Can Short Hypervectors Drive Feature-Rich GNNs? Strengthening the Graph Representation of Hyperdimensional Computing for Memory-efficient GNNs
Hyperdimensional computing (HDC) based GNNs are significantly advancing the brain-like cognition in terms of mathematical rigorousness and computational tractability. However, the researches in this field seem to have a "long vector consensus" that the length of HDC-hypervectors must be de...
Uloženo v:
| Vydáno v: | 2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 7 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
22.06.2025
|
| Témata: | |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Hyperdimensional computing (HDC) based GNNs are significantly advancing the brain-like cognition in terms of mathematical rigorousness and computational tractability. However, the researches in this field seem to have a "long vector consensus" that the length of HDC-hypervectors must be designed to mimic that of cerebellar cortex, i.e., ten thousands of bits, to express human's feature-rich memory. To system architects, this choice presents a formidable challenge that the combination of numerous nodes and ultra-long hypervectors could create a new memory bottleneck that undermines the operational brevity from HDC. To overcome above problem, in this work, we shift our focus to rebuilding a set of more GNN-friendly HDC-operations, by which, short hypervectors are sufficient to encode rich features via enjoining the strong error tolerance of neural cognition. To achieve that, three behavioral incompatibilities of HDC with general GNNs, i.e., feature distortion, structural bias, and central-node vacancy, are found and successfully resolved for more efficient feature-extraction in graphs. Taken as a whole, a memory-efficient HDC-based GNN framework, called CiliaGraph, is designed to drive one-shot graph classifying tasks with only hundreds of bits in hypervector aggregation, which offers 1 to 2 orders of memory savings. The results show that, compared to the SOTA GNNs, CiliaGraph reduces the memory access and training latency by an average of 292 \times (up to 2341 \times) and 103 \times (up to 313 \times), respectively, while maintaining the competitively accuracy. |
|---|---|
| AbstractList | Hyperdimensional computing (HDC) based GNNs are significantly advancing the brain-like cognition in terms of mathematical rigorousness and computational tractability. However, the researches in this field seem to have a "long vector consensus" that the length of HDC-hypervectors must be designed to mimic that of cerebellar cortex, i.e., ten thousands of bits, to express human's feature-rich memory. To system architects, this choice presents a formidable challenge that the combination of numerous nodes and ultra-long hypervectors could create a new memory bottleneck that undermines the operational brevity from HDC. To overcome above problem, in this work, we shift our focus to rebuilding a set of more GNN-friendly HDC-operations, by which, short hypervectors are sufficient to encode rich features via enjoining the strong error tolerance of neural cognition. To achieve that, three behavioral incompatibilities of HDC with general GNNs, i.e., feature distortion, structural bias, and central-node vacancy, are found and successfully resolved for more efficient feature-extraction in graphs. Taken as a whole, a memory-efficient HDC-based GNN framework, called CiliaGraph, is designed to drive one-shot graph classifying tasks with only hundreds of bits in hypervector aggregation, which offers 1 to 2 orders of memory savings. The results show that, compared to the SOTA GNNs, CiliaGraph reduces the memory access and training latency by an average of 292 \times (up to 2341 \times) and 103 \times (up to 313 \times), respectively, while maintaining the competitively accuracy. |
| Author | Wang, Jihe Wang, Danghui Han, Yuxi |
| Author_xml | – sequence: 1 givenname: Jihe surname: Wang fullname: Wang, Jihe email: wangjihe@nwpu.edu.cn organization: Northwestern Polytechnical University,School of Computer Science,Xi'an,China – sequence: 2 givenname: Yuxi surname: Han fullname: Han, Yuxi email: hyx956@mail.nwpu.edu.cn organization: Northwestern Polytechnical University,Engineering Research Center of Embedded System Integration Ministry of Education,Xi'an,China – sequence: 3 givenname: Danghui surname: Wang fullname: Wang, Danghui email: wangdh@nwpu.edu.cn organization: Northwestern Polytechnical University,Engineering Research Center of Embedded System Integration Ministry of Education,Xi'an,China |
| BookMark | eNo1kNFOwjAYRmuiF4q8gTF9gWG7tlt7ZcgQMEFMQK_Jz_jHmrB26QoJL-EzO0WvTvIl51x8d-TaeYeEPHI24pyZp8m4yISWZpSyVPUTF4Jl-RUZmtxoIbhigkl9S74KcHRd-xDp_NxiOGEZfejoJNgT0ilCPAZMVras6Wy57J7pOgZ0-1ijs25Pe9JZgLamK2wDdugiROsd9dWlt7MNuq5f4EAL37TH-KNVPtA3bHw4J1hVtrS999u_JzcVHDoc_nFAPqcvH8U8WbzPXovxIgGem5ikGaRM73hqtjlKiSo1JWbbTHKQZca04lpIrsotGIGKaQZKKRDZTqCWFeRiQB4uXYuImzbYBsJ583-T-AYjpWOv |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/DAC63849.2025.11133067 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9798331503048 |
| EndPage | 7 |
| ExternalDocumentID | 11133067 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China funderid: 10.13039/501100001809 – fundername: Aeronautical Science Foundation of China funderid: 10.13039/501100004750 |
| GroupedDBID | 6IE 6IH CBEJK RIE RIO |
| ID | FETCH-LOGICAL-a179t-26a208d129b7e44e529ce6b641a4c6085183415cba93e5080a555a36d3e84fa73 |
| IEDL.DBID | RIE |
| IngestDate | Wed Oct 01 07:05:15 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a179t-26a208d129b7e44e529ce6b641a4c6085183415cba93e5080a555a36d3e84fa73 |
| PageCount | 7 |
| ParticipantIDs | ieee_primary_11133067 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-June-22 |
| PublicationDateYYYYMMDD | 2025-06-22 |
| PublicationDate_xml | – month: 06 year: 2025 text: 2025-June-22 day: 22 |
| PublicationDecade | 2020 |
| PublicationTitle | 2025 62nd ACM/IEEE Design Automation Conference (DAC) |
| PublicationTitleAbbrev | DAC |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 2.2951362 |
| Snippet | Hyperdimensional computing (HDC) based GNNs are significantly advancing the brain-like cognition in terms of mathematical rigorousness and computational... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Accuracy Cognition Design automation Distortion Feature extraction GNN graph representation hyperdimensional computing memory Memory management Training Vectors |
| Title | Can Short Hypervectors Drive Feature-Rich GNNs? Strengthening the Graph Representation of Hyperdimensional Computing for Memory-efficient GNNs |
| URI | https://ieeexplore.ieee.org/document/11133067 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxcAEiCLe8sDqNk3s2J4Qamm7EFU8pG6V7VyAJUXpQ-JP8JvxOSmIgYEpVmRfJD9yn-37viPkOrIcuNCCSZMbv0ERhlkAxfzUMsaqQuhChWQTMsvUbKanDVk9cGEAIASfQReL4S4_X7g1HpX1MC06QtwWaUkpa7JWw_rtR7o3vB342cSRfhKL7rbyr7QpwWuM9v_5vQPS-eHf0em3ZzkkO1Aekc-BKenjq4fLdOI3j9UmnLcv6bDyPyyKUG5dAUOiPB1n2fKG4oVz-YLqBt4I9U86RnVq-hCCXxvOUUkXRW0vR53_WqOD1rkesJnHtPQeo3E_GAS1Cd8u2O-Q59Hd02DCmmwKzPhFt2JxauJI5d6_Wwmcg4i1g9SmvG-4SxF5Ke_RhLNGJ-BhW2SEECZJ8wQUL4xMjkm7XJRwQmjhhFESIE0k54V12gjdj61IoBAo735KOtiZ8_daMGO-7cezP96fkz0cMozAiuML0l5Va7gku26zeltWV2GYvwAcN6yc |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagIMEEiCLeeGB1mzp24kwItbRFtFEFRepW2ckFWFKUPiT-BL8Zn5OCGBiYYkX2RfIj99m-7ztCrj0jQMhIslCn2m5QpGYGQDE7tbQ2KpNRplyyiTCO1WQSjSqyuuPCAIALPoMGFt1dfjpLlnhU1sS06AhxN8mWFIK3SrpWxftteVGzc9u280kgAYXLxrr6r8Qpzm909_75xX1S_2Hg0dG3bzkgG5Afks-2zunTqwXMtG-3j8XKnbjPaaewvyyKYG5ZAEOqPO3F8fyG4pVz_oL6BtYItU_aQ31q-ujCXyvWUU5nWWkvRaX_UqWDltkesJlFtXSI8bgfDJzehG3n7NfJc_du3O6zKp8C03bZLRgPNPdUaj28CUEIkDxKIDCBaGmRBIi9lPVpMjE68sECN09LKbUfpD4okenQPyK1fJbDMaFZIrUKAQI_FCIzSaRl1OJG-pBJFHg_IXXszOl7KZkxXffj6R_vr8hOfzwcTAf38cMZ2cXhw3gszs9JbVEs4YJsJ6vF27y4dEP-BUADr-M |
| 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=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=Can+Short+Hypervectors+Drive+Feature-Rich+GNNs%3F+Strengthening+the+Graph+Representation+of+Hyperdimensional+Computing+for+Memory-efficient+GNNs&rft.au=Wang%2C+Jihe&rft.au=Han%2C+Yuxi&rft.au=Wang%2C+Danghui&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11133067&rft.externalDocID=11133067 |