Advances and Open Problems in Federated Learning
Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.
Federated Machine Learning: Concept and Applications
This work proposes building data networks among organizations based on federated mechanisms as an effective solution to allow knowledge to be shared without compromising user privacy.
Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting
The spatiotemporal multi-graph convolution network (ST-MGCN), a novel deep learning model for ride-hailing demand forecasting, is proposed which first encode the non-Euclidean pair-wise correlations among regions into multiple graphs and then explicitly model these correlations using multi- graph convolution.
Federated Learning in Mobile Edge Networks: A Comprehensive Survey
- Wei Yang Bryan Lim, Nguyen Cong Luong, C. Miao
- Computer ScienceIEEE Communications Surveys and Tutorials
- 26 September 2019
In a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved, this raises challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale.
FedML: A Research Library and Benchmark for Federated Machine Learning
FedML is introduced, an open research library and benchmark that facilitates the development of new federated learning algorithms and fair performance comparisons and can provide an efficient and reproducible means of developing and evaluating algorithms for the Federated learning research community.
CoNet: Collaborative Cross Networks for Cross-Domain Recommendation
This paper proposes a novel transfer learning approach for cross-domain recommendation by using neural networks as the base model, which can reduce tens of thousands training examples comparing with non-transfer methods and still has the competitive performance with them.
Secure Federated Matrix Factorization
A secure matrix factorization framework under the federated learning setting, called FedMF, is proposed where the model can be learned when each user only uploads the gradient information to the server, and it is proved that it could still leak users’ raw data.
An Overview of Multi-task Learning
Many areas, including computer vision, bioinformatics, health informatics, speech, natural language processing, web applications and ubiquitous computing, use MTL to improve the performance of the applications involved and some representative works are reviewed.
Hierarchical Attention Transfer Network for Cross-Domain Sentiment Classification
- Zheng Li, Ying Wei, Yu Zhang, Qiang Yang
- Computer ScienceAAAI Conference on Artificial Intelligence
- 26 April 2018
IATN provides an interactive attention transfer mechanism, which can better transfer sentiment across domains by incorporating information of both sentences and aspects by using the common features as a bridge.
- Wenyuan Dai, Qiang Yang, Gui-Rong Xue, Yong Yu
- Computer ScienceInternational Conference on Machine Learning
- 5 July 2008
This paper proposes a co-clustering based self-taught clustering algorithm, which can greatly outperform several state-of-the-art clustering methods when utilizing irrelevant unlabeled auxiliary data.