• Corpus ID: 195316395

Estimation of a Low-rank Topic-Based Model for Information Cascades

  title={Estimation of a Low-rank Topic-Based Model for Information Cascades},
  author={Ming Yu and Varun Gupta and Mladen Kolar},
  journal={J. Mach. Learn. Res.},
We consider the problem of estimating the latent structure of a social network based on the observed information diffusion events, or cascades, where the observations for a given cascade consist of only the timestamps of infection for infected nodes but not the source of the infection. Most of the existing work on this problem has focused on estimating a diffusion matrix without any structural assumptions on it. In this paper, we propose a novel model based on the intuition that an information… 
Context-dependent Networks in Multivariate Time Series: Models, Methods, and Risk Bounds in High Dimensions
Ideas from compositional time series and regularization methods in machine learning are used to conduct context-dependent network estimation for high-dimensional autoregressive time series of annotated event data and a mixture approach enjoying both approaches’ merits is proposed.
Context-dependent self-exciting point processes: models, methods, and risk bounds in high dimensions
Ideas from compositional time series and regularization methods in machine learning are leveraged to conduct network estimation for high-dimensional marked point processes that reflect how features associated with an event modulate the strength of influences among nodes.


An Influence-Receptivity Model for Topic Based Information Cascades
This work proposes a novel model for inferring network diffusion matrix based on the intuition that an information datum is more likely to propagate among two nodes if they are interested in similar topics, which are common with the information.
Learning Influence-Receptivity Network Structure with Guarantee
This paper proposes a novel latent model using the intuition that a connection is more likely to exist between two nodes if they are interested in similar topics, which are common with the information/event, and shows how these two node-topic structures can be estimated from observed adjacency matrices with theoretical guarantee on estimation error.
Uncover Topic-Sensitive Information Diffusion Networks
This paper proposes a continuous time model, TOPICCASCADE, for topicsensitive information diffusion networks, and infer the hidden diffusion networks and the topic dependent transmission rates from the observed time stamps and contents of cascades.
Learning Social Infectivity in Sparse Low-rank Networks Using Multi-dimensional Hawkes Processes
This paper proposes a convex optimization approach to discover the hidden network of social influence by modeling the recurrent events at different individuals as multidimensional Hawkes processes, emphasizing the mutual-excitation nature of the dynamics of event occurrence.
Structure and dynamics of information pathways in online media
An on-line algorithm that relies on stochastic convex optimization to efficiently solve the dynamic network inference problem and studies the evolution of information pathways in the online media space.
Learning the graph of epidemic cascades
This work analytically establishes sufficient conditions on the number of epidemics for both the global maximum-likelihood (ML) estimator, and a natural greedy algorithm to succeed with high probability in finding the graph on which an epidemic spreads, given only the times when each node gets infected.
Inferring Networks of Diffusion and Influence
This work develops an efficient approximation algorithm that scales to large datasets and finds provably near-optimal networks for tracing paths of diffusion and influence through networks and inferring the networks over which contagions propagate.
HawkesTopic: A Joint Model for Network Inference and Topic Modeling from Text-Based Cascades
This work develops the Hawkes Topic model (HTM) for analyzing text-based cascades, such as "retweeting a post" or "publishing a follow-up blog post," and shows how to jointly infer them with a mean-field variational inference algorithm.
Learning Networks of Heterogeneous Influence
This paper proposes a kernel-based method which can capture a diverse range of different types of influence without any prior assumption and shows that this model can better recover the underlying diffusion network and drastically improve the estimation of the transmission functions among networked entities.
Estimating Diffusion Networks: Recovery Conditions, Sample Complexity and Soft-thresholding Algorithm
This paper investigates the network structure inference problem for a general family of continuous-time diffusion models using an l1- regularized likelihood maximization framework and develops a simple and efficient soft-thresholding network inference algorithm which outperforms other alternatives in terms of the accuracy of recovering hidden diffusion networks.