← Back to papers
2012 COLT COLT 2012

Open Problem: Learning Dynamic Network Models from a Static Snapshot

Abstract

In this paper we consider the problem of learning a graph generating process given the evolving graph at a single point in time. Given a graph of sufficient size, can we learn the (repeatable) process that generated it? We formalize the generic problem and then consider two simple instances which are variations on the well-know graph generation models by Erdós-Rényi and Albert-Barabasi.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
📈 Trend Setter — Graph Neural Networks
🧭 Keyword Pioneer — graph generation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning

Authors

Jan Ramon , Constantin Comendant

Topics

Machine Learning > Learning Types > Unsupervised Learning Deep Learning > Architectures > Graph Neural Networks Machine Learning > Core Methods > Graphical Models Artificial Intelligence > Core AI > Knowledge Graphs

Keywords

graph generation network model dynamic network erdos-renyi model barabasi-albert model graph generating process graph snapshot
Download PDF

Related papers

Unsupervised SVMs: On the Complexity of the Furthest Hyperplane Problem 2012
Online Optimization with Gradual Variations 2012
Toward a Noncommutative Arithmetic-geometric Mean Inequality: Conjectures, Case-studies, and Consequences 2012
Computational Bounds on Statistical Query Learning 2012
Rare Probability Estimation under Regularly Varying Heavy Tails 2012