Fedivertex: a Graph Dataset based on Decentralized Social Networks for Trustworthy Machine Learning

2025-05-27

AI Summary

Existing graph datasets are predominantly static snapshots from centralized social platforms, heavily biased by recommendation algorithms and platform policies, thus failing to support trustworthy evaluation of decentralized machine learning. Method: We introduce Fedivertex—the first large-scale, dynamic graph dataset for the Fediverse—comprising 182 weekly snapshot graphs across seven open-source platforms. It is the first systematic collection of real-world decentralized social network evolution. We formalize “defederation” as a novel task modeling spontaneous link deletion, and design a distributed crawler, temporal sampling strategy, and topology-aware analysis framework, releasing the open-source Python toolkit fedivertex-py. Contribution/Results: Experiments demonstrate that Fedivertex significantly improves model generalization on peer-to-peer communication topologies. It establishes a reliable, realistic benchmark for decentralized graph learning, enabling principled evaluation of structural dynamics, link evolution, and federated graph representation learning.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Decentralized machine learning - where each client keeps its own data locally and uses its own computational resources to collaboratively train a model by exchanging peer-to-peer messages - is increasingly popular, as it enables better scalability and control over the data. A major challenge in this setting is that learning dynamics depend on the topology of the communication graph, which motivates the use of real graph datasets for benchmarking decentralized algorithms. Unfortunately, existing graph datasets are largely limited to for-profit social networks crawled at a fixed point in time and often collected at the user scale, where links are heavily influenced by the platform and its recommendation algorithms. The Fediverse, which includes several free and open-source decentralized social media platforms such as Mastodon, Misskey, and Lemmy, offers an interesting real-world alternative. We introduce Fedivertex, a new dataset of 182 graphs, covering seven social networks from the Fediverse, crawled weekly over 14 weeks. We release the dataset along with a Python package to facilitate its use, and illustrate its utility on several tasks, including a new defederation task, which captures a process of link deletion observed on these networks.

Problem

• Lack of real graph datasets for decentralized algorithm benchmarking
• Existing datasets limited to for-profit social networks
• Need for trustworthy datasets from decentralized social media platforms

Innovation

• Decentralized social networks for trustworthy ML
• Weekly crawled Fediverse graph dataset
• Python package for defederation task analysis