Federated learning (FL) is a an emerging technique that can collaboratively train a shared model while keeping the data decentralized, which is a rational solution for distributed GNN training.
A novel ring FL topology as well as a map-reduce based synchronizing method are designed in the proposed RDFL to improve decentralized FL performance and bandwidth utilization.
A recurrent neural network is used as the encoder to learn latent representation from electroencephalogram (EEG) signals, recorded while subjects looked at 50 categories of images.
(2) A dynamic weighting strategy named Consensus Focus to identify both the malicious and irrelevant domains.
Ranked #1 on Domain Adaptation on DomainNet
Federated learning(FL) is a rapidly growing field and many centralized and decentralized FL frameworks have been proposed.
FURL poses two new challenges: (1) data distribution shift (Non-IID distribution) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces.
The experiments show that FML can achieve better performance than alternatives in typical FL setting, and clients can be benefited from FML with different models and tasks.
Federated learning is proposed as a machine learning setting to enable distributed edge devices, such as mobile phones, to collaboratively learn a shared prediction model while keeping all the training data on device, which can not only take full advantage of data distributed across millions of nodes to train a good model but also protect data privacy.
Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning.
Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved.
Ranked #1 on Traffic Prediction on Q-Traffic
Bionic design refers to an approach of generative creativity in which a target object (e. g. a floor lamp) is designed to contain features of biological source objects (e. g. flowers), resulting in creative biologically-inspired design.
However, current architecture of deep networks suffers the privacy issue that users need to give out their data to the model (typically hosted in a server or a cluster on Cloud) for training or prediction.
In this paper, we propose a way of synthesizing realistic images directly with natural language description, which has many useful applications, e. g. intelligent image manipulation.
This demonstrated that, without changing the model architecture and the training algorithm, our model could automatically learn features for sleep stage scoring from different raw single-channel EEGs from different datasets without utilizing any hand-engineered features.
Ranked #2 on Sleep Stage Detection on Sleep-EDF
It's useful to automatically transform an image from its original form to some synthetic form (style, partial contents, etc.
Use of this recording configuration with neural network deconvolution promises to make clinically indicated home sleep studies practical.
This paper presents the contribution to the third 'CHiME' speech separation and recognition challenge including both front-end signal processing and back-end speech recognition.