相关论文: Towards efficient feature sharing in MIMO architec…

Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sharing practice is to share the bottom layers of a deep…

The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with the width and soon gets saturated. In this case, we argue…

Parameter sharing is a key strategy in multi-agent reinforcement learning (MARL) for improving scalability, yet conventional fully shared architectures often collapse into homogeneous behaviors. Recent methods introduce diversity through…

Transformers have shown improved performance when compared to previous architectures for sequence processing such as RNNs. Despite their sizeable performance gains, as recently suggested, the model is computationally expensive to train and…

Deep convolutional neural networks (CNNs) have shown state-of-the-art performances in various computer vision tasks. Advances on CNN architectures have focused mainly on designing convolutional blocks of the feature extractors, but less on…

This paper describes a radio architecture for distributed spectrum sharing of multiple channels among secondary users (SUs) in a wide band of frequencies and a localized area. A novel Multichannel Immediate Multiple Access (MIMA) physical…

Complicated and deep neural network models can achieve high accuracy for image recognition. However, they require a huge amount of computations and model parameters, which are not suitable for mobile and embedded devices. Therefore,…

A novel dynamic hybrid beamforming architecture is proposed to achieve the spatial multiplexing-power consumption tradeoff for near-field multiple-input multiple-output (MIMO) networks, where each radio frequency (RF) chain is connected to…

Parameter sharing has proven to be a parameter-efficient approach. Previous work on Transformers has focused on sharing parameters in different layers, which can improve the performance of models with limited parameters by increasing model…

Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests…

This paper takes a new look at Cell-free Massive MIMO (multiple-input multiple-output) through the lens of the dynamic cooperation cluster framework from the Network MIMO literature. The purpose is to identify and address scalability issues…

Overparameterization, the condition where models have more parameters than necessary to fit their training loss, is a crucial factor for the success of deep learning. However, the characteristics of the features learned by overparameterized…

Industry and academia have been working towards the evolution from Centralized massive Multiple-Input Multiple-Output (CmMIMO) to Distributed mMIMO (DmMIMO) architectures. Instead of splitting a coverage area into many cells, each served by…

A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples. This corresponds to combining information between support and…

Multiple-input multiple-output (MIMO) radar is one of the leading depth sensing modalities. However, the usage of multiple receive channels lead to relative high costs and prevent the penetration of MIMOs in many areas such as the…

The performance of irregular phased array architectures is assessed in the context of multi-user multiple-input multiple-output (MU-MIMO) communications operating beyond 100 GHz. Realizing half-wavelength spaced planar phased arrays is…

This paper proposes a novel learning method for multi-task applications. Multi-task neural networks can learn to transfer knowledge across different tasks by using parameter sharing. However, sharing parameters between unrelated tasks can…

Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm called edge…

Hybrid beamforming is a promising technology to improve the energy efficiency of massive MIMO systems. In particular, subarray hybrid beamforming can further decrease power consumption by reducing the number of phase-shifters. However,…

This paper investigates the extent to which spectrum sharing in mmWave networks with multiple cellular operators is a viable alternative to traditional dedicated spectrum allocation. Specifically, we develop a general mathematical framework…