GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection
Massive MIMO (multiple-input multiple-output) detection is an important topic in wireless communication and various machine learning based methods have been developed recently for this task. Expectation Propagation (EP) and its variants are widely used for MIMO detection and have achieved the best p...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Lu, Qincheng Luan, Sitao Chang, Xiao-Wen |
description | Massive MIMO (multiple-input multiple-output) detection is an important topic
in wireless communication and various machine learning based methods have been
developed recently for this task. Expectation Propagation (EP) and its variants
are widely used for MIMO detection and have achieved the best performance.
However, EP-based solvers fail to capture the correlation between unknown
variables, leading to a loss of information, and in addition, they are
computationally expensive. In this paper, we show that the real-valued system
can be modeled as spectral signal convolution on graph, through which the
correlation between unknown variables can be captured. Based on such analysis,
we propose graph convolution-enhanced expectation propagation (GCEPNet).
GCEPNet incorporates data-dependent attention scores into Chebyshev polynomial
for powerful graph convolution with better generalization capacity. It enables
a better estimation of the cavity distribution for EP and empirically achieves
the state-of-the-art (SOTA) MIMO detection performance with much faster
inference speed. To our knowledge, we are the first to shed light on the
connection between the system model and graph convolution, and the first to
design the data-dependent coefficients for graph convolution. |
doi_str_mv | 10.48550/arxiv.2404.14886 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2404_14886</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2404_14886</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-c38db2e343ea98dfaedfd62a94b1be06401533e72fbd3d0f69647853151f5fb53</originalsourceid><addsrcrecordid>eNotj8tOwzAURL1hgQofwAr_QIIdP-J0h0IIlRraRcU2uomv20gljpwQlb-nD1YzmhmNdAh54iyWRin2AuHUzXEimYy5NEbfk68yL7afOC1pGWA40Nz3sz_-TJ3vo6I_QN-ipcVpwHaCS0i3wQ-wv3nnA61gHLsZabWqNvQNp_PwXD2QOwfHER__dUF278Uu_4jWm3KVv64j0KmOWmFsk6CQAiEz1gFaZ3UCmWx4g0xLxpUQmCauscIypzMtU6MEV9wp1yixIM-32ytYPYTuG8JvfQGsr4DiDxIAS5o</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection</title><source>arXiv.org</source><creator>Lu, Qincheng ; Luan, Sitao ; Chang, Xiao-Wen</creator><creatorcontrib>Lu, Qincheng ; Luan, Sitao ; Chang, Xiao-Wen</creatorcontrib><description>Massive MIMO (multiple-input multiple-output) detection is an important topic
in wireless communication and various machine learning based methods have been
developed recently for this task. Expectation Propagation (EP) and its variants
are widely used for MIMO detection and have achieved the best performance.
However, EP-based solvers fail to capture the correlation between unknown
variables, leading to a loss of information, and in addition, they are
computationally expensive. In this paper, we show that the real-valued system
can be modeled as spectral signal convolution on graph, through which the
correlation between unknown variables can be captured. Based on such analysis,
we propose graph convolution-enhanced expectation propagation (GCEPNet).
GCEPNet incorporates data-dependent attention scores into Chebyshev polynomial
for powerful graph convolution with better generalization capacity. It enables
a better estimation of the cavity distribution for EP and empirically achieves
the state-of-the-art (SOTA) MIMO detection performance with much faster
inference speed. To our knowledge, we are the first to shed light on the
connection between the system model and graph convolution, and the first to
design the data-dependent coefficients for graph convolution.</description><identifier>DOI: 10.48550/arxiv.2404.14886</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2024-04</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2404.14886$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2404.14886$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Lu, Qincheng</creatorcontrib><creatorcontrib>Luan, Sitao</creatorcontrib><creatorcontrib>Chang, Xiao-Wen</creatorcontrib><title>GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection</title><description>Massive MIMO (multiple-input multiple-output) detection is an important topic
in wireless communication and various machine learning based methods have been
developed recently for this task. Expectation Propagation (EP) and its variants
are widely used for MIMO detection and have achieved the best performance.
However, EP-based solvers fail to capture the correlation between unknown
variables, leading to a loss of information, and in addition, they are
computationally expensive. In this paper, we show that the real-valued system
can be modeled as spectral signal convolution on graph, through which the
correlation between unknown variables can be captured. Based on such analysis,
we propose graph convolution-enhanced expectation propagation (GCEPNet).
GCEPNet incorporates data-dependent attention scores into Chebyshev polynomial
for powerful graph convolution with better generalization capacity. It enables
a better estimation of the cavity distribution for EP and empirically achieves
the state-of-the-art (SOTA) MIMO detection performance with much faster
inference speed. To our knowledge, we are the first to shed light on the
connection between the system model and graph convolution, and the first to
design the data-dependent coefficients for graph convolution.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAURL1hgQofwAr_QIIdP-J0h0IIlRraRcU2uomv20gljpwQlb-nD1YzmhmNdAh54iyWRin2AuHUzXEimYy5NEbfk68yL7afOC1pGWA40Nz3sz_-TJ3vo6I_QN-ipcVpwHaCS0i3wQ-wv3nnA61gHLsZabWqNvQNp_PwXD2QOwfHER__dUF278Uu_4jWm3KVv64j0KmOWmFsk6CQAiEz1gFaZ3UCmWx4g0xLxpUQmCauscIypzMtU6MEV9wp1yixIM-32ytYPYTuG8JvfQGsr4DiDxIAS5o</recordid><startdate>20240423</startdate><enddate>20240423</enddate><creator>Lu, Qincheng</creator><creator>Luan, Sitao</creator><creator>Chang, Xiao-Wen</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240423</creationdate><title>GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection</title><author>Lu, Qincheng ; Luan, Sitao ; Chang, Xiao-Wen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-c38db2e343ea98dfaedfd62a94b1be06401533e72fbd3d0f69647853151f5fb53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Lu, Qincheng</creatorcontrib><creatorcontrib>Luan, Sitao</creatorcontrib><creatorcontrib>Chang, Xiao-Wen</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lu, Qincheng</au><au>Luan, Sitao</au><au>Chang, Xiao-Wen</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection</atitle><date>2024-04-23</date><risdate>2024</risdate><abstract>Massive MIMO (multiple-input multiple-output) detection is an important topic
in wireless communication and various machine learning based methods have been
developed recently for this task. Expectation Propagation (EP) and its variants
are widely used for MIMO detection and have achieved the best performance.
However, EP-based solvers fail to capture the correlation between unknown
variables, leading to a loss of information, and in addition, they are
computationally expensive. In this paper, we show that the real-valued system
can be modeled as spectral signal convolution on graph, through which the
correlation between unknown variables can be captured. Based on such analysis,
we propose graph convolution-enhanced expectation propagation (GCEPNet).
GCEPNet incorporates data-dependent attention scores into Chebyshev polynomial
for powerful graph convolution with better generalization capacity. It enables
a better estimation of the cavity distribution for EP and empirically achieves
the state-of-the-art (SOTA) MIMO detection performance with much faster
inference speed. To our knowledge, we are the first to shed light on the
connection between the system model and graph convolution, and the first to
design the data-dependent coefficients for graph convolution.</abstract><doi>10.48550/arxiv.2404.14886</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2404.14886 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2404_14886 |
source | arXiv.org |
subjects | Computer Science - Learning |
title | GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T09%3A05%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=GCEPNet:%20Graph%20Convolution-Enhanced%20Expectation%20Propagation%20for%20Massive%20MIMO%20Detection&rft.au=Lu,%20Qincheng&rft.date=2024-04-23&rft_id=info:doi/10.48550/arxiv.2404.14886&rft_dat=%3Carxiv_GOX%3E2404_14886%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |