DS-GL: Advancing Graph Learning via Harnessing Nature's Power within Scalable Dynamical Systems
With the rapid digitization of the world, an increasing number of real-world applications are turning to non-Euclidean data, modeled as graphs. Due to their intrinsic high complexity and irregularity, learning from graph data demands tremendous computational power. Recently, CMOS-compatible Ising ma...
Uloženo v:
| Vydáno v: | 2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) s. 45 - 57 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
29.06.2024
|
| Témata: | |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | With the rapid digitization of the world, an increasing number of real-world applications are turning to non-Euclidean data, modeled as graphs. Due to their intrinsic high complexity and irregularity, learning from graph data demands tremendous computational power. Recently, CMOS-compatible Ising machines, i.e., dynamical systems fabricated with CMOS technologies, have emerged as a new approach that harnesses the inherent power of nature within dynamical systems to efficiently resolve binary optimization problems and have been adopted for traditional graph computation, such as max-cut. However, when performing complex Graph Learning (GL) tasks, Ising machines face significant hurdles: (i) they are binary and thus ill-suited for real-valued problems; (ii) their expensive all-to-all coupling network that guarantees generality for optimization problems poses daunting scalability concerns.To address these challenges, this paper proposes a nature-powered graph learning framework dubbed DS-GL, which is the first effort to transform the process of solving graph learning problems into the natural annealing process within a parameterized dynamical system embodied as a CMOS chip. To tackle the two major hurdles, DS-GL first augments the Ising machine architecture to modify the self-reaction term of its Hamiltonian function from linear to quadratic, effectively serving as an energy regulator. This adjustment maintains the system's original physical interpretation while enabling it to process continuous, real-valued data. Second, to address the scaling issue, DS-GL further upgrades the real-valued dense Ising machine by decomposing it into a mesh-based multi-PE dynamical system that supports efficient distributed spatial-temporal co-annealing across different PEs through sparse interconnects. By exploiting the inherent sparsity and community structures in real-world graphs, DS-GL is able to map complex graph learning tasks onto the scalable dynamical system while maintaining high accuracy. Evaluations with four diverse GL applications across seven real-world datasets, including traffic flow and COVID-19 prediction, show that DS-GL can deliver from 10 3 × to 10 5 × speedups over Graph Neural Networks on GPUs while operating at a power 2 orders of magnitude lower than GPUs, with 5% - 30% accuracy enhancement. |
|---|---|
| AbstractList | With the rapid digitization of the world, an increasing number of real-world applications are turning to non-Euclidean data, modeled as graphs. Due to their intrinsic high complexity and irregularity, learning from graph data demands tremendous computational power. Recently, CMOS-compatible Ising machines, i.e., dynamical systems fabricated with CMOS technologies, have emerged as a new approach that harnesses the inherent power of nature within dynamical systems to efficiently resolve binary optimization problems and have been adopted for traditional graph computation, such as max-cut. However, when performing complex Graph Learning (GL) tasks, Ising machines face significant hurdles: (i) they are binary and thus ill-suited for real-valued problems; (ii) their expensive all-to-all coupling network that guarantees generality for optimization problems poses daunting scalability concerns.To address these challenges, this paper proposes a nature-powered graph learning framework dubbed DS-GL, which is the first effort to transform the process of solving graph learning problems into the natural annealing process within a parameterized dynamical system embodied as a CMOS chip. To tackle the two major hurdles, DS-GL first augments the Ising machine architecture to modify the self-reaction term of its Hamiltonian function from linear to quadratic, effectively serving as an energy regulator. This adjustment maintains the system's original physical interpretation while enabling it to process continuous, real-valued data. Second, to address the scaling issue, DS-GL further upgrades the real-valued dense Ising machine by decomposing it into a mesh-based multi-PE dynamical system that supports efficient distributed spatial-temporal co-annealing across different PEs through sparse interconnects. By exploiting the inherent sparsity and community structures in real-world graphs, DS-GL is able to map complex graph learning tasks onto the scalable dynamical system while maintaining high accuracy. Evaluations with four diverse GL applications across seven real-world datasets, including traffic flow and COVID-19 prediction, show that DS-GL can deliver from 10 3 × to 10 5 × speedups over Graph Neural Networks on GPUs while operating at a power 2 orders of magnitude lower than GPUs, with 5% - 30% accuracy enhancement. |
| Author | Wu, Chunshu Song, Ruibing Huang, Michael Li, Ang Geng, Tony Tong Liu, Chuan |
| Author_xml | – sequence: 1 givenname: Ruibing surname: Song fullname: Song, Ruibing email: ruibing.song@rochester.edu organization: University of Rochester,Rochester,NY,USA – sequence: 2 givenname: Chunshu surname: Wu fullname: Wu, Chunshu email: chunshu.wu@rochester.edu organization: University of Rochester,Rochester,NY,USA – sequence: 3 givenname: Chuan surname: Liu fullname: Liu, Chuan email: chuan.liu@rochester.edu organization: University of Rochester,Rochester,NY,USA – sequence: 4 givenname: Ang surname: Li fullname: Li, Ang email: ang.li@pnnl.gov organization: Pacific Northwest National Laboratory,Richland,WA,USA – sequence: 5 givenname: Michael surname: Huang fullname: Huang, Michael email: michael.huang@rochester.edu organization: University of Rochester,Rochester,NY,USA – sequence: 6 givenname: Tony Tong surname: Geng fullname: Geng, Tony Tong email: tong.geng@rochester.edu organization: University of Rochester,Rochester,NY,USA |
| BookMark | eNotj8FOwzAQRI0EElDyBz34xillHcd2zC1Koa0UAVLgXG2cLbXUulUSWuXvSQWnmXd4I809uw6HQIxNBcyEAPu0qopcWTBmlkCSzgBApFcsssZmUoFMtMrELYu6ztegwRppMnXH1vMqXpTPPG9OGJwP33zR4nHLS8I2XPDkkS_HTqM44hv2Py09dvzjcKaWn32_9YFXDndY74jPh4B7PxKvhq6nfffAbja46yj6zwn7en35LJZx-b5YFXkZY6KyPpa1JZcIAEpVglZrXTfCuQ2A2jglldW1gsZlqRWZkk2jUyNQpw51bVwDWk7Y9G_XE9H62Po9tsNaXJ5qo-Uvu51VEw |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/ISCA59077.2024.00014 |
| 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 | 9798350326581 |
| EndPage | 57 |
| ExternalDocumentID | 10609676 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Office of Science funderid: 10.13039/100006132 – fundername: Advanced Scientific Computing Research funderid: 10.13039/100006192 |
| GroupedDBID | 6IE 6IH ACM ALMA_UNASSIGNED_HOLDINGS CBEJK RIE RIO |
| ID | FETCH-LOGICAL-a258t-3b9ec2100e452a9666bd1ccf005fc53596b50dc8491853dd6471a64ca6b7cd063 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001290320700004&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 02:34:55 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a258t-3b9ec2100e452a9666bd1ccf005fc53596b50dc8491853dd6471a64ca6b7cd063 |
| PageCount | 13 |
| ParticipantIDs | ieee_primary_10609676 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-June-29 |
| PublicationDateYYYYMMDD | 2024-06-29 |
| PublicationDate_xml | – month: 06 year: 2024 text: 2024-June-29 day: 29 |
| PublicationDecade | 2020 |
| PublicationTitle | 2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) |
| PublicationTitleAbbrev | ISCA |
| PublicationYear | 2024 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssib060973785 |
| Score | 2.2813096 |
| Snippet | With the rapid digitization of the world, an increasing number of real-world applications are turning to non-Euclidean data, modeled as graphs. Due to their... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 45 |
| SubjectTerms | Accuracy Computational efficiency Computer architecture Dynamical System Graph Learning Graph neural networks Nature-Powered Computing Semiconductor device modeling Transforms Turning |
| Title | DS-GL: Advancing Graph Learning via Harnessing Nature's Power within Scalable Dynamical Systems |
| URI | https://ieeexplore.ieee.org/document/10609676 |
| WOSCitedRecordID | wos001290320700004&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/eLvHCXMwlV1NSwMxEA22ePCkYsVvchA8RbO7-dh4k9a2QimFKvRWsklWCrKVfv1-Z9KtevHgLZvLQibhzSTz3iPkFjC_zIN3TOqSM4E5nLVJxoxA7W-eWeUiUXigh8N8MjGjmqweuTAhhNh8Fu5xGN_y_dyt8aoMTriCjFurBmlorbdkrd3mUag7o3NZ0-MSbh5exu0nCcWfhjIwRZFsjlydXyYqEUO6h__8-xFp_bDx6OgbZ47JXqhOyLQzZr3BI42uyA7maQ-lp2mtl_pONzNL-zDGNlf4HEYBz7slHaEtGsXr11lFxxAh5E7RztaY3n7QWsK8Rd66z6_tPqvNEphNZb5iWWGCg_qNByFTC0WMKnziXAmnrHQyk0YVknuXC4MI7b0CVLJKOKsK7TwkKqekWc2rcEaohJTFc4vaeUrwkBrhTdSRh2xIF0lxTlq4OtPPrR7GdLcwF3_MX5IDDAA2WKXmijRXi3W4Jvtus5otFzcxil9QLZxA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBT2pWPFtDoKn1X0k2Y03ae0D16XQCr0t2SQrBdlKX7_fmXSrXjx4y-aykEn4ZpL5vo-QW8D8MrFGezwufY9hDqdUEHmSofa3HymhHVE4jbMsGY_loCarOy6MtdY1n9l7HLq3fDPVS7wqgxMuIOOOxTbZ4YyFwZqutdk-ApVn4oTXBLnAlw_9YeuJQ_kXQyEYoky2j2ydXzYqDkU6B__8_yFp_vDx6OAbaY7Ilq2OSd4eet30kTpfZA3ztIvi07RWTH2nq4miPRhjoyt8Zk7C825OB2iMRvECdlLRIcQI2VO0vbamVx-0FjFvkrfO86jV82q7BE-FPFl4USGthgrOt4yHCsoYUZhA6xLOWal5xKUouG90wiRitDECcEkJppUoYm0gVTkhjWpa2VNCOSQtxleonieYb0PJjHRK8pAPxUVQnJEmrk7-uVbEyDcLc_7H_A3Z641e0zztZy8XZB-Dge1WobwkjcVsaa_Irl4tJvPZtYvoF6Hzn4c |
| 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=2024+ACM%2FIEEE+51st+Annual+International+Symposium+on+Computer+Architecture+%28ISCA%29&rft.atitle=DS-GL%3A+Advancing+Graph+Learning+via+Harnessing+Nature%27s+Power+within+Scalable+Dynamical+Systems&rft.au=Song%2C+Ruibing&rft.au=Wu%2C+Chunshu&rft.au=Liu%2C+Chuan&rft.au=Li%2C+Ang&rft.date=2024-06-29&rft.pub=IEEE&rft.spage=45&rft.epage=57&rft_id=info:doi/10.1109%2FISCA59077.2024.00014&rft.externalDocID=10609676 |