Author name cluster

Feiyun Zhu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2018 Conference Paper

Adaptive Graph Convolutional Neural Networks

Ruoyu Li
Sheng Wang
Feiyun Zhu
Junzhou Huang

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current ﬁlters in graph CNNs are built for ﬁxed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and ﬂexible graph CNN taking data of arbitrary graph structure as input. In that way a task-driven adaptive graph is learned for each graph data while training. To efﬁciently learn the graph, a distance metric learning is proposed. Extensive experiments on nine graph-structured datasets have demonstrated the superior performance improvement on both convergence speed and predictive accuracy.

PDF Details

RLDM Conference 2017 Conference Abstract

Effective Warm Start for the Online Actor-Critic Reinforcement Learning based mHealth Inter- vention

Feiyun Zhu
Peng Liao

Online reinforcement learning (RL) is increasingly popular for the personalized mobile health (mHealth) intervention. It is able to personalize the type and dose of interventions according to user’s ongoing statuses and changing needs. However, at the beginning of online learning, there are usually too few samples to support the RL updating, which leads to poor performances. A delay in good performance of the online learning algorithms can be especially detrimental in the mHealth, where users tend to quickly disengage with apps. To address this problem, we propose a new online RL methodology that focuses on an effective warm start. The main idea is to make full use of the data accumulated and the decision rule achieved in a former study. As a result, we can greatly enrich the data size at the beginning of online learning in our method. Such case accelerates the online learning process for new users to achieve good performances not only at the beginning of online learning but also through the whole online learning process. Besides, we use the decision rules achieved previously to initialize the parameter in our online RL model for new users. It provides a good initialization for the proposed online RL algorithm. Experiment results show that promising improvements have been achieved by our method compared with the state-of-the-art method.

PDF Details

AAAI Conference 2015 Conference Paper

10,000+ Times Accelerated Robust Subset Selection

Feiyun Zhu
Bin Fan
Xinliang Zhu
Ying Wang
Shiming Xiang
Chunhong Pan

Subset selection from massive data with noised information is increasingly popular for various applications. This problem is still highly challenging as current methods are generally slow in speed and sensitive to outliers. To address the above two issues, we propose an accelerated robust subset selection (ARSS) method. Speciﬁcally in the subset selection area, this is the ﬁrst attempt to employ the p (0 < p ≤ 1)-norm based measure for the representation loss, preventing large errors from dominating our objective. As a result, the robustness against outlier elements is greatly enhanced. Actually, data size is generally much larger than feature length, i. e. N L. Based on this observation, we propose a speedup solver (via ALM and equivalent derivations) to highly reduce the computational cost, theoretically from O N4 to O N2 L. Extensive experiments on ten benchmark datasets verify that our method not only outperforms state of the art methods, but also runs 10, 000+ times faster than the most related method.

PDF Details