Contrastive Training for Models of Information Cascades

TL;DR

This paper introduces a novel contrastive training method for modeling information cascades as directed spanning trees, leveraging partial temporal orderings and content features to improve inference accuracy in an unsupervised manner.

Contribution

It presents a new DST-based cascade model combined with contrastive training that exploits partial temporal and content features, enhancing unsupervised cascade inference.

Findings

Unsupervised training with basic features achieves performance comparable to strong baselines.

Adding content features significantly improves accuracy, reaching half that of fully supervised models.

The model effectively exploits partial temporal ordering and message content for cascade modeling.

Abstract

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.