A5101493169- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Opinion Dynamics and Social Influence
- Topic Modeling
- Machine Learning and Algorithms
- Machine Learning and ELM
- Recommender Systems and Techniques
- Caching and Content Delivery
- Expert finding and Q&A systems
- Stochastic Gradient Optimization Techniques
- Social Media and Politics
- Spam and Phishing Detection
- Data Quality and Management
- Neural Networks and Applications
- Mental Health Research Topics
Beijing Municipal Education Commission
2021-2022
Beijing Jiaotong University
2020-2022
Simon Fraser University
2012-2017
The community structure detection in static networks often ignores the dynamic nature of network and it is difficult to identify evolution networks. will converge or split as nodes edges change. Understanding communities over time an important issue study social Based on characteristics networks, this paper analyzed influence variables structure. We proposed Incremental algorithm with Coherent Neighborhood Propinquity considered direct indirect effects changing their previous communities....
As social networking is moving into the web, study and exploitation of correlation has emerged as a hot research topic. Most these work consider binary relations, called "friendships". However, online users tend to establish many friendships varying degree strength, e.g., relatives, friends, co-workers, acquaintances. We argue that, due their different friend relationships will have greatly degrees should be distinguished. Besides, not only factor driving user behavior. In this paper, we...
The ever rising popularity of online social networks has not only attracted much attention from everyday users but also academic researchers. In particular, research been done to investigate the effect influence on users' actions items in network. However, all data-mining field a context-independent setting, i.e., irrespective an item's characteristics. It would be interesting find specific contexts which each other similar manner. this way, applications such as recommendation engines can...
Multihop question answering has attracted extensive studies in recent years because of the emergence human annotated datasets and associated leaderboards. Recent have revealed that systems learn to exploit annotation artifacts other biases current datasets. Therefore, a model with strong interpretability should not only predict final answer, but more importantly find supporting facts’ sentences necessary answer complex questions, also known as evidence sentences. Most existing methods...
Recurrent Neural Network (RNN) is a fundamental structure in deep learning. Recently, some works study the training process of over-parameterized neural networks, and show that networks can learn functions notable concept classes with provable generalization error bound. In this paper, we analyze for RNNs random initialization, provide following improvements over recent works: 1) For RNN input sequence $x=(X_1,X_2,...,X_L)$, previous to are summation $f(\beta^T_lX_l)$ require normalized...