Sorry, you need to enable JavaScript to visit this website.

We consider a cooperative cognitive wireless network sce- nario where a primary wireless network is co-located with a cognitive (or secondary) network. In the considered scenario, the nodes of the secondary network make local binary de- cisions about the presence of a signal emitted by a primary node. Then, they transmit their decisions to a fusion center (FC). The final decision about the channel state is up to the FC by means of a proper fusion rule.

Current research on multi-antenna architectures is trending towards increasing the amount of antennas in the base stations (BSs) so as to increase the spectral efficiency. As a result, the interconnection bandwidth and computational complexity required to process the data using centralized architectures is becoming prohibitively high. Decentralized architectures can reduce these requirements by pre-processing the data before it arrives at a central processing unit (CPU).

Cell-free massive multiple-input multiple-output (MIMO) consists of a large set of distributed access points (APs) serving a number of users. The APs can be far from each other, and they can also have a big number of antennas. Thus, decentralized architectures have to be considered so as to reduce the interconnection bandwidth to a central processing unit (CPU) and make the system scalable. On the other hand, the APs in a heterogeneous network might have limited processing capabilities and fully-decentralized processing may not be available.

This work examines the problem of learning the topology of a network (graph learning) from the signals produced at a subset of the network nodes (partial observability). This challenging problem was recently tackled assuming that the topology is drawn according to an Erdős-Rényi model, for which it was shown that graph learning under partial observability is achievable, exploiting in particular homogeneity across nodes and independence across edges.

This work examines the problem of learning the topology of a network (graph learning) from the signals produced at a subset of the network nodes (partial observability). This challenging problem was recently tackled assuming that the topology is drawn according to an Erdős-Rényi model, for which it was shown that graph learning under partial observability is achievable, exploiting in particular homogeneity across nodes and independence across edges.

The cooperative relay network is a type of multi-terminal communication system. We present in this paper a Neural Network (NN)-based autoencoder (AE) approach to optimize its design. This approach implements a classical three-node cooperative system as one AE model, and uses a two-stage scheme to train this model and minimize the designed losses. We demonstrate that this approach shows performance close to the best baseline in decode-and-forward (DF), and outperforms the best baseline in amplify-and-forward (AF), over a wide range of signal-to-noise-ratio (SNR) values.