How can we automatically detect anomalies in a live and evolving knowledge graph?
Problem At Swisscom we continuously collect information about its network infrastructure in real time. All this information is stored in a massive knowledge graph with more than 200 million nodes, capturing dependencies from network devices and services.
While analyzing knowledge graphs with AI (embeddings) is well understood, there are still many challenges on dynamic evolving heterogeneous graphs. Such graphs play a key role in network forecasting, entity resolution or any form of interaction model (e.g. cells).
Mining the gap between changes, interactions or any evolution of edges in real-time puzzles our engineers for years.
Using the power of the Swiss AI LLM models creating natural human interaction interfaces to such complex graph analytics tasks
Join our journey and spot temporal anomalies of structural graph changes.
Objective Develop a method that can spot anomalies in a large, dynamic knowledge graph. These anomalies may appear at different levels: (this part will depend on which data we decide to use)
- Nodes: incorrect attributes or faulty devices.
- Edges: wrong or missing relationships between components.
- Graph structure: unusual patterns or sudden changes over time.
- LLM interface: an appealing chat interface to complex graph analytics tasks
Work in an unsupervised setting: the test data contains âtrue information,â so your model should detect deviations without explicit labels. Output should be anomaly scores to highlight suspicious parts of the graph.
Support for Hackers
- A synthetic dataset (already preprocessed as a PyTorch Geometric graph).
- A tutorial notebook introducing you to graph neural networks (GNNs) and showing how to work with the data.
- Help from Swisscom engineers to guide you and answer questions.
Technical Preferences
- PyTorch / PyTorch Geometric for graph learning.
- Creativity welcome: combine GNNs, embeddings, time-series analysis, or your own innovative ideas!
Why hack? Because detecting anomalies in such a huge, live-changing graph is a real-world problem with enormous impact. Better anomaly detection means:
- Faster root cause analysis of outages.
- More resilient networks.
- Millions of customers with more reliable service.
About the Challenge Partner
Swisscom is Switzerlandâs leading telecom provider and one of its most innovative IT companies. We operate one of the largest and most complex networks in the country. By joining this challenge, youâll be working on problems at the intersection of AI, graphs, and real-world network resilience.