustering of deep nets is beneficial for client collaboration

1 code implementation17 Jun 2022 Edvin Listo Zec, Ebba Ekblom, Martin Willbo, Olof Mogren, Sarunas Girdzijauskas

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.


Decentralized federated learning of deep neural networks on non-iid data

1 code implementation18 Jul 2021 Noa Onoszko, Gustav Karlsson, Olof Mogren, Edvin Listo Zec

We tackle the non-convex problem of learning a personalized deep learning model in a decentralized setting.

Federated Learning

Scaling Federated Learning for Fine-tuning of Large Language Models

no code implementations1 Feb 2021 Agrin Hilmkil, Sebastian Callh, Matteo Barbieri, Leon René Sütfeld, Edvin Listo Zec, Olof Mogren

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.

Federated Learning Sentiment Analysis +2

Federated learning using mixture of experts

no code implementations1 Jan 2021 Edvin Listo Zec, John Martinsson, Olof Mogren, Leon René Sütfeld, Daniel Gillblad

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.

Federated Learning

Specialized federated learning using a mixture of experts

1 code implementation5 Oct 2020 Edvin Listo Zec, Olof Mogren, John Martinsson, Leon René Sütfeld, Daniel Gillblad

In federated learning, clients share a global model that has been trained on decentralized local client data.

Federated Learning

Adversarial representation learning for private speech generation

1 code implementation16 Jun 2020 David Ericsson, Adam Östberg, Edvin Listo Zec, John Martinsson, Olof Mogren

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.

Privacy Preserving Representation Learning

Adversarial representation learning for synthetic replacement of private attributes

no code implementations14 Jun 2020 John Martinsson, Edvin Listo Zec, Daniel Gillblad, Olof Mogren

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.

Representation Learning

Character-based recurrent neural networks for morphological relational reasoning

no code implementations WS 2017 Olof Mogren, Richard Johansson

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.

Language Modelling Morphological Analysis +3

Named Entity Recognition in Swedish Health Records with Character-Based Deep Bidirectional LSTMs

1 code implementation WS 2016 Simon Almgren, Sean Pavlov, Olof Mogren

We propose an approach for named entity recognition in medical data, using a character-based deep bidirectional recurrent neural network.

Boundary Detection Feature Engineering +3

C-RNN-GAN: Continuous recurrent neural networks with adversarial training

3 code implementations29 Nov 2016 Olof Mogren

Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks.

Cannot find the paper you are looking for? You can Submit a new open access paper.