Stochastic gradient descent-based inference for dynamic network models with attractors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909429091270656 |
|---|---|
| author | Pan, Hancong Zhu, Xiaojing Caliskan, Cantay Christenson, Dino P. Spiliopoulos, Konstantinos Walker, Dylan Kolaczyk, Eric D. |
| author_facet | Pan, Hancong Zhu, Xiaojing Caliskan, Cantay Christenson, Dino P. Spiliopoulos, Konstantinos Walker, Dylan Kolaczyk, Eric D. |
| contents | In Coevolving Latent Space Networks with Attractors (CLSNA) models, nodes in a latent space represent social actors, and edges indicate their dynamic interactions. Attractors are added at the latent level to capture the notion of attractive and repulsive forces between nodes, borrowing from dynamical systems theory. However, CLSNA reliance on MCMC estimation makes scaling difficult, and the requirement for nodes to be present throughout the study period limit practical applications. We address these issues by (i) introducing a Stochastic gradient descent (SGD) parameter estimation method, (ii) developing a novel approach for uncertainty quantification using SGD, and (iii) extending the model to allow nodes to join and leave over time. Simulation results show that our extensions result in little loss of accuracy compared to MCMC, but can scale to much larger networks. We apply our approach to the longitudinal social networks of members of US Congress on the social media platform X. Accounting for node dynamics overcomes selection bias in the network and uncovers uniquely and increasingly repulsive forces within the Republican Party. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07124 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Stochastic gradient descent-based inference for dynamic network models with attractors Pan, Hancong Zhu, Xiaojing Caliskan, Cantay Christenson, Dino P. Spiliopoulos, Konstantinos Walker, Dylan Kolaczyk, Eric D. Methodology Social and Information Networks In Coevolving Latent Space Networks with Attractors (CLSNA) models, nodes in a latent space represent social actors, and edges indicate their dynamic interactions. Attractors are added at the latent level to capture the notion of attractive and repulsive forces between nodes, borrowing from dynamical systems theory. However, CLSNA reliance on MCMC estimation makes scaling difficult, and the requirement for nodes to be present throughout the study period limit practical applications. We address these issues by (i) introducing a Stochastic gradient descent (SGD) parameter estimation method, (ii) developing a novel approach for uncertainty quantification using SGD, and (iii) extending the model to allow nodes to join and leave over time. Simulation results show that our extensions result in little loss of accuracy compared to MCMC, but can scale to much larger networks. We apply our approach to the longitudinal social networks of members of US Congress on the social media platform X. Accounting for node dynamics overcomes selection bias in the network and uncovers uniquely and increasingly repulsive forces within the Republican Party. |
| title | Stochastic gradient descent-based inference for dynamic network models with attractors |
| topic | Methodology Social and Information Networks |
| url | https://arxiv.org/abs/2403.07124 |