Model-Independent Online Learning for Influence Maximization
This work addresses the problem of selecting seed users for marketing in social networks for marketers, offering a model-independent approach that is incremental by building on prior bandit-based methods.
The authors tackled influence maximization in social networks without assuming a known diffusion model, proposing a model-independent framework that learns efficiently from data and achieves a better regret bound dependent on network size, with experimental results showing robustness and near-optimal performance.
We consider influence maximization (IM) in social networks, which is the problem of maximizing the number of users that become aware of a product by selecting a set of "seed" users to expose the product to. While prior work assumes a known model of information diffusion, we propose a novel parametrization that not only makes our framework agnostic to the underlying diffusion model, but also statistically efficient to learn from data. We give a corresponding monotone, submodular surrogate function, and show that it is a good approximation to the original IM objective. We also consider the case of a new marketer looking to exploit an existing social network, while simultaneously learning the factors governing information propagation. For this, we propose a pairwise-influence semi-bandit feedback model and develop a LinUCB-based bandit algorithm. Our model-independent analysis shows that our regret bound has a better (as compared to previous work) dependence on the size of the network. Experimental evaluation suggests that our framework is robust to the underlying diffusion model and can efficiently learn a near-optimal solution.