Rui Li and Chaoyun Zhang won the best student paper award at the International Conference on Machine Learning for Networking (MLN'2018). Their paper DELMU: A Deep Learning Approach to Maximising the Utility of Virtualised Millimetre-Wave Backhauls puts forward a general rate utility framework for slicing mm-wave backhaul links, encompassing all known types of service utilities and introduces DELMU, a deep learning solution that tackles the complexity of optimising non-convex objective functions built upon arbitrary combinations of such utilities. The proposed method can be trained within minutes, following which it computes rate allocations that match those obtained with state-of-the-art global optimisation algorithms, yet orders of magnitude faster. This confirms the applicability of DELMU to highly dynamic traffic regimes and we demonstrate up to 62% network utility gains over a baseline greedy approach. Rui Li and Chaoyun Zhang work with Paul Patras. Earlier this year Rui Li received the Brendan Murphy award at the UK annual Multi-service Networks Workshop for this work. MLN conference provides a forum for scientists, engineers and researchers to discuss and exchange novel ideas, results, experiences, and work-in-process on all aspects of Machine Learning and Networking. MLN 2018 was held from 27th to 29th November 2018 in Paris, France. Related links Paper in the Edinburgh Research Explorer International Conference on Machine Learning for Networking (MLN'2018) This article was published on 2024-11-22