Research project Resource Efficient Machine Learning in Complex Networks

Due to their increasing size, machine learning models and data-sets are increasingly being processed in complex networks. For example, training state-of-the-art machine learning models now typically require massive parallel processing, making computations manageable but exhausting excessive communication resources.

Moreover, data is increasingly being collected and processed in IoT (internet of things) networks, for example by smartphones, home-appliances and wireless sensors). Energy resources are often limited, and communication over shared wireless networks has limited reliability, connectivity, and data-rates.

The success of machine learning in these networks is largely based on exhausting more and more communication, computation, and energy resources. This is unsustainable! The goal of this project is to advance the systematic design and theoretical foundations of resource efficient machine learning in complex networks.

We split the time equally between three main activities investigated in parallel:

1. Communication efficient machine learning: How can we compress algorithm information while maintaining performance?
2. Machine learning in wireless networks: How can we ensure the best performance with limited shared communication resources?
3. Energy efficient machine learning in IoT: What is the best trade-off between communication and computation resources?

Our focus is on practical algorithms with provable performance guarantees based on mathematical models verified by simulations and experiments using real IoT devices or micro-computers.