{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:21:45Z","timestamp":1757625705236,"version":"3.44.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031998560"},{"type":"electronic","value":"9783031998577"}],"license":[{"start":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:00:00Z","timestamp":1755907200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:00:00Z","timestamp":1755907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-031-99857-7_2","type":"book-chapter","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:16:40Z","timestamp":1755839800000},"page":"18-32","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DCI: An Efficient Workload-Aware Dual-Cache Allocation GNN Inference Acceleration System"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2800-6976","authenticated-orcid":false,"given":"Yi","family":"Luo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6602-9994","authenticated-orcid":false,"given":"Yaobin","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0204-6678","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8154-9053","authenticated-orcid":false,"given":"Yingchen","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6991-4314","authenticated-orcid":false,"given":"Huan","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8299-2992","authenticated-orcid":false,"given":"Qingfeng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4081-7897","authenticated-orcid":false,"given":"Jun","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,23]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"R\u00e9au, M., Renaud, N., Xue, L.C., Bonvin, A.M.J.J.: Deeprank-GNN: a graph neural network framework to learn patterns in protein\u2013protein interfaces. Bioinformatics 39(1), btac759 (2023)","DOI":"10.1093\/bioinformatics\/btac759"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Lin, Z., Li, C., Miao, Y., Liu, Y., Xu, Y.: Pagraph: scaling GNN training on large graphs via computation-aware caching. In: Proceedings of the 11th ACM Symposium on Cloud Computing, pp. 401\u2013415 (2020)","DOI":"10.1145\/3419111.3421281"},{"key":"2_CR3","first-page":"22118","volume":"33","author":"W Hu","year":"2020","unstructured":"Hu, W., et al.: Open graph benchmark: datasets for machine learning on graphs. Adv. Neural. Inf. Process. Syst. 33, 22118\u201322133 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Gnnsampler: bridging the gap between sampling algorithms of GNN and hardware. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 498\u2013514. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-26419-1_30"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Qiu, J., et al.: GCC: graph contrastive coding for graph neural network pre-training. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1150\u20131160 (2020)","DOI":"10.1145\/3394486.3403168"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Song, Y., Wang, Y., Xiong, C., Wang, T., Tang, P.: An efficient sampling-based SpMM kernel for balancing accuracy and speed in GNN inference. In: 2024 IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), pp. 468\u2013475. IEEE (2024)","DOI":"10.1109\/ISPA63168.2024.00066"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Yik, J., Kuppannagari, S.R., Zeng, H., Prasanna, V.K.: Input feature pruning for accelerating GNN inference on heterogeneous platforms. In: 2022 IEEE 29th International Conference on High Performance Computing, Data, and Analytics (HiPC), pp. 282\u2013291. IEEE (2022)","DOI":"10.1109\/HiPC56025.2022.00045"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, W., Sun, J., Sun, G.: Accelerating GNN inference by soft channel pruning. In: 2022 IEEE 13th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/PAAP56126.2022.10010603"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Wang, Y., Hooi, B., Liu, Y., Shah, N.: Graph explicit neural networks: explicitly encoding graphs for efficient and accurate inference. In: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, pp. 348\u2013356 (2023)","DOI":"10.1145\/3539597.3570388"},{"key":"2_CR10","unstructured":"Gao, X., Zhang, W., Shao, Y., Nguyen, Q.V.H., Cui, B., Yin, H.: Efficient graph neural network inference at large scale. arXiv preprint arXiv:2211.00495 (2022)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Liu, T., Li, P., Su, Z., Dong, M.: Efficient inference of graph neural networks using local sensitive hash. IEEE Trans. Sustain. Comput. 9(3) (2024)","DOI":"10.1109\/TSUSC.2024.3351282"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, L., Lai, Z., Tang, Y., Li, D., Liu, F., Luo, X.: Pcgraph: accelerating GNN inference on large graphs via partition caching. In: International Symposium on Parallel and Distributed Processing with Applications, pp. 279\u2013287 (2021)","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00048"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Min, S.W., et al.: Large graph convolutional network training with GPU-oriented data communication architecture. arXiv preprint arXiv:2103.03330 (2021)","DOI":"10.14778\/3476249.3476264"},{"key":"2_CR14","unstructured":"Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR15","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.ins.2023.03.013","volume":"632","author":"B Yu","year":"2023","unstructured":"Yu, B., Xie, H., Xu, Z.: PN-GCN: positive-negative graph convolution neural network in information system to classification. Inf. Sci. 632, 411\u2013423 (2023)","journal-title":"Inf. Sci."},{"key":"2_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102078","volume":"102","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Rasouli, S., Wong, M., Feng, T., Huang, T.: RT-GCN: Gaussian-based spatiotemporal graph convolutional network for robust traffic prediction. Inf. Fusion 102, 102078 (2024)","journal-title":"Inf. Fusion"},{"key":"2_CR17","unstructured":"Chen, J., Ma, T., Xiao, C.: FastGCN: fast learning with graph convolutional networks via importance sampling. In: International Conference on Learning Representations (2018)"},{"key":"2_CR18","unstructured":"Chen, J., Zhu, J., Song, L.: Stochastic training of graph convolutional networks with variance reduction. arXiv preprint arXiv:1710.10568 (2017)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Bulu\u00e7, A., Fineman, J.T., Frigo, M., Gilbert, J.R., Leiserson, C.E.: Parallel sparse matrix-vector and matrix-transpose-vector multiplication using compressed sparse blocks. In: Proceedings of the Twenty-First Annual Symposium on Parallelism in Algorithms and Architectures, pp. 233\u2013244 (2009)","DOI":"10.1145\/1583991.1584053"},{"key":"2_CR20","unstructured":"DGL Team. DGL: Deep Graph Library (2024). https:\/\/www.dgl.ai\/. Accessed 10 Aug 2024"},{"key":"2_CR21","unstructured":"PyTorch Team. PyTorch: Get Started with Previous Versions (2024). https:\/\/pytorch.org\/get-started\/previous-versions\/. Accessed 10 Aug 2024"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: GNNLab: a factored system for sample-based GNN training over GPUs. In: Proceedings of the Seventeenth European Conference on Computer Systems, pp. 417\u2013434 (2022)","DOI":"10.1145\/3492321.3519557"},{"key":"2_CR23","unstructured":"Zeng, H., Zhou, H., Srivastava, A., Kannan, R., Prasanna, V.: Graphsaint: graph sampling based inductive learning method. In: International Conference on Learning Representations"},{"key":"2_CR24","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"2_CR25","unstructured":"Zhu, Z., Jing, B., Wan, X., Liu, Z., Liang, L., et\u00a0al.: Glisp: a scalable GNN learning system by exploiting inherent structural properties of graphs. arXiv preprint arXiv:2401.03114 (2024)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2025: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-99857-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T19:08:45Z","timestamp":1757444925000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-99857-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,23]]},"ISBN":["9783031998560","9783031998577"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-99857-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,23]]},"assertion":[{"value":"23 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dresden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}