Author name cluster

Zhen Wen

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.

2 papers

1 author row

IJCAI Conference 2013 Conference Paper

One-Class Conditional Random Fields for Sequential Anomaly Detection

Yale Song
Zhen Wen
Ching-Yung Lin
Randall Davis

Sequential anomaly detection is a challenging problem due to the one-class nature of the data (i. e. , data is collected from only one class) and the temporal dependence in sequential data. We present One-Class Conditional Random Fields (OCCRF) for sequential anomaly detection that learn from a one-class dataset and capture the temporal dependence structure, in an unsupervised fashion. We propose a hinge loss in a regularized risk minimization framework that maximizes the margin between each sequence being classified as “normal” and “abnormal. ” This allows our model to accept most (but not all) of the training data as normal, yet keeps the solution space tight. Experimental results on a number of real-world datasets show our model outperforming several baselines. We also report an exploratory study on detecting abnormal organizational behavior in enterprise social networks.

PDF Details DOI

AAMAS Conference 2013 Conference Paper

Social Capital: The Power of Influencers in Networks

Karthik Subbian
Dhruv Sharma
Zhen Wen
Jaideep Srivastava

The problem of finding the influencers in social networks has been traditionally dealt in an optimization setting by finding the top-k nodes that has the maximum information spread in the network. These methods aim to find the influencers in a network through the process of information diffusion. However, none of these approaches model the individual social value generated by collaborations in these networks. Such social value is often the real motivation for which the nodes connect to each other. In this work, we propose a framework to compute this network social value using the concept of social capital, namely the amount of bonding and bridging connections in the network. We first compute the social capital value of the network and then allocate this network value to the nodes of the network. We establish the fairness of our allocation using several axioms of fairness. Our experiments on the real data sets show that the computed social capital is an excellent proxy for finding influencers and our approach outperforms several popular baselines.

PDF