Summary of Dame: Personalized Federated Social Event Detection with Dual Aggregation Mechanism, by Xiaoyan Yu et al.
DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanism
by Xiaoyan Yu, Yifan Wei, Pu Li, Shuaishuai Zhou, Hao Peng, Li Sun, Liehuang Zhu, Philip S. Yu
First submitted to arxiv on: 1 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 A personalized federated learning framework for social event detection, called DAMe, is proposed to improve performance on this task through a dual aggregation mechanism. The local aggregation strategy uses Bayesian optimization to incorporate global knowledge while retaining local characteristics, and the global aggregation strategy provides clients with maximum external knowledge of their preferences. Additionally, a global-local event-centric constraint prevents overfitting and “client-drift”. Experiments in a realistic simulation using six social event datasets and an ablation study demonstrate the effectiveness of DAMe. Robustness analyses also show that DAMe is resistant to injection attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning for social event detection wants to make sure people are good at recognizing events like parties or protests on social media. The problem is that different people might have different ways of sharing information, so it’s hard to train a model that works well everywhere. This paper introduces a new way of doing federated learning that helps the model learn from everyone’s data while still being good at detecting specific events. They tested this new method using six different datasets and showed that it works well and is resistant to fake or manipulated information. |
Keywords
» Artificial intelligence » Event detection » Federated learning » Optimization » Overfitting
