Timezone: »

 
Poster
Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback
Zheng Wen · Branislav Kveton · Michal Valko · Sharan Vaswani

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #32
in Posters Wed »

We study the online influence maximization problem in social networks under the independent cascade model. Specifically, we aim to learn the set of "best influencers" in a social network online while repeatedly interacting with it. We address the challenges of (i) combinatorial action space, since the number of feasible influencer sets grows exponentially with the maximum number of influencers, and (ii) limited feedback, since only the influenced portion of the network is observed. Under a stochastic semi-bandit feedback, we propose and analyze IMLinUCB, a computationally efficient UCB-based algorithm. Our bounds on the cumulative regret are polynomial in all quantities of interest, achieve near-optimal dependence on the number of interactions and reflect the topology of the network and the activation probabilities of its edges, thereby giving insights on the problem complexity. To the best of our knowledge, these are the first such results. Our experiments show that in several representative graph topologies, the regret of IMLinUCB scales as suggested by our upper bounds. IMLinUCB permits linear generalization and thus is both statistically and computationally suitable for large-scale problems. Our experiments also show that IMLinUCB with linear generalization can lead to low regret in real-world online influence maximization.

Keywords: Bandit Algorithms · Online Learning
[ Paper] 

Author Information

Zheng Wen (Adobe Research)

Zheng Wen is currently a senior research scientist at Big Data Experience Lab, Adobe Research. His current research focuses on machine learning, operations research, and big data. Before joining Adobe Research, he was a research scientist in Advertising Science Team, Yahoo Labs. Prior to that, he received a Ph.D. in Electrical Engineering from Stanford University.

Branislav Kveton (Adobe Research)
Michal Valko (DeepMind Paris and Inria Lille - Nord Europe)
Michal Valko

Michal is a machine learning scientist in DeepMind Paris, tenured researcher at Inria, and the lecturer of the master course Graphs in Machine Learning at l'ENS Paris-Saclay. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. This means 1) reducing the “intelligence” that humans need to input into the system and 2) minimizing the data that humans need to spend inspecting, classifying, or “tuning” the algorithms. That is why he is working on methods and settings that are able to deal with minimal feedback, such as deep reinforcement learning, bandit algorithms, or self-supervised learning. Michal is actively working on represenation learning and building worlds models. He is also working on deep (reinforcement) learning algorithm that have some theoretical underpinning. He has also worked on sequential algorithms with structured decisions where exploiting the structure leads to provably faster learning. He received his Ph.D. in 2011 from the University of Pittsburgh under the supervision of Miloš Hauskrecht and after was a postdoc of Rémi Munos before taking a permanent position at Inria in 2012.

Sharan Vaswani (University of British Columbia)

More from the Same Authors