Using Survival Theory in Early Pattern Detection for Viral Cascades

Gao, Xiaofeng; Jia, Xiaosong; Yang, Chaoqi; Chen, Guihai

doi:10.1109/tkde.2020.3014203

Cited by 7 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Temporal models mainly study the time-series data, incorporated by additional social information. They adopt various stochastic processes to model and simulate the information diffusion in networks, in a statistical and generative manner [10], [11]; • Deep learning-based models are utilizing state-of-the-art techniques from neural networks to learn expressive representations of cascades [3], [12]. Among them many adopted techniques from graph representation learning and graph neural networks.…”

Section: Related Workmentioning

confidence: 99%

CCGL: Contrastive Cascade Graph Learning

Xu,

Zhou,

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Supervised learning, while prevalent for information cascade modeling, often requires abundant labeled data in training, and the trained model is not easy to generalize across tasks and datasets. Semi-supervised learning facilitates unlabeled data for cascade understanding in pre-training. It often learns fine-grained feature-level representations, which can easily result in overfitting for downstream tasks. Recently, contrastive self-supervised learning is designed to alleviate these two fundamental issues in linguistic and visual tasks. However, its direct applicability for cascade modeling, especially graph cascade related tasks, remains underexplored. In this work, we present Contrastive Cascade Graph Learning (CCGL), a novel framework for cascade graph representation learning in a contrastive, self-supervised, and task-agnostic way. In particular, CCGL first designs an effective data augmentation strategy to capture variation and uncertainty. Second, it learns a generic model for graph cascade tasks via self-supervised contrastive pre-training using both unlabeled and labeled data. Third, CCGL learns a task-specific cascade model via fine-tuning using labeled data. Finally, to make the model transferable across datasets and cascade applications, CCGL further enhances the model via distillation using a teacher-student architecture. We demonstrate that CCGL significantly outperforms its supervised and semi-supervised counterparts for several downstream tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

CCGL: Contrastive Cascade Graph Learning

Xu,

Zhou,

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Although not often applied to cascade modeling, recent advances have been used to model more complex dynamics of temporal point processes using neural networks [18,31]. Other than point-process models, a few others explored epidemic models [26,32], Bass model [33,34], Survival Analysis [35,36], Jump Processes [9], etc. Despite their explainable behavior and zero need for heavy feature engineering, generative models are susceptible to adverse influences from outliers [13] and found less powerful at making precise predictions [12].…”

Section: Related Workmentioning

confidence: 99%

Incomplete Gamma Integrals for Deep Cascade Prediction using Content, Network, and Exogenous Signals

Dutta¹,

Mittal²,

Das³

et al. 2021

Preprint

View full text Add to dashboard Cite

The behavior of information cascades (such as retweets) has been modeled extensively. While point process-based generative models have long been in use for estimating cascade growths, deep learning has greatly enhanced diverse feature integration. We observe two significant temporal signals in cascade data that have not been emphasized or reported to our knowledge. First, the popularity of the cascade root is known to influence cascade size strongly; but the effect falls off rapidly with time. Second, there is a measurable positive correlation between the novelty of the root content (with respect to a streaming external corpus) and the relative size of the resulting cascade. Responding to these observations, we propose GammaCas, a new cascade growth model as a parametric function of time, which combines deep influence signals from content (e.g., tweet text), network features (e.g., followers of the root user), and exogenous event sources (e.g., online news). Specifically, our model processes these signals through a customized recurrent network, whose states then provide the parameters of the cascade rate function, which is integrated over time to predict the cascade size. The network parameters are trained end-to-end using observed cascades. GammaCas outperforms seven recent and diverse baselines significantly on a large-scale dataset of retweet cascades coupled with time-aligned online news -it beats the best baseline with 18.98% increase in terms of Kendall's τ correlation and 35.63 reduction in Mean Absolute Percentage Error. Extensive ablation and case studies unearth interesting insights regarding retweet cascade dynamics.

show abstract