Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Mattias Åkesson

Scalable federated machine learning with FEDn

Feb 27, 2021
Morgan Ekmefjord, Addi Ait-Mlouk, Sadi Alawadi, Mattias Åkesson, Desislava Stoyanova, Ola Spjuth, Salman Toor, Andreas Hellander

Figure 1 for Scalable federated machine learning with FEDn

Figure 2 for Scalable federated machine learning with FEDn

Figure 3 for Scalable federated machine learning with FEDn

Figure 4 for Scalable federated machine learning with FEDn

Federated machine learning has great promise to overcome the input privacy challenge in machine learning. The appearance of several projects capable of simulating federated learning has led to a corresponding rapid progress on algorithmic aspects of the problem. However, there is still a lack of federated machine learning frameworks that focus on fundamental aspects such as scalability, robustness, security, and performance in a geographically distributed setting. To bridge this gap we have designed and developed the FEDn framework. A main feature of FEDn is to support both cross-device and cross-silo training settings. This makes FEDn a powerful tool for researching a wide range of machine learning applications in a realistic setting.

Via

Access Paper or Ask Questions

Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computation

Jan 31, 2020
Mattias Åkesson, Prashant Singh, Fredrik Wrede, Andreas Hellander

Figure 1 for Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computation

Figure 2 for Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computation

Figure 3 for Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computation

Figure 4 for Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computation

Approximate Bayesian Computation is widely used in systems biology for inferring parameters in stochastic gene regulatory network models. Its performance hinges critically on the ability to summarize high-dimensional system responses such as time series into a few informative, low-dimensional summary statistics. The quality of those statistics critically affect the accuracy of the inference. Existing methods to select the best subset out of a pool of candidate statistics do not scale well with large pools. Since it is imperative for good performance this becomes a serious bottleneck when doing inference on complex and high-dimensional problems. This paper proposes a convolutional neural network architecture for automatically learning informative summary statistics of temporal responses. We show that the proposed network can effectively circumvent the statistics selection problem as a preprocessing step to ABC for a challenging inference problem learning parameters in a high-dimensional stochastic genetic oscillator. We also study the impact of experimental design on network performance by comparing different data richness and different data acquisition strategies.

Via

Access Paper or Ask Questions