• de
Prof. Dr. Holger Karl

3rd KuVS Fachgespräch "Machine Learning & Networking" - October 6 & 7

Malene 2022 Teilnehmer
Teilnehmer des Malene 2022 Fachgesprächs am Hasso-Plattner-Institut

Welcome to the 3rd edition of the KuVS Fachgespräch "Machine Learning & Networking (Malene)", October 6 & 7, 2022, at Hasso-Plattner-Institut in Potsdam. It is jointly supported by GI and ITG/VDE. 

Tentative Program 

DayTimeSession / Paper title AuthorsFolien
Thursday, Oct. 6th10:00 - 12:00

Joint working session: Tools, Frameworks, Data sets 

 12:00 - 13:00 Lunch break  
 13:00 - 13:30 Registration   
 13:30 - 15:30Session 1: Basics of ML in and for networks  
 13:30 - 14:00 Survey: Data-parallel Architectures for Distributed Machine LearningPaeleke, KarlPDF
 14:00 - 14:30 Analyzing Sparsity of Deep Neural Networks in an Edge AI Split Computing ScenarioHaberer, LandsiedelPDF
 14:30 - 15:00 Resource-Aware Distributed Machine Learning on Heterogeneous IoT DevicesSamikwa, BraunPDF
 15:00 - 15:30Preliminary Rate of Convergence Analysis of Constant Step-Size Distributed Stochastic Gradient DescentRedderPDF
 15:30 - 16:00Break  
 16:00 - 17:30Session 2: Reinforcement learning, multi-agent approaches  
 16:00 - 16:30Multi-Agent Reinforcement Learning for Coordination of Device-to-Device communicationPochaba, Dorfinger, Herlich, Kwitt, HirländerPDF
 16:30 - 17:00Multi-Agent Distributed Reinforcement Learning for Making Decentralized DecisionsTan, Khalili, Hecker, Karl 
 17:00 - 17:30Towards Deep Learning Multiple Access (DLMA) through Multi-Agent Reinforcement LearningLindner 
 19:00Joint dinner  
Friday, Oct. 7th9:00 - 10:30Session 3: Distributed learning  
 9:00 - 9:30Ensuring Fairness in Renewable-Aware Scheduling for Federated LearningAgrawal, Wiesner 
 9:30 - 10:00Distributed Optimal-Transport Clustering for Malicious User Rejection in Federated-Learning VANETsPacheco, BraunPDF
 10:00 - 10:30Towards Autonomous Edge Cloud Maintenance using Machine-Learned Digital Twin NetworksBoltresPDF
 10:30 - 11:00Break  
 11:00 - 12:00Session 4: Networking protocols  
 11:00 - 11:30Machine-learning based Multipath Wireless Access on an Infrastructure for Latency Critical AI-ApplicationsPoorzare, Wippel, Waldhorst, ZirpinsPDF
 11:30 - 12:00End-to-End is Not Enough: Towards a Coordinated Congestion Control (C3)König, ZitterbartPDF
 12:00 - 13:00Lunch break   
 13:00 - 14:30Session 5: Network structure  
 13:00 - 13:30Passive Investigation of Networks and Classification of the discovered Assets according to the IT Basic Protection of the BSISchwinger, Meyer, KrillePDF
 13:30 - 14:00How to Predict Flow-Level Network Traffic EvolutionGholam Zadeh 
 14:00 - 14:30WAN-GAN: Synthesizing Wide Area Network Topologies via Generative Adversarial NetworksDietz, Seufert, Hoßfeld 

Work session: Tools, Frameworks, Data sets 

To kickstart the discussions, we will start with a joint working session without a dedicated speaker. The idea is to collect sets of commonly used tools, data sets, or frameworks to ease entering into research into this field. The outcome of this session should at least be turned into a living document hosted by KuVS, possibly, a publication is conceivable (similar to Dagstuhl result white papers) as a survey or a tutorial. Everybody is cordially invited to attend. 


To register, please send an email to holger.karl@hpi.de. There is no registration fee; participation is free of charge. Please do register nevertheless so that we can plan accordingly. 

Procedure and Dates 

  • Registration deadline: Friday, September 30 
  • Location: At Hasso-Plattner-Institute, Griebnitzsee (travel hints) at building L, groud floor ("Eventfläche L") 

What is a Fachgespräch? 

Fachgespräche are a low-key version of workshops, organized (among others) by the Communication and Distributed Systems group of the Gesellschaft für Informatik. They foster community building by organising meetings on topics of current interest, with a low entry barrier. Typical target audience are people in their later Master or early PhD phase, but of course everybody is welcome. Participants are invited to present early ideas, work in progress, or also talk about work that has already been published - we deliberately do NOT require original research at a Fachgespräch. For PhD students new to the field of machine learning and networks, please also have a look at the summer school on  AI in Networking Summer School

What is Malene? 

Malene is one such Fachgespräch, dedicated to the interaction of machine learning and networking. You can find earlier editions here: 2020a2020b, 2021 (co-located with NetSys conference).   

What is special about the 3rd edition of Malene? 

This time, we want to focus the discussion on how networking can assist machine learning systems and, in particular, distributed ML systems. E.g., how to ensure that distributed training is provided with the right data and runs at the right place in a network, taking all kinds of resource requirements into account. 


    • Andreas Blenk, TU Munich 
    • Holger Karl, HPI 
    • Olaf Landsiedel, Uni Kiel 
    • Stefan Schneider, Uni Paderborn 
    • Michael Seufert, Uni Würzburg