Recent Projects

With the emergence of 5G, IoT, edge computing, and edge intelligence, collective intelligence becomes a key trend in many wireless distributed systems, such as a group of drones and the Internet of Vehicles (IoV). Various new computing and communication paradigms emerge in this area, e.g., federated learning, coded computation. In this project, we analyze theoretical frameworks, propose algorithms to solve this type of problem, and test our algorithms in a proof-of-concept test platform.

Recommender systems will become the future information acquisition technology by allowing users to obtain content based on their intent other than explicitly searching for prespecified content. In the first part of this project, we are developing learning algorithms to realize effective and accurate recommendations. We are conducting experiments over several real data set, such as Yahoo! news and ads recommendations. In the second part of this project, we are trying to build up a bandwidth-aware recommender system that can adjust the recommendation strategy based on the current bandwidth of the system. We try to build fundamental framework for the learning and analysis of the system. Some interesting topics I am currently working on include reinforcement learning, contextual learning, combination of expert advices, and wireless recommender systems.

Understanding human languages and interacting using human language is a high-level intelligence for machines, recent trends of natural language processing allow machines to interact with human beings in a more natural way. This project covers a range of basic problems in NLP, such as conversational semantic role labeling, topic modeling, structural text generation, information bottleneck theory in NLP, and applications on FinTech, social science, healthcare, transportation, and other domains.