Related papers: GFlowNets for Active Learning Based Resource Alloc…

With the rapid proliferation of smart mobile devices, federated learning (FL) has been widely considered for application in wireless networks for distributed model training. However, data heterogeneity, e.g., non-independently identically…

Owing to the use of attention mechanism to leverage the dependency across tokens, Transformers are efficient for natural language processing. By harnessing permutation properties broadly exist in resource allocation policies, each mapping…

The field of wireless networks has been rapidly developed during the past decade due to the increasing popularity of the mobile devices. The great demand for mobility and connectivity makes wireless networking a field whose continuous…

In the last few years there has been significant growth in the area of wireless communication. IEEE 802.16/WiMAX is the network which is designed for providing high speed wide area broadband wireless access; WiMAX is an emerging wireless…

The optimal scheduling of interfering links in a dense wireless network with full frequency reuse is a challenging task. The traditional method involves first estimating all the interfering channel strengths then optimizing the scheduling…

The next-generation of wireless networks will enable many machine learning (ML) tools and applications to efficiently analyze various types of data collected by edge devices for inference, autonomy, and decision making purposes. However,…

Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward function. However, learning efficiency is constrained by the…

This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects proportionally to a given reward function through the trajectory of state transitions. In this work, we observe that GFlowNets tend to under-exploit the…

The next generation wireless networks (i.e. 5G and beyond), which would be extremely dynamic and complex due to the ultra-dense deployment of heterogeneous networks (HetNets), poses many critical challenges for network planning, operation,…

Residual radio resources are abundant in wireless networks due to dynamic traffic load, which can be exploited to support high throughput for serving non-real-time (NRT) traffic. In this paper, we investigate how to achieve this by resource…

In cellular networks, resource allocation is performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper investigates the distributed resource allocation…

Generative Flow Networks (GFlowNets) have shown promising potential to generate high-scoring candidates with probability proportional to their rewards. As existing GFlowNets freely explore in state space, they encounter significant…

LoRa wireless networks are considered as a key enabling technology for next generation internet of things (IoT) systems. New IoT deployments (e.g., smart city scenarios) can have thousands of devices per square kilometer leading to huge…

With rapidly increasing distributed deep learning workloads in large-scale data centers, efficient distributed deep learning framework strategies for resource allocation and workload scheduling have become the key to high-performance deep…

Conventionally, the resource allocation is formulated as an optimization problem and solved online with instantaneous scenario information. Since most resource allocation problems are not convex, the optimal solutions are very difficult to…

The increasing demands of various high data rate wireless applications have been seen in the recent years and it will continue in the future. To fulfill these demands, the limited existing wireless resources should be utilized properly or…

The conventional model aggregation-based federated learning (FL) approach requires all local models to have the same architecture, which fails to support practical scenarios with heterogeneous local models. Moreover, frequent model exchange…

Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE…

This paper proposes three novel resource and user scheduling algorithms with contiguous frequency-domain resource allocation (FDRA) for wireless communications systems. The first proposed algorithm jointly schedules users and resources…

While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient…