Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Decaffe: DHT Tree-Based Online Federated Fake News Detection

Cheng-Wei Ching, Liting Hu

TL;DR

Decaffe addresses real-time fake-news detection in mobile social networks by combining a DHT-based aggregation topology with online federated fine-tuning of a BERT classifier. It introduces centralized and decentralized tuning, plus personalized adaptation, to cope with fast-evolving, heterogeneous MSN data at scale. Evaluations on three real-world datasets with thousands of DHT nodes show improved accuracy and F1 and demonstrate scalable, low-latency dissemination and aggregation. The work provides a practical architecture for adaptive, privacy-conscious fake-news detection in dynamic MSNs.

Abstract

The proliferation of mobile social networks (MSNs) has transformed information dissemination, leading to increased reliance on these platforms for news consumption. However, this shift has been accompanied by the widespread propagation of fake news, posing significant challenges in terms of public panic, political influence, and the obscuring of truth. Traditional data processing pipelines for fake news detection in MSNs suffer from lengthy response times and poor scalability, failing to address the unique characteristics of news in MSNs, such as prompt propagation, large-scale quantity, and rapid evolution. This paper introduces a novel system named Decaffe - a DHT Tree-Based Online Federated Fake News Detection system. Decaffe leverages distributed hash table (DHT)-based aggregation trees for scalability and real-time detection, and it employs two model fine-tuning methods for adapting to mobile network dynamics. The system's structure includes a root, branches, and leaves for effective dissemination of a pre-trained model and ensemble-based aggregation of predictive results. Decaffe uniquely combines centralized server-based and decentralized serverless model fine-tuning approaches with personalized model fine-tuning, addressing the challenges of real-time detection, scalability, and adaptability in the dynamic environment of MSNs.

Decaffe: DHT Tree-Based Online Federated Fake News Detection

TL;DR

Decaffe addresses real-time fake-news detection in mobile social networks by combining a DHT-based aggregation topology with online federated fine-tuning of a BERT classifier. It introduces centralized and decentralized tuning, plus personalized adaptation, to cope with fast-evolving, heterogeneous MSN data at scale. Evaluations on three real-world datasets with thousands of DHT nodes show improved accuracy and F1 and demonstrate scalable, low-latency dissemination and aggregation. The work provides a practical architecture for adaptive, privacy-conscious fake-news detection in dynamic MSNs.

Abstract

The proliferation of mobile social networks (MSNs) has transformed information dissemination, leading to increased reliance on these platforms for news consumption. However, this shift has been accompanied by the widespread propagation of fake news, posing significant challenges in terms of public panic, political influence, and the obscuring of truth. Traditional data processing pipelines for fake news detection in MSNs suffer from lengthy response times and poor scalability, failing to address the unique characteristics of news in MSNs, such as prompt propagation, large-scale quantity, and rapid evolution. This paper introduces a novel system named Decaffe - a DHT Tree-Based Online Federated Fake News Detection system. Decaffe leverages distributed hash table (DHT)-based aggregation trees for scalability and real-time detection, and it employs two model fine-tuning methods for adapting to mobile network dynamics. The system's structure includes a root, branches, and leaves for effective dissemination of a pre-trained model and ensemble-based aggregation of predictive results. Decaffe uniquely combines centralized server-based and decentralized serverless model fine-tuning approaches with personalized model fine-tuning, addressing the challenges of real-time detection, scalability, and adaptability in the dynamic environment of MSNs.
Paper Structure (15 sections, 1 equation, 6 figures)

This paper contains 15 sections, 1 equation, 6 figures.

Table of Contents

  1. Introduction
  2. Background and Preliminaries
  3. Traditional data analytics pipeline
  4. Preliminaries
  5. Decaffe Design
  6. Overview
  7. Construction of DHT-based aggregation trees
  8. Online model fine-tuning and ensemble-based model inference
  9. Performance Evaluation
  10. Setup
  11. Emulation Deployment.
  12. Datasets and models.
  13. Prediction Results
  14. Scalability Analysis
  15. Conclusion

Figures (6)

  • Figure 1: Traditional data processing pipeline.
  • Figure 2: Message routing in Pastry.
  • Figure 3: The BERT model structure
  • Figure 4: Accuracy on three news datasets: COVID19 news, vaccination news, and election news.
  • Figure 5: F1 score on three news datasets: COVID19 news, vaccination news, and election news.
  • ...and 1 more figures