Related papers: Towards efficient feature sharing in MIMO architec…

In many distributed learning problems, the heterogeneous loading of computing machines may harm the overall performance of synchronous strategies. In this paper, we propose an effective asynchronous distributed framework for the…

Large models support great zero-shot and few-shot capabilities. However, updating these models on new tasks can break performance on previous seen tasks and their zero/few-shot unseen tasks. Our work explores how to update zero/few-shot…

In this paper, we address two crucial challenges in the design of cell-free (CF) systems: degradation in the performance of CF systems by imperfect channel state information at the transmitter (CSIT) and high computational/signaling loads…

Intelligent reflecting surface (IRS) has been considered as a revolutionary technology to enhance the wireless communication performance. To cater for multiple mobile users, adjusting IRS beamforming patterns over time, i.e., dynamic IRS…

Channel state information (CSI) feedback is necessary for the frequency division duplexing (FDD) multiple input multiple output (MIMO) systems due to the channel non-reciprocity. With the help of deep learning, many works have succeeded in…

Cell-free massive multiple-input multiple-output (MIMO), with a large number of distributed access points (APs) that jointly serve the user equipments (UEs), is a promising network architecture for future wireless communications. To reduce…

Automated incident management is critical for microservice reliability. While recent unified frameworks leverage multimodal data for joint optimization, they unrealistically assume perfect data completeness. In practice, network…

We consider the problem of learning a function respecting a symmetry from among a class of symmetries. We develop a unified framework that enables symmetry discovery across a broad range of subgroups including locally symmetric, dihedral…

Beam codebooks are integral components of the future millimeter wave (mmWave) multiple input multiple output (MIMO) system to relax the reliance on the instantaneous channel state information (CSI). The design of these codebooks, therefore,…

A novel over-the-air machine learning framework over multi-hop multiple-input and multiple-output (MIMO) networks is proposed. The core idea is to imitate fully connected (FC) neural network layers using multiple MIMO channels by carefully…

The physical layer foundations of cell-free massive MIMO (CF-mMIMO) have been well-established. As a next step, researchers are investigating practical and energy-efficient network implementations. This paper focuses on multiple sets of…

For years the model performance in machine learning obeyed a power-law relationship with the model size. For the consideration of parameter efficiency, recent studies focus on increasing model depth rather than width to achieve better…

Neural networks for multi-domain learning empowers an effective combination of information from different domains by sharing and co-learning the parameters. In visual tracking, the emerging features in shared layers of a multi-domain…

Massive multi-input multi-output (MIMO) has evolved along two tracks: cellular and cell-free, each with unique advantages and limitations. The cellular approach suffers from worse user spectral efficiency at cell edges, whereas the…

Multi-scale architectures have shown effectiveness in a variety of tasks thanks to appealing cross-scale complementarity. However, existing architectures treat different scale features equally without considering the scale-specific…

Vision Transformers (ViTs) have underpinned the recent breakthroughs in computer vision. However, designing the architectures of ViTs is laborious and heavily relies on expert knowledge. To automate the design process and incorporate…

Multi-task learning, which optimizes performance across multiple tasks, is inherently a multi-objective optimization problem. Various algorithms are developed to provide discrete trade-off solutions on the Pareto front. Recently, continuous…

Mutual Coupling (MC) is an unavoidable feature in Reconfigurable Intelligent Surfaces (RISs) with sub-wavelength inter-element spacing. Its inherent presence naturally leads to non-local RIS structures, which can be efficiently described…

The theory of multiple-input multiple-output (MIMO) technology has been well-developed to increase fading channel capacity over single-input single-output (SISO) systems. This capacity gain can often be leveraged by utilizing channel state…

Multi-task learning is an open and challenging problem in computer vision. The typical way of conducting multi-task learning with deep neural networks is either through handcrafted schemes that share all initial layers and branch out at an…