Qiang Yang

TL;DR: This paper develops a framework to create up-to-date maps with rich knowledge from GPS trajectory collections using novel graph-based clustering techniques with prior knowledge on road design and develops a scale- and orientation-invariant traj-SIFT feature to localize and recognize junctions using a supervised learning framework.

TL;DR: A novel research problem of mining the latent friends of bloggers based on the contents of their blog entries is put forward, and a detailed analysis of the advantages and disadvantages of different approaches are given.

TL;DR: In this paper, the authors investigated the optimal coordinated operation of multiple autonomous distributed generators (DGs) and revealed the potential technical benefit by identifying the optimal network topologies and allocating the critical loads (CLs) to appropriate DGs based on the minimum spanning tree (MST) algorithm with power loss and reliability considerations.

TL;DR: In this article, a transfer learning framework based on POMDP is proposed to learn a personalized dialogue system, which can adapt to different user needs by considering differences between source and target users.

TL;DR: This paper proposes the Federated Stochastic Block Coordinate Descent (FedBCD) to effectively reduce the communication rounds for VFL and shows that when the batch size, sample size and the local iterations are selected appropriately, the algorithm requires O( √T ) communication rounds to achieve O(1/ √ T ) accuracy.