DeepGate2: Functionality-Aware Circuit Representation Learning

Circuit representation learning aims to obtain neural repre-sentations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks. Existing solutions, such as DeepGate, have the potential to embed both circuit structural informa...

Full description

Saved in:
Bibliographic Details
Published in:Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design pp. 1 - 9
Main Authors: Shi, Zhengyuan, Pan, Hongyang, Khan, Sadaf, Li, Min, Liu, Yi, Huang, Junhua, Zhen, Hui-Ling, Yuan, Mingxuan, Chu, Zhufei, Xu, Qiang
Format: Conference Proceeding
Language:English
Published: IEEE 28.10.2023
Subjects:
ISSN:1558-2434
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Circuit representation learning aims to obtain neural repre-sentations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks. Existing solutions, such as DeepGate, have the potential to embed both circuit structural information and functional behavior. However, their capabilities are limited due to weak supervision or flawed model design, resulting in unsatisfactory performance in downstream tasks. In this paper, we introduce Deep Gate2, a novel functionality-aware learning framework that significantly improves upon the original DeepGate solution in terms of both learning effectiveness and efficiency. Our approach involves using pairwise truth table differences between sampled logic gates as training supervision, along with a well-designed and scalable loss function that explicitly considers circuit functionality. Additionally, we consider inherent circuit characteristics and design an efficient one-round graph neural network (GNN), resulting in an order of magnitude faster learning speed than the original DeepGate solution. Experimental results demonstrate significant improvements in two practical downstream tasks: logic synthesis and Boolean satisfiability solving. The code is available at https://github.com/cure-lablDeepGate2.
AbstractList Circuit representation learning aims to obtain neural repre-sentations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks. Existing solutions, such as DeepGate, have the potential to embed both circuit structural information and functional behavior. However, their capabilities are limited due to weak supervision or flawed model design, resulting in unsatisfactory performance in downstream tasks. In this paper, we introduce Deep Gate2, a novel functionality-aware learning framework that significantly improves upon the original DeepGate solution in terms of both learning effectiveness and efficiency. Our approach involves using pairwise truth table differences between sampled logic gates as training supervision, along with a well-designed and scalable loss function that explicitly considers circuit functionality. Additionally, we consider inherent circuit characteristics and design an efficient one-round graph neural network (GNN), resulting in an order of magnitude faster learning speed than the original DeepGate solution. Experimental results demonstrate significant improvements in two practical downstream tasks: logic synthesis and Boolean satisfiability solving. The code is available at https://github.com/cure-lablDeepGate2.
Author Chu, Zhufei
Xu, Qiang
Li, Min
Shi, Zhengyuan
Zhen, Hui-Ling
Pan, Hongyang
Liu, Yi
Yuan, Mingxuan
Huang, Junhua
Khan, Sadaf
Author_xml – sequence: 1
  givenname: Zhengyuan
  surname: Shi
  fullname: Shi, Zhengyuan
  email: zyshi21@cse.cuhk.edu.hk
  organization: The Chinese University of Hong Kong
– sequence: 2
  givenname: Hongyang
  surname: Pan
  fullname: Pan, Hongyang
  organization: Ningbo University
– sequence: 3
  givenname: Sadaf
  surname: Khan
  fullname: Khan, Sadaf
  email: skhan@cse.cuhk.edu.hk
  organization: The Chinese University of Hong Kong
– sequence: 4
  givenname: Min
  surname: Li
  fullname: Li, Min
  email: mli@cse.cuhk.edu.hk
  organization: The Chinese University of Hong Kong
– sequence: 5
  givenname: Yi
  surname: Liu
  fullname: Liu, Yi
  email: yliu22@cse.cuhk.edu.hk
  organization: The Chinese University of Hong Kong
– sequence: 6
  givenname: Junhua
  surname: Huang
  fullname: Huang, Junhua
  organization: Huawei,Noah's Ark Lab
– sequence: 7
  givenname: Hui-Ling
  surname: Zhen
  fullname: Zhen, Hui-Ling
  organization: Huawei,Noah's Ark Lab
– sequence: 8
  givenname: Mingxuan
  surname: Yuan
  fullname: Yuan, Mingxuan
  organization: Huawei,Noah's Ark Lab
– sequence: 9
  givenname: Zhufei
  surname: Chu
  fullname: Chu, Zhufei
  organization: Ningbo University
– sequence: 10
  givenname: Qiang
  surname: Xu
  fullname: Xu, Qiang
  email: qxu@cse.cuhk.edu.hk
  organization: The Chinese University of Hong Kong
BookMark eNo1T21LwzAYjKLgNvcP_NA_0Jo8aZrED8LoXhwUBNHP42n2VCIzK2mG7N9bUT8dd9wdd1N2FY6BGMsEL4Tg9n5b14ul0tLyAjjIQnAJUltzweZ2BKlGDqDUJZsIpUwOpSxv2HQYPjgfA6aasMclUb_BRPCQrU_BJX8MePDpnC--MFJW--hOPmUv1EcaKCT8cWQNYQw-vN-y6w4PA83_cMbe1qvX-ilvnjfbetHkHniZ8nEVt6Xag9MGjSxhVDVUEixq1Tpq9R47EE63DjWOAnZcGIdWUNW2lZAzdvfb64lo10f_ifG8-_8rvwG2skxS
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICCAD57390.2023.10323798
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350322255
EISSN 1558-2434
EndPage 9
ExternalDocumentID 10323798
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62274100
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IF
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
FEDTE
IEGSK
IJVOP
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i204t-2370945d2c78a8342204726329a75bceb7daf21c7bca7abceaf018ca91e6bb613
IEDL.DBID RIE
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001116715100111&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:22:16 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-2370945d2c78a8342204726329a75bceb7daf21c7bca7abceaf018ca91e6bb613
PageCount 9
ParticipantIDs ieee_primary_10323798
PublicationCentury 2000
PublicationDate 2023-Oct.-28
PublicationDateYYYYMMDD 2023-10-28
PublicationDate_xml – month: 10
  year: 2023
  text: 2023-Oct.-28
  day: 28
PublicationDecade 2020
PublicationTitle Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design
PublicationTitleAbbrev ICCAD
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020286
Score 2.4427714
Snippet Circuit representation learning aims to obtain neural repre-sentations of circuit elements and has emerged as a promising research direction that can be...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Computational modeling
Design automation
Graph neural networks
Logic gates
Predictive models
Representation learning
Training
Title DeepGate2: Functionality-Aware Circuit Representation Learning
URI https://ieeexplore.ieee.org/document/10323798
WOSCitedRecordID wos001116715100111&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED3RigEWvor4VgZWt6lj52wGJFSoQEJVhQB1q2zHQVnSKqTw97HdtMDAwGZZchKfpby78713AJcyY0JhwlxYkmjC0GiiUOeEOjiJYyU0BjmG10ccjcRkIscNWT1wYay1ofjMdv0w3OVnM7PwqbKeF39LUIoWtBDTJVlrHV05oExXpTqx7D0M3FY4upC-6zuEd1drf3VRCSAy3Pnn63eh803Hi8ZroNmDDVvuw_YPJcEDuL61du4zYfQqGjqoWmb4nIdNbj5VZaNBUZlFUUdPofC14RuVUaOu-taBl-Hd8-CeNK0RSEFjVhP3HS4u4xk1KJRIGKVe9TFNqFTItbEaM5XTvkFtFCo3ofK4L4ySfZtq7c7lENrlrLRHEDmXIGfeL8ypZkZIxXLFuXs056nJuDqGjjfFdL5Uv5iurHDyx_wpbHmD-_87FWfQrquFPYdN81EX79VFOLMvOpSXCw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED1BQQIWvor4JgOr29SxY5sBCRWqVpSqQgV1q2zHQVnSKqTw97HdtMDAwGZZcuTcSXl3l3vvAK5FQrhkEbFpSaQQYVohyVSKsIWTMJRcMS_H8NpngwEfj8WwIqt7LowxxjefmYZb-n_5yVTPXams6cTfIib4OmxQQnC4oGut8isLlfGyWScUzV7bvgxlNqlvuBnhjeXpX3NUPIx0dv95gT2ofxPyguEKavZhzeQHsPNDS_AQbu-NmblaGL4JOhasFjU-G2Oju09ZmKCdFXqelcGzb32tGEd5UOmrvtXhpfMwandRNRwBZTgkJbL3sJkZTbBmXPKIYOx0H-MIC8mo0kaxRKa4pZnSkkm7IdOwxbUULRMrZT1zBLV8mptjCGxQkBIXGaZYEc2FJKmk1D6a0lgnVJ5A3ZliMlvoX0yWVjj9Y_8Ktrqjp_6k3xs8nsG2M7772mN-DrWymJsL2NQfZfZeXHr_fQFHmppS
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Digest+of+technical+papers+-+IEEE%2FACM+International+Conference+on+Computer-Aided+Design&rft.atitle=DeepGate2%3A+Functionality-Aware+Circuit+Representation+Learning&rft.au=Shi%2C+Zhengyuan&rft.au=Pan%2C+Hongyang&rft.au=Khan%2C+Sadaf&rft.au=Li%2C+Min&rft.date=2023-10-28&rft.pub=IEEE&rft.eissn=1558-2434&rft.spage=1&rft.epage=9&rft_id=info:doi/10.1109%2FICCAD57390.2023.10323798&rft.externalDocID=10323798