用联邦学习实现去中心化社交平台协同内容审核
Collaborative Content Moderation in the Fediverse
- 各服务器共享本地训练的模型参数，联合构建统一审核模型
- 在三种审核任务中平均宏F1分别达0.71、0.73和0.58
- 适合资源有限的去中心化社交网络使用
Fediverse是由多个互连服务器组成的去中心化社交生态，支持如Mastodon等多样化服务。其迅速增长（部分由马斯克收购推特引发）给管理员带来挑战，尤其在内容审核方面。与依赖大规模标注数据和专用基础设施的中心化平台不同，本文提出基于联邦学习的协同审核系统FedMod。该系统使具有相似特征的服务器可交换局部训练的模型参数，共同构建一个联邦模型。实验表明，FedMod在有害内容检测、机器人内容识别和内容警示分配三项任务上表现稳健，平均每服务器宏F1得分分别为0.71、0.73和0.58。
原文摘要 · Abstract (English)
The Fediverse, a group of interconnected servers providing a variety of interoperable services (e.g. micro-blogging in Mastodon) has gained rapid popularity. This sudden growth, partly driven by Elon Musk's acquisition of Twitter, has created challenges for administrators though. This paper focuses on one particular challenge: content moderation, e.g. the need to remove spam or hate speech. While centralized platforms like Facebook and Twitter rely on automated tools for moderation, their dependence on massive labeled datasets and specialized infrastructure renders them impractical for decentralized, low-resource settings like the Fediverse. In this work, we design and evaluate FedMod, a collaborative content moderation system based on federated learning. Our system enables servers to exchange parameters of partially trained local content moderation models with similar servers, creating a federated model shared among collaborating servers. FedMod demonstrates robust performance on three different content moderation tasks: harmful content detection, bot content detection, and content warning assignment, achieving average per-server macro-F1 scores of 0.71, 0.73, and 0.58, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。