Efficient inference algorithms for network activities

Dr. Tran Quoc Long, will give a talk on Efficient inference algorithms for network activities.

The talk is scheduled on Friday 27 February at 9:00am, at Tap doan room 14th Floor, FPT Building, Duy Tan street, Hanoi.

Slide of talk is here.

Everyone interested is welcome!

Abstract: The real social network and associated communities are often hidden under the declared friend or group lists in social networks. We usually observe the manifestation of these hidden networks and communities in the form of recurrent and time-stamped individuals’ activities in the social network. The inference of relationship between users/nodes or groups of users/nodes could be further complicated when activities are interval-censored, that is, when one only observed the number of activities that occurred in certain time windows. The same phenomenon happens in the online advertisement world where the advertisers often offer a set of advertisement impressions and observe a set of conversions (i.e. product/service adoption). In this case, the advertisers desire to know which advertisements best appeal to the customers and most importantly, their rate of conversions.

Inspired by these challenges, we investigated inference algorithms that efficiently recover user relationships in both cases: time-stamped data and interval-censored data. In case of time-stamped data, we proposed a novel algorithm called NetCodec, which relies on a Hawkes process that models the intertwine relationship between group participation and between-user influence. Using Bayesian variational principle and optimization techniques, NetCodec could infer both group participation and user influence simultaneously with iteration complexity being O((N+I)G), where N is the number of events, I is the number of users, and G is the number of groups. In case of interval-censored data, we proposed a Monte-Carlo EM inference algorithm where we iteratively impute the time-stamped events using a Poisson process that has intensity function approximates the underlying intensity function. We show that that proposed simulated approach delivers better inference performance than baseline methods.

In the advertisement problem, we propose a Click-to-Conversion delay model that uses Hawkes processes to model the advertisement impressions and thinned Poisson processes to model the Click-to-Conversion mechanism. We then derive an efficient Maximum Likelihood Estimator which utilizes the Minorization-Maximization framework. We verify the model against real life online advertisement logs.

Short bio: 

Trần Quốc Long was born in Hanoi, Vietnam.

After completing his schoolwork at HUS High School for Gifted Students in 1998, Long entered Vietnam National University at Hanoi.

He received a Bachelor of Science with major in Communication Technology in June 2002.

From 2003 to 2005, he studied at National University of Singapore and received a Master of Engineering with major in Computer Engineering in May 2005.

During the following two years, he was employed as a lecturer in the Vietnam National University at Hanoi.

In August 2007, Long entered the PhD in Computer Science program in the College of Computing, Georgia Institute of Technology in Atlanta, Georgia.