16 citations · 29 across the 16 of their papers we have counts for
7 papers · 1 filter
Boosting Gradient Ascent for Continuous DR-submodular Maximization
Qixin Zhang, Zongqi Wan, Zengde Deng +4
Projected Gradient Ascent (PGA) is the most commonly used optimization scheme in machine learning and operations research areas. Nevertheless, numerous studies and examples have sh…
Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization
Qixin Zhang, Zengde Deng, Xiangru Jian +3
Maximizing a monotone submodular function is a fundamental task in machine learning, economics, and statistics. In this paper, we present two communication-efficient decentralized…
Online Learning for Non-monotone Submodular Maximization: From Full Information to Bandit Feedback
Qixin Zhang, Zengde Deng, Zaiyi Chen +3
In this paper, we revisit the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, which finds wide real-world applications in the domai…
Neighbor Enhanced Graph Convolutional Networks for Node Classification and Recommendation
Hao Chen, Zhong Huang, Yue Xu +4
The recently proposed Graph Convolutional Networks (GCNs) have achieved significantly superior performance on various graph-related tasks, such as node classification and recommend…
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function
Qixin Zhang, Zengde Deng, Zaiyi Chen +2
In this paper, we revisit Stochastic Continuous Submodular Maximization in both offline and online settings, which can benefit wide applications in machine learning and operations…
Non-Recursive Graph Convolutional Networks
Hao Chen, Zengde Deng, Yue Xu +1
Graph Convolutional Networks (GCNs) are powerful models for node representation learning tasks. However, the node representation in existing GCN models is usually generated by perf…
Voting-Based Multi-Agent Reinforcement Learning for Intelligent IoT
Yue Xu, Zengde Deng, Mengdi Wang +3
The recent success of single-agent reinforcement learning (RL) in Internet of things (IoT) systems motivates the study of multi-agent reinforcement learning (MARL), which is more c…