Related papers: Towards efficient feature sharing in MIMO architec…
We propose a parameter sharing method for Transformers (Vaswani et al., 2017). The proposed approach relaxes a widely used technique, which shares parameters for one layer with all layers such as Universal Transformers (Dehghani et al.,…
This paper considers a downlink cell-free multiple-input multiple-output (MIMO) network in which multiple multi-antenna access points (APs) serve multiple users via coherent joint transmission. In order to reduce the energy consumption by…
Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and dimensionality. This misalignment prevents graph models from…
Few-shot multimodal industrial anomaly detection is a critical yet underexplored task, offering the ability to quickly adapt to complex industrial scenarios. In few-shot settings, insufficient training samples often fail to cover the…
State-of-the-art schemes for performance analysis and optimization of multiple-input multiple-output systems generally experience degradation or even become invalid in dynamic complex scenarios with unknown interference and channel state…
Scaling the number of antennas up is a key characteristic of current and future wireless communication systems. The hardware cost and power consumption, however, motivate large-scale MIMO systems, especially at millimeter wave (mmWave)…
In this paper, we endeavour to seek a fundamental understanding of the potentials and limitations of training-based multiuser multiple-input multiple-output (MIMO) systems. In a multiuser MIMO system, users are geographically separated. So,…
Model merging is a flexible and computationally tractable approach to merge single-task checkpoints into a multi-task model. Prior work has solely focused on constrained multi-task settings where there is a one-to-one mapping between a…
Even if massive multiple-input multiple-output (MIMO) can theoretically bring huge benefits, it incurs substantial hardware complexity and expensive hardware costs. To address these issues while maintaining the system performance…
Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task.…
To mitigate the ever worsening "Power wall" and "Memory wall" problems, multi-core architectures with multilevel cache hierarchies have been widely accepted in modern processors. However, the complexity of the architectures makes modeling…
Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships. To address this weakness, we propose a…
Machine learning tasks are generally formulated as optimization problems, where one searches for an optimal function within a certain functional space. In practice, parameterized functional spaces are considered, in order to be able to…
Today, network devices share buffer across priority queues to avoid drops during transient congestion. While cost-effective most of the time, this sharing can cause undesired interference among seemingly independent traffic. As a result,…
We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision. To do so we exploit depth and relative camera pose cues to…
We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets. Early in training, wide neural networks trained on online data have not only identical loss curves but also…
Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from…
We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning. We leverage the assumption that learning from different tasks, sharing common properties,…
In this paper, we propose an energy-efficient radar beampattern design framework for a Millimeter Wave (mmWave) massive multi-input multi-output (mMIMO) system, equipped with a hybrid analog-digital (HAD) beamforming structure. Aiming to…
Future wireless communication systems are expected to explore spectral bands typically used by radar systems, in order to overcome spectrum congestion of traditional communication bands. Since in many applications radar and communication…