Related papers: Locally Orthogonal Training Design for Cloud-RANs …

Owing to their remarkable representation capabilities for heterogeneous graph data, Heterogeneous Graph Neural Networks (HGNNs) have been widely adopted in many critical real-world domains such as recommendation systems and medical…

The baseband-up centralization architecture of radio access networks (C-RAN) has recently been proposed to support efficient cooperative communications and reduce deployment and operational costs. However, the massive fronthaul bandwidth…

We propose to use stochastic Riemannian coordinate descent on the orthogonal group for recurrent neural network training. The algorithm rotates successively two columns of the recurrent matrix, an operation that can be efficiently…

The task of finding an extension to a given partial drawing of a graph while adhering to constraints on the representation has been extensively studied in the literature, with well-known results providing efficient algorithms for…

Graph Neural Networks (GNNs) have achieved remarkable performance on graph-based tasks. The key idea for GNNs is to obtain informative representation through aggregating information from local neighborhoods. However, it remains an open…

Spatio-temporal forecasting is challenging attributing to the high nonlinearity in temporal dynamics as well as complex location-characterized patterns in spatial domains, especially in fields like weather forecasting. Graph convolutions…

A cloud radio access network (C-RAN) is considered as a candidate to meet the expectations of higher data rate de- mands in wireless networks. In C-RAN, low energy base stations (BSs) are deployed over a small geography and are allowed to…

Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and in particular in medical imaging where local structures of tissues occur at arbitrary rotations. LRI constituted the cornerstone of several…

Imposing orthogonality on the layers of neural networks is known to facilitate the learning by limiting the exploding/vanishing of the gradient; decorrelate the features; improve the robustness. This paper studies the theoretical properties…

A key problem in the design of cloud radio access networks (CRANs) is that of devising effective baseband compression strategies for transmission on the fronthaul links connecting a remote radio head (RRH) to the managing central unit (CU).…

Cognitive Radio Networks (CRNs) are considered as a promising solution to the spectrum shortage problem in wireless communication. In this paper, we initiate the first systematic study on the algorithmic complexity of the connectivity…

In this paper, we propose a super-resolution wideband beam training method for near-field communications, which is able to achieve ultra-low overhead. To this end, we first study the multi-beam characteristic of a sparse uniform linear…

The cloud-radio access network (CRAN) is expected to be the core network architecture for next generation mobile radio systems. In this paper, we consider the downlink of a CRAN formed of one central processor (the cloud) and several…

Multi-view learning has progressed rapidly in recent years. Although many previous studies assume that each instance appears in all views, it is common in real-world applications for instances to be missing from some views, resulting in…

Scalability of graph neural networks remains one of the major challenges in graph machine learning. Since the representation of a node is computed by recursively aggregating and transforming representation vectors of its neighboring nodes…

Graph Neural Networks (GNNs) are routinely used in molecular physics, social sciences, and economics to model many-body interactions in graph-like systems. However, GNNs are inherently local and can suffer from information flow bottlenecks.…

Training Graph Convolutional Networks (GCNs) is expensive as it needs to aggregate data recursively from neighboring nodes. To reduce the computation overhead, previous works have proposed various neighbor sampling methods that estimate the…

In this paper, we devise a highly efficient machine learning-based channel estimation for orthogonal frequency division multiplexing (OFDM) systems, in which the training of the estimator is performed online. A simple learning module is…

We present Locally Orderless Networks (LON) and its theoretic foundation which links it to Convolutional Neural Networks (CNN), to Scale-space histograms, and measurement theory. The key elements are a regular sampling of the bias and the…

Constructing the adjacency graph is fundamental to graph-based clustering. Graph learning in kernel space has shown impressive performance on a number of benchmark data sets. However, its performance is largely determined by the chosen…