Contrastive Training for Models of Information Cascades
This work addresses the challenge of inferring information cascades in networks like blogs, offering an unsupervised approach that can leverage node and text features, though it is incremental as it builds on existing models.
The paper tackles the problem of modeling information cascades by proposing a directed spanning tree model and a contrastive training procedure that uses partial temporal ordering instead of labeled links, achieving performance comparable to strong baselines with basic features and significantly better results with content features, reaching half the accuracy of a fully supervised model.
This paper proposes a model of information cascades as directed spanning trees (DSTs) over observed documents. In addition, we propose a contrastive training procedure that exploits partial temporal ordering of node infections in lieu of labeled training links. This combination of model and unsupervised training makes it possible to improve on models that use infection times alone and to exploit arbitrary features of the nodes and of the text content of messages in information cascades. With only basic node and time lag features similar to previous models, the DST model achieves performance with unsupervised training comparable to strong baselines on a blog network inference task. Unsupervised training with additional content features achieves significantly better results, reaching half the accuracy of a fully supervised model.