363 citations · 1.2k across the 23 of their papers we have counts for
23 papers
Atom: Neural Traffic Compression with Spatio-Temporal Graph Neural Networks
Paul Almasan, Krzysztof Rusek, Shihan Xiao +4
Storing network traffic data is key to efficient network management; however, it is becoming more challenging and costly due to the ever-increasing data transmission rates, traffic…
FTMRate: Collision-Immune Distance-based Data Rate Selection for IEEE 802.11 Networks
Wojciech Ciezobka, Maksymilian Wojnar, Katarzyna Kosek-Szott +2
Data rate selection algorithms for Wi-Fi devices are an important area of research because they directly impact performance. Most of the proposals are based on measuring the transm…
Leveraging Spatial and Temporal Correlations for Network Traffic Compression
Paul Almasan, Krzysztof Rusek, Shihan Xiao +4
The deployment of modern network applications is increasing the network size and traffic volumes at an unprecedented pace. Storing network-related information (e.g., traffic traces…
RouteNet-Fermi: Network Modeling with Graph Neural Networks
Miquel Ferriol-Galmés, Jordi Paillisse, José Suárez-Varela +6
Network models are an essential block of modern networks. For example, they are widely used in network planning and optimization. However, as networks increase in scale and complex…
Fast Traffic Engineering by Gradient Descent with Learned Differentiable Routing
Krzysztof Rusek, Paul Almasan, José Suárez-Varela +3
Emerging applications such as the metaverse, telesurgery or cloud computing require increasingly complex operational demands on networks (e.g., ultra-reliable low latency). Likewis…
Reproducibility Companion Paper: Describing Subjective Experiment Consistency by -Value P-P Plot
Jakub Nawała, Lucjan Janowski, Bogdan Ćmiel +3
In this paper we reproduce experimental results presented in our earlier work titled "Describing Subjective Experiment Consistency by -Value P-P Plot" that was presented in the…
Generalised Score Distribution: Underdispersed Continuation of the Beta-Binomial Distribution
Bogdan Ćmiel, Jakub Nawała, Lucjan Janowski +1
A class of discrete probability distributions contains distributions with limited support. A typical example is some variant of a Likert scale, with response mapped to either the $…
RouteNet-Erlang: A Graph Neural Network for Network Performance Evaluation
Miquel Ferriol-Galmés, Krzysztof Rusek, José Suárez-Varela +4
Network modeling is a fundamental tool in network research, design, and operation. Arguably the most popular method for modeling is Queuing Theory (QT). Its main limitation is that…
Generalised Score Distribution: A Two-Parameter Discrete Distribution Accurately Describing Responses from Quality of Experience Subjective Experiments
Jakub Nawała, Lucjan Janowski, Bogdan Ćmiel +2
Subjective responses from Multimedia Quality Assessment (MQA) experiments are conventionally analysed with methods not suitable for the data type these responses represent. Further…
Fine-grained network traffic prediction from coarse data
Krzysztof Rusek, Mathias Drton
ICT systems provide detailed information on computer network traffic. However, due to storage limitations, some of the information on past traffic is often only retained in an aggr…
RiskNet: Neural Risk Assessment in Networks of Unreliable Resources
Krzysztof Rusek, Piotr Boryło, Piotr Jaglarz +3
We propose a graph neural network (GNN)-based method to predict the distribution of penalties induced by outages in communication networks, where connections are protected by resou…
Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities
José Suárez-Varela, Paul Almasan, Miquel Ferriol-Galmés +8
Graph neural networks (GNN) have shown outstanding applications in many fields where data is fundamentally represented as graphs (e.g., chemistry, biology, recommendation systems).…
Scaling Graph-based Deep Learning models to larger networks
Miquel Ferriol-Galmés, José Suárez-Varela, Krzysztof Rusek +2
Graph Neural Networks (GNN) have shown a strong potential to be integrated into commercial products for network control and management. Early works using GNN have demonstrated an u…
The Graph Neural Networking Challenge: A Worldwide Competition for Education in AI/ML for Networks
José Suárez-Varela, Miquel Ferriol-Galmés, Albert López +21
During the last decade, Machine Learning (ML) has increasingly become a hot topic in the field of Computer Networks and is expected to be gradually adopted for a plethora of contro…
Describing Subjective Experiment Consistency by -Value P-P Plot
Jakub Nawała, Lucjan Janowski, Bogdan Ćmiel +1
There are phenomena that cannot be measured without subjective testing. However, subjective testing is a complex issue with many influencing factors. These interplay to yield eithe…
Initial characterization of interstellar comet 2I/Borisov
Piotr Guzik, Michał Drahus, Krzysztof Rusek +3
Interstellar comets penetrating through the Solar System had been anticipated for decades. The discovery of asteroidal-looking 'Oumuamua was thus a huge surprise and a puzzle. Furt…
Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case
Paul Almasan, José Suárez-Varela, Krzysztof Rusek +2
Deep Reinforcement Learning (DRL) has shown a dramatic improvement in decision-making and automated control problems. Consequently, DRL represents a promising technique to efficien…
RouteNet: Leveraging Graph Neural Networks for network modeling and optimization in SDN
Krzysztof Rusek, José Suárez-Varela, Paul Almasan +2
Network modeling is a key enabler to achieve efficient network operation in future self-driving Software-Defined Networks. However, we still lack functional network models able to…
Generalized Score Distribution
Lucjan Janowski, Bogdan Ćmiel, Krzysztof Rusek +2
A class of discrete probability distributions contains distributions with limited support, i.e. possible argument values are limited to a set of numbers (typically consecutive). Ex…
Notation for Subject Answer Analysis
Lucjan Janowski, Jakub Nawała, Werner Robitza +3
It is believed that consistent notation helps the research community in many ways. First and foremost, it provides a consistent interface of communication. Subjective experiments d…
Message-Passing Neural Networks Learn Little's Law
Krzysztof Rusek, Piotr Chołda
The paper presents a solution to the problem of universal representation of graphs exemplifying communication network topologies with the help of neural networks. The proposed appr…
Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN
Krzysztof Rusek, José Suárez-Varela, Albert Mestres +2
Network modeling is a critical component for building self-driving Software-Defined Networks, particularly to find optimal routing schemes that meet the goals set by administrators…
New Look at Finite Single Server Queue with Poisson Input and Semi-Markov Service Times
Krzysztof Rusek, Zdzisław Papir
The mathematics of the finite single server queue with Poisson input and semi-Markov service times() is similar to that used for systems. This observation re…