Summary of Dynamic Gradient Influencing For Viral Marketing Using Graph Neural Networks, by Saurabh Sharma et al.
Dynamic Gradient Influencing for Viral Marketing Using Graph Neural Networks
by Saurabh Sharma, Ambuj Singh
First submitted to arxiv on: 19 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a novel data-driven approach to maximizing the adoption of products through viral marketing in social networks. The Dynamic Viral Marketing (DVM) problem uses Graph Neural Networks (GNNs) to model product adoption, considering both topological and attribute information. The goal is to find the minimum budget and optimal changes to achieve a specified adoption goal, which is shown to be NP-Hard and related to the influence maximization problem. To address this challenge, the paper proposes Dynamic Gradient Influencing (DGI), which utilizes gradient ranking to identify optimal perturbations and targets low-budget, high-influence non-adopters in discrete steps. The approach includes efficient node budget computation and the “Meta-Influence” heuristic for assessing a node’s downstream influence. Experimental results show significant gains of 24% on budget and 37% on AUC compared to baselines on real-world attributed networks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tackles the problem of making products go viral on social networks by using special computer programs (Graph Neural Networks) that understand both how things are connected (topology) and what those connections mean (attributes). The goal is to find the best way to get people to adopt a product, while spending as little money as possible. This problem is very hard to solve, but the paper shows that it’s related to another important problem called influence maximization. To solve this challenge, the paper proposes a new approach called Dynamic Gradient Influencing, which helps identify the most effective ways to get people to adopt a product by looking at how well certain actions work. The results show that this approach can be very effective in making products go viral. |
Keywords
* Artificial intelligence * Auc
