Xiaoxiao Ma

Xiaoxiao Ma

I am a Senior Applied Scientist at Oracle with 9+ years of experience across industry and research, including work at Amazon and internships in Australia. My work and research focus on agentic AI systems, natural language processing, large language models, automatic prompt optimization, RAG, graph neural networks, recommender systems, anomaly detection, deep generative models, and deep learning.

Semi-Supervised Fake News Detection with Mixture of Experts

Published in Proceedings of the ACM Web Conference 2026, 2026

This paper studies fake news detection under limited supervision when adversaries use both semantic camouflage, such as style imitation, and structural camouflage, such as manipulated propagation patterns. It proposes a semi-supervised mixture-of-experts framework that keeps graph neural network and large language model components as distinct experts and uses their complementary judgments for cross-validation instead of collapsing them into a single hybrid model. The method is designed to improve robustness under scarce labels while handling more diverse fake news behaviors.

Recommended citation:
Download Paper