DeepCas: An End-to-end Predictor of Information Cascades

By Cheng Li, Jiaqi W. Ma, Xiaoxiao Guo, Qiaozhu Mei. 2016

378 citations recorded by the source corpus.

Information cascades, effectively facilitated by most social network platforms, are recognized as a major factor in almost every social success and disaster in these networks. Can cascades be predicted? While many believe that they are inherently unpredictable, recent work has shown that some key properties of information cascades, such as size, growth, and shape, can be predicted by a machine learning algorithm that combines many features. These predictors all depend on a bag of hand-crafting features to represent the cascade network and the global network structures. Such features, always carefully and sometimes mysteriously designed, are not easy to extend or to generalize to a different platform or domain. Inspired by the recent successes of deep learning in multiple data mining tasks, we investigate whether an end-to-end deep learning approach could effectively predict the future size of cascades. Such a method automatically learns the representation of individual cascade graphs in the context of the global network structure, without hand-crafted features or heuristics. We find that node embeddings fall short of predictive power, and it is critical to learn the representation of a cascade graph as a whole. We present algorithms that learn the representation of cascade graphs in an end-to-end manner, which significantly improve the performance of cascade prediction over strong baselines including feature based methods, node embedding methods, and graph kernel methods. Our results also provide interesting implications for cascade prediction in general.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “[63] predict the increment of a cascade size after a given time interval.”
A Survey on Network Embedding (2017, background): “For instance, some deep model based end-to-end solutions are proposed for cascade prediction (Li et al. 2017) and network alignment (Man et al. 2016).”
Topological Recurrent Neural Network for Diffusion Prediction (2017, methodology): “which are not aware of the data graph structure; DeepCas’s data model is a set of independent paths sampled from the induced subgraph over the active nodes at each time t [15], and each path alone only partially captures the cascade structure.”
DeepInf: Social Influence Prediction with Deep Learning (2018, methodology): “[26] proposed an end-toend predictor for inferring cascade size by incorporating recurrent neural network (RNN) and representation learning.”
DeepHawkes: Bridging the Gap between Prediction and Understanding of Information Cascades (2017, methodology): “As a remedy, deep learning methods were recently introduced to automatically learn features for popularity prediction [8].”