Unfolding WMMSE Using Graph Neural Networks for Efficient Power Allocation

Chowdhury, A. R.; Verma, Gunjan; Rao, Chirag; Swami, Ananthram; Segarra, Santiago

doi:10.1109/twc.2021.3071480

Cited by 107 publications

(69 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of GMD found in the literature include the adjacency matrix [37,38], the Laplacian matrix [39], and their normalized counterparts [5,15]. In the context of robot communications, the GMD can be used to represent channel information [41,42].…”

Section: Wide and Deep Graph Neural Networkmentioning

confidence: 99%

Wide and Deep Graph Neural Network with Distributed Online Learning

Gao,

Gama,

Ribeiro

2021

Preprint

View full text Add to dashboard Cite

Graph neural networks (GNNs) are naturally distributed architectures for learning representations from network data. This renders them suitable candidates for decentralized tasks.In these scenarios, the underlying graph often changes with time due to link failures or topology variations, creating a mismatch between the graphs on which GNNs were trained and the ones on which they are tested. Online learning can be leveraged to retrain GNNs at testing time to overcome this issue. However, most online algorithms are centralized and usually offer guarantees only on convex problems, which GNNs rarely lead to. This paper develops the Wide and Deep GNN (WD-GNN), a novel architecture that can be updated with distributed online learning mechanisms. The WD-GNN consists of two components: the wide part is a linear graph filter and the deep part is a nonlinear GNN. At training time, the joint wide and deep architecture learns nonlinear representations from data. At testing time, the wide, linear part is retrained, while the deep, nonlinear one remains fixed. This often leads to a convex formulation. We further propose a distributed online learning algorithm that can be implemented in a decentralized setting. We also show the stability of the WD-GNN to changes of the underlying graph and analyze the convergence of the proposed online learning procedure. Experiments on movie recommendation, source localization and robot swarm control corroborate theoretical findings and show the potential of the WD-GNN for distributed online learning.

show abstract

Section: Wide and Deep Graph Neural Networkmentioning

confidence: 99%

Wide and Deep Graph Neural Network with Distributed Online Learning

Gao,

Gama,

Ribeiro

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To overcome this issue, a graph neural network (GNN) has been applied in wireless communication systems [27]- [31]. This is an extension of a CNN to graph domains where graph convolutional operations aggregate interconnected node inputs.…”

Section: B Universal Formulationmentioning

confidence: 99%

“…Parameters shared by nodes among subgraph combinations lead to flexible structures realized by a stack of graph filter layers. This approach lends itself to scalable solutions of massive identification applications such as multi-antenna channel estimation [27], link scheduling [28], and resource management [29]- [31]. However, a decentralized realization based on this framework has not been properly addressed especially via backhaul coordination mechanisms, i.e., in [27]- [29], centralized data collection steps are necessary for the global network information.…”

Section: B Universal Formulationmentioning

confidence: 99%

“…However, a decentralized realization based on this framework has not been properly addressed especially via backhaul coordination mechanisms, i.e., in [27]- [29], centralized data collection steps are necessary for the global network information. Although a few distributed GNN implementations are presented [30], [31], handcrafted interaction policies request fixed topology configurations. Thus, all node pairs guaranteed by dedicated connections [31] prevents the variation of social graph G S .…”

Section: B Universal Formulationmentioning

confidence: 99%

“…Although a few distributed GNN implementations are presented [30], [31], handcrafted interaction policies request fixed topology configurations. Thus, all node pairs guaranteed by dedicated connections [31] prevents the variation of social graph G S . Furthermore, an identical structure of the corresponding physical and social domains undermines an adaptation to a practical networking setup where interfering nodes are not aligned with communicating ones.…”

Section: B Universal Formulationmentioning

confidence: 99%

See 2 more Smart Citations

Learning Autonomy in Management of Wireless Random Networks

Lee¹,

Lee²,

Quek³

2021

Preprint

View full text Add to dashboard Cite

This paper presents a machine learning strategy that tackles a distributed optimization task in a wireless network with an arbitrary number of randomly interconnected nodes. Individual nodes decide their optimal states with distributed coordination among other nodes through randomly varying backhaul links. This poses a technical challenge in distributed universal optimization policy robust to a random topology of the wireless network, which has not been properly addressed by conventional deep neural networks (DNNs) with rigid structural configurations. We develop a flexible DNN formalism termed distributed message-passing neural network (DMPNN) with forward and backward computations independent of the network topology. A key enabler of this approach is an iterative message-sharing strategy through arbitrarily connected backhaul links. The DMPNN provides a convergent solution for for collecting inputs from local nodes and evaluating a valid DNN output. By contrast, a learning to cooperate formalism [20], [22] has been recently introduced to tackle the distributed network management in [12]- [14]. The underlying policy is to decouple a node operation into two component DNN units: a message generator and a distributed optimizer. The message generator encodes locally available information into messages. The messages are subsequently transferred to nearby nodes over network links. The distributed optimizer combines incoming messages to determine the optimal state of the corresponding node. These units are trained offline in a centralized domain, while their inference is conducted on the fly in a decentralized manner.Distributed wireless systems, e.g., internet-of-things (IoT) and wireless sensor networks, entail network configurations, such as network topology and node population, that are given arbitrarily and change gradually. However, existing distributed DL methods [12]-[14] fail to grasp these random features since either the DNNs become ineligible to accommodate all possible candidates of networking setup for the limit of the capacity or their computations readily become prohibitively demanding. This gives rise to the necessity of a universal DL framework applicable to arbitrary network configurations.We consider a distributed optimization problem over a random network. The distributed coordination allows nodes to share messages through backhaul links. Individual nodes produce the optimal solution based on messages along with local information. In reality, direct interactions among all nodes are not possible due to the absence of the backhaul links. Thus, the network model is inherently an undirected graph with randomly connected edges. With a graphical network model, an efficient DL computation structure of distributed optimizations is investigated. A single node aiming at distributed message-passing (DMP) inference is constructed with message generation, message reception, state update, and distributed decision. Each node generates a message dedicated to an adjacent node that is connected by a backhaul link. S...

show abstract

Resource Allocation in Heterogeneous Network with Supervised GNNs

Sun

Zhang

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Unfolding WMMSE Using Graph Neural Networks for Efficient Power Allocation

Cited by 107 publications

References 70 publications

Wide and Deep Graph Neural Network with Distributed Online Learning

Wide and Deep Graph Neural Network with Distributed Online Learning

Learning Autonomy in Management of Wireless Random Networks

Resource Allocation in Heterogeneous Network with Supervised GNNs

Contact Info

Product

Resources

About