Influence Estimation and Maximization via Neural Mean-Field Dynamics
This work addresses influence maximization, a key problem in social network analysis and viral marketing, by providing a more accurate and efficient method, though it is incremental as it builds on existing diffusion models with novel algorithmic enhancements.
The authors tackled the problem of influence estimation and maximization on heterogeneous diffusion networks by proposing a neural mean-field dynamics framework, which simultaneously learns network structure and node infection probabilities from cascade data and achieves significant improvements in accuracy and efficiency over existing methods, with empirical studies showing robust performance across synthetic and real-world data.
We propose a novel learning framework using neural mean-field (NMF) dynamics for inference and estimation problems on heterogeneous diffusion networks. Our new framework leverages the Mori-Zwanzig formalism to obtain an exact evolution equation of the individual node infection probabilities, which renders a delay differential equation with memory integral approximated by learnable time convolution operators. Directly using information diffusion cascade data, our framework can simultaneously learn the structure of the diffusion network and the evolution of node infection probabilities. Connections between parameter learning and optimal control are also established, leading to a rigorous and implementable algorithm for training NMF. Moreover, we show that the projected gradient descent method can be employed to solve the challenging influence maximization problem, where the gradient is computed extremely fast by integrating NMF forward in time just once in each iteration. Extensive empirical studies show that our approach is versatile and robust to variations of the underlying diffusion network models, and significantly outperform existing approaches in accuracy and efficiency on both synthetic and real-world data.