# Learnability of Competitive Threshold Models

arXiv: https://arxiv.org/abs/2205.03750 · HTML: https://mlsanity.com/paper/2205.03750/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 8 May 2022.

## Builds on (most cited first, 9 of 9)

- [DeepInf: Social Influence Prediction with Deep Learning](https://mlsanity.com/paper/1807.05560/) (2018)
- [On the Practical Computational Power of Finite Precision RNNs for Language Recognition](https://mlsanity.com/paper/1805.04908/) (2018)
- [DeepCas: an End-to-end Predictor of Information Cascades](https://mlsanity.com/paper/1611.05373/) (2016)
- [The Anatomy of a Scientific Rumor](https://mlsanity.com/paper/1301.2952/) (2013)
- [The Four Dimensions of Social Network Analysis: An Overview of Research Methods, Applications, and Software Tools](https://mlsanity.com/paper/2002.09485/) (2020)
- [Learning Influence Functions from Incomplete Observations](https://mlsanity.com/paper/1611.02305/) (2016)
- [StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks](https://mlsanity.com/paper/2009.14337/) (2020)
- [Contact-based Social Contagion in Multiplex Networks](https://mlsanity.com/paper/1307.1656/) (2013)
- [Coupon Advertising in Online Social Systems: Algorithms and Sampling Techniques](https://mlsanity.com/paper/1802.06946/) (2018)

## Built on by (most cited first, 2 of 2)

- [A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization](https://mlsanity.com/paper/2211.03074/) (2022)
- [Learning the Propagation of Worms in Wireless Sensor Networks](https://mlsanity.com/paper/2209.09984/) (2022)

## Abstract (arXiv)

Modeling the spread of social contagions is central to various applications in social computing. In this paper, we study the learnability of the competitive threshold model from a theoretical perspective. We demonstrate how competitive threshold models can be seamlessly simulated by artificial neural networks with finite VC dimensions, which enables analytical sample complexity and generalization bounds. Based on the proposed hypothesis space, we design efficient algorithms under the empirical risk minimization scheme. The theoretical insights are finally translated into practical and explainable modeling methods, the effectiveness of which is verified through a sanity check over a few synthetic and real datasets. The experimental results promisingly show that our method enjoys a decent performance without using excessive data points, outperforming off-the-shelf methods.