{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:15:14Z","timestamp":1778948114782,"version":"3.51.4"},"reference-count":120,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Hyperdimensional Computing (HDC), also known as Vector Symbolic Architectures (VSA), is a neuro-inspired computing framework that exploits high-dimensional random vector spaces. HDC uses extremely parallelizable arithmetic to provide computational solutions that balance accuracy, efficiency and robustness. The majority of current HDC research focuses on the learning capabilities of these high-dimensional spaces. However, a tangential research direction investigates the properties of these high-dimensional spaces more generally as a probabilistic model for computation. In this manuscript, we provide an approachable, yet thorough, survey of the components of HDC. To highlight the dual use of HDC, we provide an in-depth analysis of two vastly different applications. The first uses HDC in a learning setting to classify graphs. Graphs are among the most important forms of information representation, and graph learning in IoT and sensor networks introduces challenges because of the limited compute capabilities. Compared to the state-of-the-art Graph Neural Networks, our proposed method achieves comparable accuracy, while training and inference times are on average 14.6\u00d7 and 2.0\u00d7 faster, respectively. Secondly, we analyse a dynamic hash table that uses a novel hypervector type called circular-hypervectors to map requests to a dynamic set of resources. The proposed hyperdimensional hashing method has the efficiency to be deployed in large systems. Moreover, our approach remains unaffected by a realistic level of memory errors which causes significant mismatches for existing methods.<\/jats:p>","DOI":"10.1186\/s40537-024-01010-8","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T15:03:34Z","timestamp":1729782214000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Hyperdimensional computing: a framework for stochastic computation and symbolic AI"],"prefix":"10.1186","volume":"11","author":[{"given":"Mike","family":"Heddes","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Nunes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tony","family":"Givargis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandru","family":"Nicolau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Veidenbaum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,24]]},"reference":[{"key":"1010_CR1","doi-asserted-by":"crossref","unstructured":"Abusnaina A, Khormali A, Alasmary H, Park J, Anwar A, Mohaisen A. Adversarial learning attacks on graph-based IoT malware detection systems. In: 2019 IEEE 39th international conference on distributed computing systems (ICDCS). IEEE; 2019. p. 1296\u2013305.","DOI":"10.1109\/ICDCS.2019.00130"},{"key":"1010_CR2","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1109\/TBME.2016.2647680","volume":"64","author":"N Ahmidi","year":"2017","unstructured":"Ahmidi N, Tao L, et al. A dataset and benchmarks for segmentation and recognition of gestures in robotic surgery. Trans Biomed Eng. 2017;64:2025\u201341.","journal-title":"Trans Biomed Eng"},{"key":"1010_CR3","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1109\/TSC.2017.2711009","volume":"11","author":"Y Al-Dhuraibi","year":"2017","unstructured":"Al-Dhuraibi Y, Paraiso F, Djarallah N, Merle P. Elasticity in cloud computing: state of the art and research challenges. IEEE Trans Serv Comput. 2017;11:430\u201347.","journal-title":"IEEE Trans Serv Comput"},{"key":"1010_CR4","doi-asserted-by":"crossref","unstructured":"Alonso P, Shridhar K, Kleyko D, Osipov E, Liwicki M. Hyperembed: tradeoffs between resources and performance in NLP tasks with hyperdimensional computing enabled embedding of n-gram statistics. In: 2021 international joint conference on neural networks (IJCNN). 2021; IEEE. p. 1\u20139.","DOI":"10.1109\/IJCNN52387.2021.9534359"},{"key":"1010_CR5","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"AB Arrieta","year":"2020","unstructured":"Arrieta AB, D\u00edaz-Rodr\u00edguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, Garc\u00eda S, Gil-L\u00f3pez S, Molina D, Benjamins R, et al. Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf Fusion. 2020;58:82\u2013115.","journal-title":"Inf Fusion"},{"key":"1010_CR6","doi-asserted-by":"publisher","first-page":"i47","DOI":"10.1093\/bioinformatics\/bti1007","volume":"21","author":"KM Borgwardt","year":"2005","unstructured":"Borgwardt KM, Ong CS, Sch\u00f6nauer S, Vishwanathan S, Smola AJ, Kriegel HP. Protein function prediction via graph kernels. Bioinformatics. 2005;21:i47\u201356.","journal-title":"Bioinformatics"},{"key":"1010_CR7","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.3390\/electronics8111289","volume":"8","author":"S Branco","year":"2019","unstructured":"Branco S, Ferreira AG, Cabral J. Machine learning in resource-scarce embedded systems, FPGAs, and end-devices: a survey. Electronics. 2019;8:1289.","journal-title":"Electronics"},{"key":"1010_CR8","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/S0169-7552(98)00110-X","volume":"30","author":"S Brin","year":"1998","unstructured":"Brin S, Page L. The anatomy of a large-scale hypertextual web search engine. Comput Netw ISDN Syst. 1998;30:107\u201317.","journal-title":"Comput Netw ISDN Syst"},{"key":"1010_CR9","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1214\/08-AOAS190","volume":"3","author":"P Cabella","year":"2009","unstructured":"Cabella P, Marinucci D. Statistical challenges in the analysis of cosmic microwave background radiation. Ann Appl Stat. 2009;3:61\u201395.","journal-title":"Ann Appl Stat"},{"key":"1010_CR10","first-page":"1","volume":"53","author":"Y Chen","year":"2020","unstructured":"Chen Y, Zheng B, Zhang Z, Wang Q, Shen C, Zhang Q. Deep learning on mobile and embedded devices: state-of-the-art, challenges, and future directions. ACM Comput Surv. 2020;53:1\u201337.","journal-title":"ACM Comput Surv"},{"key":"1010_CR11","doi-asserted-by":"publisher","DOI":"10.1201\/9781420041767","volume-title":"Engineering applications of noncommutative harmonic analysis: with emphasis on rotation and motion groups","author":"GS Chirikjian","year":"2000","unstructured":"Chirikjian GS. Engineering applications of noncommutative harmonic analysis: with emphasis on rotation and motion groups. Boca Raton: CRC Press; 2000."},{"key":"1010_CR12","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1126\/science.aam9868","volume":"358","author":"S Dasgupta","year":"2017","unstructured":"Dasgupta S, Stevens CF, Navlakha S. A neural algorithm for a fundamental computing problem. Science. 2017;358:793\u20136.","journal-title":"Science"},{"key":"1010_CR13","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1021\/jm00106a046","volume":"34","author":"AK Debnath","year":"1991","unstructured":"Debnath AK, Lopez de Compadre RL, Debnath G, Shusterman AJ, Hansch C. Structure\u2013activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. J Med Chem. 1991;34:786\u201397.","journal-title":"J Med Chem"},{"key":"1010_CR14","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1145\/1323293.1294281","volume":"41","author":"G DeCandia","year":"2007","unstructured":"DeCandia G, Hastorun D, Jampani M, Kakulapati G, Lakshman A, Pilchin A, Sivasubramanian S, Vosshall P, Vogels W. Dynamo: Amazon\u2019s highly available key-value store. ACM SIGOPS Oper Syst Rev. 2007;41:205\u201320.","journal-title":"ACM SIGOPS Oper Syst Rev"},{"key":"1010_CR15","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1016\/S0022-2836(03)00628-4","volume":"330","author":"PD Dobson","year":"2003","unstructured":"Dobson PD, Doig AJ. Distinguishing enzyme structures from non-enzymes without alignments. J Mol Biol. 2003;330:771\u201383.","journal-title":"J Mol Biol"},{"key":"1010_CR16","unstructured":"Eisenbud DE, Yi C, Contavalli C, Smith C, Kononov R, Mann-Hielscher E, Cilingiroglu A, Cheyney B, Shang W, Hosein JD. Maglev: a fast and reliable software network load balancer. In: 13th {USENIX} symposium on networked systems design and implementation ({NSDI} 16; 2016. p. 523\u201335."},{"issue":"17","key":"1010_CR17","doi-asserted-by":"publisher","first-page":"13652","DOI":"10.1109\/JIOT.2021.3067717","volume":"8","author":"P Ferrer-Cid","year":"2021","unstructured":"Ferrer-Cid P, Barcelo-Ordinas JM, Garcia-Vidal J. Graph learning techniques using structured data for IoT air pollution monitoring platforms. IEEE Internet Things J. 2021;8(17):13652\u201363.","journal-title":"IEEE Internet Things J"},{"key":"1010_CR18","doi-asserted-by":"crossref","unstructured":"Frady EP, Kleyko D, Kymn CJ, Olshausen BA, Sommer FT. Computing on functions using randomized vector representations. arXiv preprint. 2021. arXiv:2109.03429 .","DOI":"10.1145\/3517343.3522597"},{"key":"1010_CR19","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1002\/sim.2463","volume":"25","author":"F Gao","year":"2006","unstructured":"Gao F, Chia KS, Krantz I, Nordin P, Machin D. On the application of the von Mises distribution and angular regression methods to investigate the seasonality of disease onset. Stat Med. 2006;25:1593\u2013618.","journal-title":"Stat Med"},{"key":"1010_CR20","unstructured":"Gao Y, et al. Jhu-isi gesture and skill assessment working set (jigsaws): a surgical activity dataset for human motion modeling. In: MICCAI workshop: M2cai; 2014. p. 3."},{"key":"1010_CR21","unstructured":"Gayler R. Multiplicative binding, representation operators and analogy. In: Advances in analogy research. 1998. p. 1\u20134."},{"key":"1010_CR22","unstructured":"Gayler RW. Vector symbolic architectures answer Jackendoff\u2019s challenges for cognitive neuroscience. arXiv preprint. 2004. cs\/0412059."},{"key":"1010_CR23","unstructured":"Gayler RW, Levy SD. A distributed basis for analogical mapping. In: New frontiers in analogy research; 2009."},{"key":"1010_CR24","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MCAS.2020.2988388","volume":"20","author":"L Ge","year":"2020","unstructured":"Ge L, Parhi KK. Classification using hyperdimensional computing: a review. Circ Syst Mag. 2020;20:30\u201347.","journal-title":"Circ Syst Mag"},{"key":"1010_CR25","doi-asserted-by":"crossref","unstructured":"Ge L, Parhi KK. Seizure detection using power spectral density via hyperdimensional computing. In: ICASSP 2021\u20132021 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE; 2021. p. 7858\u201362.","DOI":"10.1109\/ICASSP39728.2021.9414083"},{"key":"1010_CR26","unstructured":"van Gelder T. Distributed vs. local representation. In: MIT encyclopedia of the cognitive sciences. 1999. p. 235\u20137."},{"key":"1010_CR27","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1214\/aoms\/1177706098","volume":"30","author":"EN Gilbert","year":"1959","unstructured":"Gilbert EN. Random graphs. Ann Math Stat. 1959;30:1141\u20134.","journal-title":"Ann Math Stat"},{"key":"1010_CR28","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1137\/140976649","volume":"57","author":"DF Gleich","year":"2015","unstructured":"Gleich DF. Pagerank beyond the web. SIAM Rev. 2015;57:321\u201363.","journal-title":"SIAM Rev"},{"key":"1010_CR29","doi-asserted-by":"crossref","unstructured":"Gori M, Monfardini G, Scarselli F. A new model for learning in graph domains. In: International joint conference on neural networks (IJCNN). 2005; IEEE. p. 729\u201334.","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"1010_CR30","volume-title":"A guide to chi-squared testing","author":"PE Greenwood","year":"1996","unstructured":"Greenwood PE, Nikulin MS. A guide to chi-squared testing, vol. 280. New York: Wiley; 1996."},{"key":"1010_CR31","doi-asserted-by":"publisher","first-page":"97651","DOI":"10.1109\/ACCESS.2021.3059762","volume":"10","author":"E Hassan","year":"2021","unstructured":"Hassan E, Halawani Y, Mohammad B, Saleh H. Hyper-dimensional computing challenges and opportunities for AI applications. IEEE Access. 2021;10:97651\u201364.","journal-title":"IEEE Access"},{"key":"1010_CR32","doi-asserted-by":"crossref","unstructured":"Heddes M, Nunes I, Givargis T, Nicolau A, Veidenbaum A. Hyperdimensional hashing: a robust and efficient dynamic hash table. In: Design automation conference (DAC). 2022.","DOI":"10.1145\/3489517.3530553"},{"key":"1010_CR33","first-page":"1","volume":"24","author":"M Heddes","year":"2023","unstructured":"Heddes M, Nunes I, Verg\u00e9s P, Kleyko D, Abraham D, Givargis T, Nicolau A, Veidenbaum A. Torchhd: an open source python library to support research on hyperdimensional computing and vector symbolic architectures. J Mach Learn Res. 2023;24:1\u201310.","journal-title":"J Mach Learn Res"},{"key":"1010_CR34","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1093\/bioinformatics\/17.1.107","volume":"17","author":"C Helma","year":"2001","unstructured":"Helma C, King RD, Kramer S, Srinivasan A. The predictive toxicology challenge 2000\u20132001. Bioinformatics. 2001;17:107\u20138.","journal-title":"Bioinformatics"},{"key":"1010_CR35","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez-Cano A, Zhuo C, Yin X, Imani M. Reghd: robust and efficient regression in hyper-dimensional learning system. In: Design automation conference (DAC). IEEE; 2021. p. 7\u201312.","DOI":"10.1109\/DAC18074.2021.9586284"},{"key":"1010_CR36","unstructured":"Hinton GE. Distributed representations. 1984."},{"key":"1010_CR37","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/s10651-006-0015-7","volume":"13","author":"H Holzmann","year":"2006","unstructured":"Holzmann H, Munk A, Suster M, Zucchini W. Hidden Markov models for circular and linear-circular time series. Environ Ecol Stat. 2006;13:325\u201347.","journal-title":"Environ Ecol Stat"},{"key":"1010_CR38","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1145\/2248487.2150989","volume":"47","author":"AA Hwang","year":"2012","unstructured":"Hwang AA, Stefanovici IA, Schroeder B. Cosmic rays don\u2019t strike twice: understanding the nature of dram errors and the implications for system design. ACM SIGPLAN Not. 2012;47:111\u201322.","journal-title":"ACM SIGPLAN Not"},{"key":"1010_CR39","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1109\/TED.2010.2047907","volume":"57","author":"E Ibe","year":"2010","unstructured":"Ibe E, Taniguchi H, Yahagi Y, Shimbo KI, Toba T. Impact of scaling on neutron-induced soft error in SRAMs from a 250 nm to a 22 nm design rule. IEEE Trans Electron Devices. 2010;57:1527\u201338.","journal-title":"IEEE Trans Electron Devices"},{"key":"1010_CR40","doi-asserted-by":"crossref","unstructured":"Imani M, Gupta S, Rosing T. Ultra-efficient processing in-memory for data intensive applications. In: Design automation conference (DAC). IEEE; 2017. p. 1\u20136.","DOI":"10.1145\/3061639.3062337"},{"key":"1010_CR41","doi-asserted-by":"crossref","unstructured":"Imani M, Kong D, Rahimi A, Rosing T. Voicehd: hyperdimensional computing for efficient speech recognition. In: International conference on rebooting computing (ICRC). IEEE; 2017. p. 1\u20138.","DOI":"10.1109\/ICRC.2017.8123666"},{"key":"1010_CR42","doi-asserted-by":"crossref","unstructured":"Imani M, Nassar T, Rahimi A, Rosing T. Hdna: energy-efficient dna sequencing using hyperdimensional computing. In: 2018 IEEE EMBS international conference on biomedical & health informatics (BHI). IEEE; 2018. p. 271\u20134.","DOI":"10.1109\/BHI.2018.8333421"},{"key":"1010_CR43","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/abf151","volume":"1","author":"H Jaeger","year":"2021","unstructured":"Jaeger H. Towards a generalized theory comprising digital, neuromorphic and unconventional computing. Neuromorphic Comput Eng. 2021;1: 012002.","journal-title":"Neuromorphic Comput Eng"},{"key":"1010_CR44","doi-asserted-by":"crossref","unstructured":"Joshi A, Halseth JT, Kanerva P. Language geometry using random indexing. In: International symposium on quantum interaction (QI). Springer; 2016. p. 265\u201374.","DOI":"10.1007\/978-3-319-52289-0_21"},{"key":"1010_CR45","volume-title":"Sparse distributed memory","author":"P Kanerva","year":"1988","unstructured":"Kanerva P. Sparse distributed memory. London: MIT press; 1988."},{"key":"1010_CR46","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s12559-009-9009-8","volume":"1","author":"P Kanerva","year":"2009","unstructured":"Kanerva P. Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors. Cogn Comput. 2009;1:139\u201359.","journal-title":"Cogn Comput"},{"key":"1010_CR47","unstructured":"Kanerva P. What we mean when we say what\u2019s the dollar of Mexico?: prototypes and mapping in concept space. In: AAAI fall symposium series; 2010."},{"key":"1010_CR48","first-page":"10000","volume":"1","author":"P Kanerva","year":"1997","unstructured":"Kanerva P, et al. Fully distributed representation. PAT. 1997;1:10000.","journal-title":"PAT"},{"key":"1010_CR49","doi-asserted-by":"crossref","unstructured":"Kang U, Tong H, Sun J. Fast random walk graph kernel. In: SIAM international conference on data mining, SIAM; 2012. p. 828\u201338.","DOI":"10.1137\/1.9781611972825.71"},{"key":"1010_CR50","doi-asserted-by":"crossref","unstructured":"Karger D, Lehman E, Leighton T, Panigrahy R, Levine M, Lewin D. Consistent hashing and random trees: distributed caching protocols for relieving hot spots on the world wide web. In: Proceedings of the twenty-ninth annual ACM symposium on theory of computing. 1997. p. 654\u201363.","DOI":"10.1145\/258533.258660"},{"key":"1010_CR51","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1038\/s41928-020-0410-3","volume":"3","author":"G Karunaratne","year":"2020","unstructured":"Karunaratne G, Le Gallo M, Cherubini G, Benini L, Rahimi A, Sebastian A. In-memory hyperdimensional computing. Nat Electron. 2020;3:327\u201337.","journal-title":"Nat Electron"},{"key":"1010_CR52","first-page":"1493","volume":"7","author":"SS Keerthi","year":"2006","unstructured":"Keerthi SS, Chapelle O, DeCoste D, Bennett KP, Parrado-Hern\u00e1ndez E. Building support vector machines with reduced classifier complexity. J Mach Learn Res. 2006;7:1493\u2013515.","journal-title":"J Mach Learn Res"},{"key":"1010_CR53","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.jneumeth.2012.03.007","volume":"207","author":"R Kempter","year":"2012","unstructured":"Kempter R, Leibold C, et al. Quantifying circular-linear associations: hippocampal phase precession. J Neurosci Methods. 2012;207:113\u201324.","journal-title":"J Neurosci Methods"},{"key":"1010_CR54","doi-asserted-by":"crossref","unstructured":"Khan R, Khan SU, Zaheer R, Khan S. Future internet: the internet of things architecture, possible applications and key challenges. In: International conference on frontiers of information technology (FIT). IEEE; 2012. p. 257\u201360.","DOI":"10.1109\/FIT.2012.53"},{"key":"1010_CR55","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1109\/JPROC.2022.3209104","volume":"110","author":"D Kleyko","year":"2022","unstructured":"Kleyko D, Davies M, Frady EP, Kanerva P, Kent SJ, Olshausen BA, Osipov E, Rabaey JM, Rachkovskij DA, Rahimi A, et al. Vector symbolic architectures as a computing framework for emerging hardware. Proc IEEE. 2022;110:1538\u201371.","journal-title":"Proc IEEE"},{"key":"1010_CR56","doi-asserted-by":"crossref","unstructured":"Kleyko D, Rachkovskij DA, Osipov E, Rahim A. A survey on hyperdimensional computing aka vector symbolic architectures, part II: applications, cognitive models, and challenges. arXiv preprint. 2021. arXiv:2112.15424 .","DOI":"10.1145\/3538531"},{"key":"1010_CR57","doi-asserted-by":"crossref","unstructured":"Kleyko D, Rachkovskij DA, Osipov E, Rahimi A. A survey on hyperdimensional computing aka vector symbolic architectures, part I: models and data transformations. arXiv preprint. 2021. arXiv:2111.06077 .","DOI":"10.1145\/3538531"},{"key":"1010_CR58","doi-asserted-by":"publisher","first-page":"3675","DOI":"10.1007\/s00521-019-04397-1","volume":"32","author":"D Kleyko","year":"2020","unstructured":"Kleyko D, Rahimi A, Gayler RW, Osipov E. Autoscaling bloom filter: controlling trade-off between true and false positives. Neural Comput Appl. 2020;32:3675\u201384.","journal-title":"Neural Comput Appl"},{"key":"1010_CR59","unstructured":"Kondor R, Pan H. The multiscale Laplacian graph kernel. In: Advances in neural information processing systems (NIPS). 2016. p. 2982\u201390."},{"key":"1010_CR60","unstructured":"Kriege NM, Giscard PL, Wilson RC. On valid optimal assignment kernels and applications to graph classification. In: Advances in neural information processing systems (NIPS). 2016. p. 1615\u201323."},{"key":"1010_CR61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41109-019-0195-3","volume":"5","author":"NM Kriege","year":"2020","unstructured":"Kriege NM, Johansson FD, Morris C. A survey on graph kernels. Appl Netw Sci. 2020;5:1\u201342.","journal-title":"Appl Netw Sci"},{"key":"1010_CR62","doi-asserted-by":"publisher","first-page":"1566","DOI":"10.1109\/TNN.2006.880676","volume":"17","author":"EM Kussul","year":"2006","unstructured":"Kussul EM, Baidyk TN, Wunsch DC II, Makeyev O, Martin A. Permutation coding technique for image recognition systems. IEEE Trans Neural Netw. 2006;17:1566\u201379.","journal-title":"IEEE Trans Neural Netw"},{"key":"1010_CR63","doi-asserted-by":"publisher","unstructured":"Lai L, Suda N. Enabling deep learning at the IoT edge. In: Proceedings of the international conference on computer-aided design. New York: ACM; 2018. p. 1\u20136. https:\/\/doi.org\/10.1145\/3240765.3243473.","DOI":"10.1145\/3240765.3243473."},{"key":"1010_CR64","volume-title":"The concentration of measure phenomenon","author":"M Ledoux","year":"2001","unstructured":"Ledoux M. The concentration of measure phenomenon, vol. 89. Rhode Island: American Mathematical Soc; 2001."},{"key":"1010_CR65","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1002\/wics.98","volume":"2","author":"A Lee","year":"2010","unstructured":"Lee A. Circular data. Wiley Interdiscip Rev Comput Stat. 2010;2:477\u201386.","journal-title":"Wiley Interdiscip Rev Comput Stat"},{"key":"1010_CR66","doi-asserted-by":"crossref","unstructured":"Li H, Wu TF, Rahimi A, Li KS, Rusch M, Lin CH, Hsu JL, Sabry MM, Eryilmaz SB, Sohn J, et al. Hyperdimensional computing with 3D VRRAM in-memory kernels: device-architecture co-design for energy-efficient, error-resilient language recognition. In: International electron devices meeting (IEDM). IEEE; 2016. p. 16\u20131.","DOI":"10.1109\/IEDM.2016.7838428"},{"key":"1010_CR67","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1080\/02664769922160","volume":"26","author":"U Lund","year":"1999","unstructured":"Lund U. Least circular distance regression for directional data. J Appl Stat. 1999;26:723\u201333.","journal-title":"J Appl Stat"},{"key":"1010_CR68","doi-asserted-by":"crossref","unstructured":"Manabat AX, Marcelo CR, Quinquito AL, Alvarez A. Performance analysis of hyperdimensional computing for character recognition. In: International symposium on multimedia and communication technology (ISMAC). IEEE; 2019. p. 1\u20135.","DOI":"10.1109\/ISMAC.2019.8836136"},{"key":"1010_CR69","volume-title":"Directional statistics","author":"KV Mardia","year":"2000","unstructured":"Mardia KV, Jupp PE, Mardia K. Directional statistics, vol. 2. London: Wiley Online Library; 2000."},{"key":"1010_CR70","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511751677","volume-title":"Random fields on the sphere: representation, limit theorems and cosmological applications","author":"D Marinucci","year":"2011","unstructured":"Marinucci D, Peccati G. Random fields on the sphere: representation, limit theorems and cosmological applications, vol. 389. Cambridge: Cambridge University Press; 2011."},{"key":"1010_CR71","doi-asserted-by":"crossref","unstructured":"Mirrokni V, Thorup M, Zadimoghaddam M. Consistent hashing with bounded loads. In: Proceedings of the twenty-ninth annual ACM-SIAM symposium on discrete algorithms. SIAM; 2018. p. 587\u2013604.","DOI":"10.1137\/1.9781611975031.39"},{"key":"1010_CR72","unstructured":"Morris C, Kriege NM, Bause F, Kersting K, Mutzel P, Neumann M. Tudataset: a collection of benchmark datasets for learning with graphs. In: ICML workshop on graph representation learning and beyond (GR+). 2020."},{"key":"1010_CR73","unstructured":"Najafabadi FR, Rahimi A, Kanerva P, Rabaey JM. Hyperdimensional computing for text classification. In: Design, automation test in Europe conference exhibition (DATE). 2016. p. 1\u20131."},{"key":"1010_CR74","doi-asserted-by":"crossref","unstructured":"Neubert P, Protzel P. Towards hypervector representations for learning and planning with schemas. In: Joint German\/Austrian conference on artificial intelligence (K\u00fcnstliche Intelligenz). Springer; 2018. p. 182\u20139.","DOI":"10.1007\/978-3-030-00111-7_16"},{"key":"1010_CR75","unstructured":"Neumann M, Moreno P, Antanas L, Garnett R, Kersting K. Graph kernels for object category prediction in task-dependent robot grasping. In: KDD workshop on mining and learning with graphs (MGL). 2013. p. 0\u20136."},{"key":"1010_CR76","doi-asserted-by":"crossref","unstructured":"Nikolentzos G, Meladianos P, Vazirgiannis M. Matching node embeddings for graph similarity. In: Thirty-first AAAI conference on artificial intelligence. 2017.","DOI":"10.1609\/aaai.v31i1.10839"},{"key":"1010_CR77","doi-asserted-by":"crossref","unstructured":"Nunes I, Heddes M, Givargis T, Nicolau A. An extension to basis-hypervectors for learning from circular data in hyperdimensional computing. In: 2023 60th ACM\/IEEE design automation conference (DAC). IEEE; 2023. p. 1\u20136.","DOI":"10.1109\/DAC56929.2023.10247736"},{"key":"1010_CR78","doi-asserted-by":"crossref","unstructured":"Nunes I, Heddes M, Givargis T, Nicolau A, Veidenbaum A. Graphhd: efficient graph classification using hyperdimensional computing. In: Design, automation & test in Europe conference & exhibition (DATE). 2022.","DOI":"10.23919\/DATE54114.2022.9774533"},{"key":"1010_CR79","doi-asserted-by":"crossref","unstructured":"Nunes I, Heddes M, Verg\u00e9s P, Abraham D, Veidenbaum A, Nicolau A, Givargis T. Dothash: estimating set similarity metrics for link prediction and document deduplication. In: Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining. 2023. p. 1758\u201369.","DOI":"10.1145\/3580305.3599314"},{"key":"1010_CR80","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1145\/1842733.1842736","volume":"44","author":"E Nygren","year":"2010","unstructured":"Nygren E, Sitaraman RK, Sun J. The akamai network: a platform for high-performance internet applications. ACM SIGOPS Oper Syst Rev. 2010;44:2\u201319.","journal-title":"ACM SIGOPS Oper Syst Rev"},{"key":"1010_CR81","doi-asserted-by":"crossref","unstructured":"Osipov E, Kleyko D, Legalov A. Associative synthesis of finite state automata model of a controlled object with hyperdimensional computing. In: IECON 2017-43rd annual conference of the IEEE industrial electronics society. IEEE; 2017. p. 3276\u201381.","DOI":"10.1109\/IECON.2017.8216554"},{"key":"1010_CR82","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11749-021-00759-x","volume":"30","author":"A Pewsey","year":"2021","unstructured":"Pewsey A, Garc\u00eda-Portugu\u00e9s E. Recent advances in directional statistics. TEST. 2021;30:1\u201358.","journal-title":"TEST"},{"key":"1010_CR83","unstructured":"Plate TA. Distributed representations and nested compositional structure. Ph.D. thesis. University of Toronto; 1994."},{"key":"1010_CR84","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1109\/72.377968","volume":"6","author":"TA Plate","year":"1995","unstructured":"Plate TA. Holographic reduced representations. IEEE Trans Neural Netw. 1995;6:623\u201341.","journal-title":"IEEE Trans Neural Netw"},{"key":"1010_CR85","volume-title":"Holographic reduced representation: distributed representation for cognitive structures","author":"TA Plate","year":"2003","unstructured":"Plate TA. Holographic reduced representation: distributed representation for cognitive structures. Stanford: CSLI Publications; 2003."},{"key":"1010_CR86","unstructured":"Rachkovskij D, Fedoseyeva T. On audio signals recognition by multilevel neural network. In: Proceedings of the international symposium on neural networks and neural computing (NEURONET). 1990. p. 281\u20133."},{"key":"1010_CR87","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1162\/089976601300014592","volume":"13","author":"DA Rachkovskij","year":"2001","unstructured":"Rachkovskij DA, Kussul EM. Binding and normalization of binary sparse distributed representations by context-dependent thinning. Neural Comput. 2001;13:411\u201352.","journal-title":"Neural Comput"},{"key":"1010_CR88","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1615\/J Automat Inf Scien.v37.i6.20","volume":"37","author":"DA Rachkovskiy","year":"2005","unstructured":"Rachkovskiy DA, Slipchenko SV, Kussul EM, Baidyk TN. Sparse binary distributed encoding of scalars. J Autom Inf Sci. 2005;37:12\u201323.","journal-title":"J Autom Inf Sci"},{"key":"1010_CR89","doi-asserted-by":"crossref","unstructured":"Rahimi A, Benatti S, Kanerva P, Benini L, Rabaey JM. Hyperdimensional biosignal processing: a case study for EMG-based hand gesture recognition. In: International conference on rebooting computing (ICRC). IEEE; 2016. p. 1\u20138.","DOI":"10.1109\/ICRC.2016.7738683"},{"key":"1010_CR90","doi-asserted-by":"publisher","first-page":"2508","DOI":"10.1109\/TCSI.2017.2705051","volume":"64","author":"A Rahimi","year":"2017","unstructured":"Rahimi A, Datta S, Kleyko D, Frady EP, Olshausen B, Kanerva P, Rabaey JM. High-dimensional computing as a nanoscalable paradigm. Trans Circ Syst I Regular Pap. 2017;64:2508\u201321.","journal-title":"Trans Circ Syst I Regular Pap"},{"key":"1010_CR91","doi-asserted-by":"crossref","unstructured":"Rahimi A, Kanerva P, Rabaey JM. A robust and energy-efficient classifier using brain-inspired hyperdimensional computing. In: International symposium on low power electronics and design (ISLPED). 2016. p. 64\u20139.","DOI":"10.1145\/2934583.2934624"},{"issue":"1","key":"1010_CR92","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1108\/EUM0000000007161","volume":"54","author":"AM Robertson","year":"1998","unstructured":"Robertson AM, Willett P. Applications of n-grams in textual information systems. J Doc. 1998;54(1):48\u201367.","journal-title":"J Doc"},{"key":"1010_CR93","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G. The graph neural network model. Trans Neural Netw. 2008;20:61\u201380.","journal-title":"Trans Neural Netw"},{"key":"1010_CR94","first-page":"1","volume":"55","author":"K Schlegel","year":"2021","unstructured":"Schlegel K, Neubert P, Protzel P. A comparison of vector symbolic architectures. Artif Intell Rev. 2021;55:1\u201333.","journal-title":"Artif Intell Rev"},{"key":"1010_CR95","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3314326","volume":"15","author":"M Schmuck","year":"2019","unstructured":"Schmuck M, Benini L, Rahimi A. Hardware optimizations of dense binary hyperdimensional computing: rematerialization of hypervectors, binarized bundling, and combinational associative memory. J Emerg Technol Comput Syst. 2019;15:1\u201325.","journal-title":"J Emerg Technol Comput Syst"},{"key":"1010_CR96","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1145\/2492101.1555372","volume":"37","author":"B Schroeder","year":"2009","unstructured":"Schroeder B, Pinheiro E, Weber WD. Dram errors in the wild: a large-scale field study. ACM SIGMETRICS Perform Eval Rev. 2009;37:193\u2013204.","journal-title":"ACM SIGMETRICS Perform Eval Rev"},{"key":"1010_CR97","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.peva.2005.01.004","volume":"63","author":"H Shen","year":"2006","unstructured":"Shen H, Xu CZ, Chen G. Cycloid: a constant-degree and lookup-efficient P2P overlay network. Perform Eval. 2006;63:195\u2013216.","journal-title":"Perform Eval"},{"key":"1010_CR98","first-page":"2539","volume":"12","author":"N Shervashidze","year":"2011","unstructured":"Shervashidze N, Schweitzer P, Van Leeuwen EJ, Mehlhorn K, Borgwardt KM. Weisfeiler-lehman graph kernels. J Mach Learn Res. 2011;12:2539\u201361.","journal-title":"J Mach Learn Res"},{"key":"1010_CR99","doi-asserted-by":"crossref","unstructured":"Shridhar K, Jain H, Agarwal A, Kleyko D. End to end binarized neural networks for text classification. In: Proceedings of SustaiNLP: workshop on simple and efficient natural language processing. 2020. p. 29\u201334.","DOI":"10.18653\/v1\/2020.sustainlp-1.4"},{"key":"1010_CR100","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.future.2019.04.010","volume":"100","author":"C Simpkin","year":"2019","unstructured":"Simpkin C, Taylor I, Bent GA, de Mel G, Rallapalli S, Ma L, Srivatsa M. Constructing distributed time-critical applications using cognitive enabled services. Futur Gener Comput Syst. 2019;100:70\u201385.","journal-title":"Futur Gener Comput Syst"},{"key":"1010_CR101","doi-asserted-by":"crossref","unstructured":"Smith D, Stanford P. A random walk in hamming space. In: 1990 IJCNN international joint conference on neural networks. IEEE; 1990. p. 465\u201370.","DOI":"10.1109\/IJCNN.1990.137756"},{"issue":"3","key":"1010_CR102","first-page":"272","volume":"13","author":"A Sokolov","year":"2006","unstructured":"Sokolov A, Rachkovskij D. Approaches to sequence similarity representation. J Inf Theor Appl. 2006;13(3):272\u20138.","journal-title":"J Inf Theor Appl"},{"key":"1010_CR103","doi-asserted-by":"crossref","unstructured":"Sridharan V, Liberty D. A study of dram failures in the field. In: SC\u201912: proceedings of the international conference on high performance computing, networking, storage and analysis. IEEE; 2012. p. 1\u201311.","DOI":"10.1109\/SC.2012.13"},{"key":"1010_CR104","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/TNET.2002.808407","volume":"11","author":"I Stoica","year":"2003","unstructured":"Stoica I, Morris R, Liben-Nowell D, Karger DR, Kaashoek MF, Dabek F, Balakrishnan H. Chord: a scalable peer-to-peer lookup protocol for internet applications. IEEE\/ACM Trans Netw. 2003;11:17\u201332.","journal-title":"IEEE\/ACM Trans Netw"},{"key":"1010_CR105","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-322-3703-7","volume-title":"Advances in neuromorphic hardware exploiting emerging nanoscale devices","author":"M Suri","year":"2017","unstructured":"Suri M. Advances in neuromorphic hardware exploiting emerging nanoscale devices. New Delhi: Springer; 2017."},{"key":"1010_CR106","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/90.663936","volume":"6","author":"DG Thaler","year":"1998","unstructured":"Thaler DG, Ravishankar CV. Using name-based mappings to increase hit rates. IEEE\/ACM Trans Netw. 1998;6:1\u201314.","journal-title":"IEEE\/ACM Trans Netw"},{"key":"1010_CR107","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1613\/jair.1.12664","volume":"72","author":"A Thomas","year":"2021","unstructured":"Thomas A, Dasgupta S, Rosing T. Theoretical foundations of hyperdimensional computing. J Artif Intell Res. 2021;72:215\u201349.","journal-title":"J Artif Intell Res"},{"key":"1010_CR108","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1198\/108571105X29056","volume":"10","author":"J Tracey","year":"2005","unstructured":"Tracey J, Zhu J, Crooks K. A set of nonlinear regression models for animal movement in response to a single landscape feature. J Agric Biol Environ Stat. 2005;10:1\u201318.","journal-title":"J Agric Biol Environ Stat"},{"key":"1010_CR109","doi-asserted-by":"crossref","unstructured":"Verg\u00e9s P, Heddes M, Nunes I, Givargis T, Nicolau A. Classification using hyperdimensional computing: a review with comparative analysis. 2023.","DOI":"10.21203\/rs.3.rs-3425561\/v1"},{"key":"1010_CR110","doi-asserted-by":"publisher","unstructured":"Wale N, Karypis G. Comparison of descriptor spaces for chemical compound retrieval and classification. In: International conference on data mining (ICDM). 2006. p. 678\u201389. https:\/\/doi.org\/10.1109\/ICDM.2006.39.","DOI":"10.1109\/ICDM.2006.39"},{"key":"1010_CR111","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/s11036-008-0144-3","volume":"14","author":"W Wang","year":"2009","unstructured":"Wang W, Ravishankar CV. Hash-based virtual hierarchies for scalable location service in mobile ad-hoc networks. Mobile Netw Appl. 2009;14:625\u201337.","journal-title":"Mobile Netw Appl"},{"key":"1010_CR112","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1093\/jigpal\/jzu028","volume":"23","author":"D Widdows","year":"2015","unstructured":"Widdows D, Cohen T. Reasoning with vectors: a continuous model for fast robust inference. Logic J IGPL. 2015;23:141\u201373.","journal-title":"Logic J IGPL"},{"key":"1010_CR113","doi-asserted-by":"crossref","unstructured":"Wu TF, Li H, Huang PC, Rahimi A, Rabaey JM, Wong HSP, Shulaker MM, Mitra S. Brain-inspired computing exploiting carbon nanotube fets and resistive ram: hyperdimensional computing case study. In: International solid-state circuits conference-(ISSCC); IEEE. 2018. p. 492\u20134.","DOI":"10.1109\/ISSCC.2018.8310399"},{"issue":"1","key":"1010_CR114","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2020","unstructured":"Wu Z, Pan S, Chen F, Long G, Zhang C, Philip SY. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst. 2020;32(1):4\u201324.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1010_CR115","unstructured":"Xu K, Hu W, Leskovec J, Jegelka S. How powerful are graph neural networks? In: International conference on learning representations (ICLR). 2019."},{"key":"1010_CR116","unstructured":"Xu K, Li C, Tian Y, Sonobe T, Kawarabayashi KI, Jegelka S. Representation learning on graphs with jumping knowledge networks. In: International conference on machine learning (ICML). 2018. p. 5453\u201362."},{"key":"1010_CR117","doi-asserted-by":"crossref","unstructured":"Yanardag P, Vishwanathan S. Deep graph kernels. In: International conference on knowledge discovery and data mining (SIGKDD). 2015. p. 1365\u201374.","DOI":"10.1145\/2783258.2783417"},{"key":"1010_CR118","unstructured":"Yerxa T, Anderson A, Weiss E. The hyperdimensional stack machine. In: Cognitive computing. 2018. p. 1\u20132."},{"key":"1010_CR119","doi-asserted-by":"crossref","unstructured":"Zhan Y, Shen D. Increasing the efficiency of support vector machine by simplifying the shape of separation hypersurface. In: International conference on computational and information science. Springer; 2004. p. 732\u20138.","DOI":"10.1007\/978-3-540-30497-5_114"},{"key":"1010_CR120","doi-asserted-by":"crossref","unstructured":"Zou Z, Kim Y, Imani F, Alimohamadi H, Cammarota R, Imani M. Scalable edge-based hyperdimensional learning system with brain-like neural adaptation. In: International conference for high performance computing, storage and analysis (SC): networking. 2021. p. 1\u201315.","DOI":"10.1145\/3458817.3480958"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-024-01010-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-024-01010-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-024-01010-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T15:04:34Z","timestamp":1729782274000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-024-01010-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,24]]},"references-count":120,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["1010"],"URL":"https:\/\/doi.org\/10.1186\/s40537-024-01010-8","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,24]]},"assertion":[{"value":"19 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"145"}}