D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
Inference from data is of key importance in many applications of informatics. The current trend in performing such a task of inference from data is to utilise machine learning algorithms. Moreover, in many applications that it is either required or is pref ...
In this paper, we combine network coding and tomographic techniques for topology inference. Our goal is to infer the topology of a network by sending probes between a given set of multiple sources and multiple receivers and by having intermediate nodes per ...
This paper describes a new kind of genetic representation called analog genetic encoding (AGE). The representation is aimed at the evolutionary synthesis and reverse engineering of circuits and networks such as analog electronic circuits, neural networks, ...
We consider the problem of finding the minimum number of transmissions in an ad-hoc network for all-to-all broadcasting using network coding. This work generalizes previous results for canonical topologies such as the circle and the wrap around grid to the ...
Failure restoration at the IP layer in IP-over-WDM networks requires to map the IP topology on the WDM topology in such a way that a failure at the WDM layer leaves the IP topology connected. Such a mapping is called survivable. Finding a survivable mappin ...
Unstructured overlay networks are driven by simple protocols that are easy to analyze and implement. The lack of structure, however, leads to weak message delivery guarantees and poor scaling. Structured overlays impose a global overlay topology that is th ...
Analytic queueing network models constitute a flexible tool for the study of network flow. These aggregate models are simple to manipulate and their analytic aspect renders them suitable for use within an optimization framework. Analytic queueing network m ...
Analytic queueing network models constitute a flexible tool for the study of network flow. These aggregate models are simple to manipulate and their analytic aspect renders them suitable for use within an optimization framework. Analytic queueing network m ...
A statistical physics perspective of complex networks: from the architecture of the Internet and the brain to the spreading of an epidemic Statistical physics has revealed itself as the ideal framework to describe large networks appearing in a variety of d ...
Analytic queueing network models often assume infinite capacity for all queues. For real systems this infinite capacity assumption does not hold, but is often maintained due to the difficulty of grasping the between-queue correlation structure present in f ...
