Triple Archives Particle Swarm Optimization
Open accessThe DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.
Abstract
There are two common challenges in particle swarm optimization (PSO) research, that is, selecting proper exemplars and designing an efficient learning model for a particle. In this article, we propose a triple archives PSO (TAPSO), in which particles in three archives are used to deal with the above two challenges. First, particles who have better fitness (i.e., elites) are recorded in one archive while other particles who offer faster progress, called profiteers in this article, are saved in another archive. Second, when breeding each dimension of a potential exemplar for a particle, we choose a pair of elite and profiteer from corresponding archives as two parents to generate the dimension value by ordinary genetic operators. Third, each particle carries out a specific learning model according to the fitness of its potential exemplars. Furthermore, there is no acceleration coefficient in TAPSO aiming to simplify the learning models. Finally, if an exemplar has excellent performance, it will be regarded as an outstanding exemplar and saved in the third archive, which can be reused by inferior particles aiming to enhance the exploitation and to save computing resources. The experimental results and comparisons between TAPSO and other eight PSOs on 30 benchmark functions and four real applications suggest that TAPSO attains very promising performance in different types of functions, contributing to both higher solution accuracy and faster convergence speed. Furthermore, the effectiveness and efficiency of these new proposed strategies are discussed based on extensive experiments.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Kennedy, J., & Eberhart, R. (2002) · Proceedings of ICNN'95 - International Conference on Neural Networks · doi:10.1109/icnn.1995.488968 · Cited by 58,192
Particle swarm optimization: An overview
Poli, R., Kennedy, J., & Blackwell, T. (2007) · Swarm Intelligence · doi:10.1007/s11721-007-0002-0 · Cited by 21,101
A new optimizer using particle swarm theory
Eberhart, R., & Kennedy, J. (2002) · MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science · doi:10.1109/mhs.1995.494215 · Cited by 16,067 · cited 2×
“In canonical PSO [1], [2], a learner particle selects the global or the local best particle, measured by fitness, as its exemplar to perform the learning process.”
BackgroundMethodA modified particle swarm optimizer
Shi, Y., & Eberhart, R. (2002) · 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360) · doi:10.1109/icec.1998.699146 · Cited by 10,229 · cited 1×
“4 over the optimization process which is still applied in many PSOs now [14].”
BackgroundComprehensive learning particle swarm optimizer for global optimization of multimodal functions
Liang, J. J., Qin, A. K., Suganthan, P. N., & Baskar, S. (2006) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2005.857610 · Cited by 3,743 · cited 4×
“Motivated by the studies, many scholars pour attention on generating a new promising exemplar for a particle based on multiple individuals’ experience [6], [8], [42].”
BackgroundMethodInfluentialSelf-Organizing Hierarchical Particle Swarm Optimizer With Time-Varying Acceleration Coefficients
Ratnaweera, A., Halgamuge, S. K., & Watson, H. C. (2004) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2004.826071 · Cited by 3,034 · cited 1×
“[15] further advocated a hierarchical PSO with time-varying acceleration coefficients (HPSO-TVAC).”
Background(2005) · Cited by 2,565
Adaptive Particle Swarm Optimization
Zhan, Z.-H., Zhang, J., Li, Y., & Chung, H. S.-H. (2009) · IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) · doi:10.1109/tsmcb.2009.2015956 · Cited by 2,075
Self-citationThe Fully Informed Particle Swarm: Simpler, Maybe Better
Mendes, R., Kennedy, J., & Neves, J. (2004) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2004.826074 · Cited by 1,745 · cited 3×
“Motivated by the studies, many scholars pour attention on generating a new promising exemplar for a particle based on multiple individuals’ experience [6], [8], [42].”
BackgroundMethodPopulation structure and particle swarm performance
Kennedy, J., & Mendes, R. (2003) · Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600) · doi:10.1109/cec.2002.1004493 · Cited by 1,586 · cited 2×
“2) Learning Strategies Adjustment: In the PSO community, extracting information based on the global version topological structure PSO (GPSO) and the local version topological structure PSO (LPSO) are two basic learning strategies for particles [28].”
BackgroundFuzzy adaptive particle swarm optimization
Shi, Y., & Eberhart, R. C. (2002) · Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546) · doi:10.1109/cec.2001.934377 · Cited by 1,071 · cited 1×
“However, considering that the search process of PSO is nonlinear and complicated, various nonlinear-varying strategies are proposed to adjust the parameters [16]–[19] aiming to give particles diverse search behaviors.”
BackgroundA Competitive Swarm Optimizer for Large Scale Optimization
Cheng, R., & Jin, Y. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2322602 · Cited by 1,052 · cited 1×
“Furthermore, learning strategies based on the pairwise competition mechanism [40] and exemplar pool strategy [41] also achieve a good balance between exploration and exploitation.”
BackgroundA novel particle swarm optimization algorithm with adaptive inertia weight
Nickabadi, A., Ebadzadeh, M. M., & Safabakhsh, R. (2011) · Applied Soft Computing · doi:10.1016/j.asoc.2011.01.037 · Cited by 806 · cited 1×
“To lay out a more satisfactory adjustment for the parameters, many scholars proposed different adjustments by taking advantage of historical information of the entire population [9], [20], [21].”
BackgroundOrthogonal Learning Particle Swarm Optimization
Zhan, Z.-H., Zhang, J., Li, Y., & Shi, Y.-H. (2011) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2010.2052054 · Cited by 725
Self-citationNonlinear inertia weight variation for dynamic adaptation in particle swarm optimization
Chatterjee, A., & Siarry, P. (2006) · Computers & Operations Research · doi:10.1016/j.cor.2004.08.012 · Cited by 690
Genetic Learning Particle Swarm Optimization
Gong, Y.-J., Li, J.-J., Zhou, Y., Li, Y., Chung, H. S.-H., Shi, Y.-H., & Zhang, J. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2475174 · Cited by 563 · cited 2×
“Motivated by the studies, many scholars pour attention on generating a new promising exemplar for a particle based on multiple individuals’ experience [6], [8], [42].”
BackgroundParticle swarm optimization with Gaussian mutation
Higashi, N., & Iba, H. (2004) · Proceedings of the 2003 IEEE Swarm Intelligence Symposium. SIS'03 (Cat. No.03EX706) · doi:10.1109/sis.2003.1202250 · Cited by 544 · cited 1×
“For instance, genetic operators [42], [43] and various local searching strategies [41], [44], [45] are very popular auxiliaries for balancing the exploration and exploitation.”
BackgroundLynn, N., & Suganthan, P. N. (2015) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2015.05.002 · Cited by 515 · cited 2×
“To overcome shortcomings caused by a single learning exemplar, many researchers adopt comprehensive information of the entire population as an exemplar for a particle by different weighting methods [6], [8], [10], [31]–[33].”
MethodDynamic multi-swarm particle swarm optimizer
Liang, J. J., & Suganthan, P. N. (2005) · Proceedings 2005 IEEE Swarm Intelligence Symposium, 2005. SIS 2005. · doi:10.1109/sis.2005.1501611 · Cited by 486 · cited 3×
“Due to space limitations, the basic information of the benchmark functions is given in Table S-I of the supplementary material, and the details of the functions can refer to [9], [13], [37], [45], and [58].”
BackgroundFitness-distance-ratio based particle swarm optimization
Peram, T., Veeramachaneni, K., & Mohan, C. K. (2004) · Proceedings of the 2003 IEEE Swarm Intelligence Symposium. SIS'03 (Cat. No.03EX706) · doi:10.1109/sis.2003.1202264 · Cited by 474 · cited 2×
“For instance, in [7], a particle uses the ratio of the relative fitness and the distance of other particles, rather than the fitness, to determine its exemplar.”
BackgroundA novel particle swarm optimization algorithm with Levy flight
Haklı, H., & Uğuz, H. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2014.06.034 · Cited by 426 · cited 1×
“Furthermore, Lévy flight, as a common random walk strategy, is another type of auxiliary for PSO [46], [47].”
BackgroundGong, M., Cai, Q., Chen, X., & Ma, L. (2014) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2013.2260862 · Cited by 394
A Self-Learning Particle Swarm Optimizer for Global Optimization Problems
Li, C., Yang, S., & Nguyen, T. T. (2012) · IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) · doi:10.1109/tsmcb.2011.2171946 · Cited by 384 · cited 5×
“Due to space limitations, the basic information of the benchmark functions is given in Table S-I of the supplementary material, and the details of the functions can refer to [9], [13], [37], [45], and [58].”
BackgroundMethodInfluentialFrankenstein's PSO: A Composite Particle Swarm Optimization Algorithm
Montes de Oca, M. A., Stutzle, T., Birattari, M., & Dorigo, M. (2009) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2009.2021465 · Cited by 366 · cited 1×
“For comparative analysis, other eight state-of-the-art PSO variants, including F_PSO [59], OLPSO [10], SLPSO [13], PSODDS [60], HCLPSO [33], CCPSOISM [61], SRPSO [22], and EPSO [48], are selected as peer algorithms in this article.”
MethodZhan, Z.-H., Li, J., Cao, J., Zhang, J., Chung, H. S.-H., & Shi, Y.-H. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tsmcb.2012.2209115 · Cited by 346 · cited 1×
“Furthermore, the multiswarm mechanism [37], [38] is also an efficient way to enhance the performance of PSO.”
BackgroundSelf-citationSelf regulating particle swarm optimization algorithm
Tanweer, M. R., Suresh, S., & Sundararajan, N. (2014) · Information Sciences · doi:10.1016/j.ins.2014.09.053 · Cited by 338 · cited 2×
“A common feature in these improvements is that particles regulate their own parameters according to their fitness [22]–[24], velocity [25], or population diversity [26], [27].”
BackgroundMethodEnsemble particle swarm optimizer
Lynn, N., & Suganthan, P. N. (2017) · Applied Soft Computing · doi:10.1016/j.asoc.2017.02.007 · Cited by 298 · cited 2×
“To take full advantage of some existing PSO variants, Lynn and Suganthan [48] proposed an ensemble PSO (EPSO), in which five PSO variants are hybridized together by an ensemble approach.”
MethodTwo problems with backpropagation and other steepest-descent learning procedures for networks
Sutton, R. S. (1986) · eScholarship (California Digital Library) · Cited by 264
Wang, Z.-J., Zhan, Z.-H., Yu, W.-J., Lin, Y., Zhang, J., Gu, T.-L., & Zhang, J. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2933499 · Cited by 257 · cited 1×
“ability in solving complicated problems [3]–[5].”
Self-citationLiu, X.-F., Zhan, Z.-H., Gao, Y., Zhang, J., Kwong, S., & Zhang, J. (2019) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2018.2875430 · Cited by 246 · cited 1×
“The heterogeneous learning strategies based on the multiswarm mechanism enable the population to efficiently cope with different fitness land-scapes and offer a better balance between exploration and exploitation [37]–[39].”
BackgroundSelf-citationParticle swarm optimization based on dimensional learning strategy
Xu, G., Cui, Q., Shi, X., Ge, H., Zhan, Z.-H., Lee, H. P., Liang, Y., Tai, R., & Wu, C. (2019) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2018.12.009 · Cited by 236 · cited 2×
“In this sense, the comprehensive learning strategy [8], the orthogonal learning strategy [10], the interactive learning strategy [34], and the dimensional learning strategy [31] are remarkable works.”
BackgroundMethodSelf-citationXin, B., Chen, J., Zhang, J., Fang, H., & Peng, Z.-H. (2012) · IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) · doi:10.1109/tsmcc.2011.2160941 · Cited by 189
Population topologies for particle swarm optimization and differential evolution
Lynn, N., Ali, M. Z., & Suganthan, P. N. (2018) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2017.11.002 · Cited by 187 · cited 1×
“Many studies [28]–[30] suggest that learning strategies based on sparse and dense neighbor topologies are beneficial for complicated multimodal problems and simple unimodal problems, respectively.”
BackgroundLi, Y., Zhan, Z.-H., Lin, S., Zhang, J., & Luo, X. (2015) · Information Sciences · doi:10.1016/j.ins.2014.09.030 · Cited by 187 · cited 1×
“For comparative analysis, other eight state-of-the-art PSO variants, including F_PSO [59], OLPSO [10], SLPSO [13], PSODDS [60], HCLPSO [33], CCPSO-ISM [61], SRPSO [22], and EPSO [48], are selected as peer algorithms in this article.”
MethodSelf-citationAn expanded particle swarm optimization based on multi-exemplar and forgetting ability
Xia, X., Gui, L., He, G., Wei, B., Zhang, Y., Yu, F., Wu, H., & Zhan, Z.-H. (2020) · Information Sciences · doi:10.1016/j.ins.2019.08.065 · Cited by 175 · cited 1×
“Moreover, considering that all particles using the same learning model may cause a lack of intelligence in populations to cope with different complex situations, some researchers expand the mono-learning-model to the multi-learning model [12], [13].”
BackgroundSelf-citationComposite Particle Swarm Optimizer With Historical Memory for Function Optimization
Li, J., Zhang, J., Jiang, C., & Zhou, M. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2424836 · Cited by 173 · cited 1×
“A common feature in these improvements is that particles regulate their own parameters according to their fitness [22]–[24], velocity [25], or population diversity [26], [27].”
BackgroundCloudde: A Heterogeneous Differential Evolution Algorithm and Its Distributed Cloud Version
Zhan, Z., Liu, X., Zhang, H., Yu, Z., Weng, J., Li, Y., Gu, T., & Zhang, J. (2016) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2016.2597826 · Cited by 164
Self-citationKıran, M. S., & Gündüz, M. (2013) · Applied Soft Computing · doi:10.1016/j.asoc.2012.12.007 · Cited by 158 · cited 1×
“from this, some studies manifest that hybridizing PSO with other evolutionary algorithms (EAs) also shows very promising performance [49]–[51].”
BackgroundZhang, L., Tang, Y., Hua, C., & Guan, X. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2014.11.018 · Cited by 153 · cited 2×
“To lay out a more satisfactory adjustment for the parameters, many scholars proposed different adjustments by taking advantage of historical information of the entire population [9], [20], [21].”
BackgroundMethodParticle Swarm Optimization With Interswarm Interactive Learning Strategy
Qin, Q., Cheng, S., Zhang, Q., Li, L., & Shi, Y. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2474153 · Cited by 139 · cited 1×
“In this sense, the comprehensive learning strategy [8], the orthogonal learning strategy [10], the interactive learning strategy [34], and the dimensional learning strategy [31] are remarkable works.”
BackgroundTopology selection for particle swarm optimization
Liu, Q., Wei, W., Yuan, H., Zhan, Z., & Li, Y. (2016) · Information Sciences · doi:10.1016/j.ins.2016.04.050 · Cited by 121
Self-citationZhang, X., Du, K.-J., Zhan, Z., Kwong, S., Gu, T., & Zhang, J. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2937565 · Cited by 118
Self-citationAn Adaptive Multiobjective Particle Swarm Optimization Based on Multiple Adaptive Methods
Han, H., Lü, W., & Qiao, J. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2692385 · Cited by 113 · cited 1×
“A common feature in these improvements is that particles regulate their own parameters according to their fitness [22]–[24], velocity [25], or population diversity [26], [27].”
BackgroundTanweer, M. R., Sundaram, S., & Sundararajan, N. (2015) · Information Sciences · doi:10.1016/j.ins.2015.07.035 · Cited by 101
A Scatter Learning Particle Swarm Optimization Algorithm for Multimodal Problems
Ren, Z., Zhang, A., Wen, C., & Feng, Z. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2279802 · Cited by 91 · cited 2×
“For instance, genetic operators [42], [43] and various local searching strategies [41], [44], [45] are very popular auxiliaries for balancing the exploration and exploitation.”
BackgroundNeighborhood Re-structuring in Particle Swarm Optimization
Mohais, A. S., Mendes, R., Ward, C., & Posthoff, C. (2005) · Lecture notes in computer science · doi:10.1007/11589990_80 · Cited by 84 · cited 1×
“Other distance-based [35] and fitness-based [36] selections of exem-plars also manifest very favorable performance.”
BackgroundLu, J., Hu, H., & Bai, Y. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.10.065 · Cited by 83
That's More Like It: Multiple Exemplars Facilitate Word Learning
Twomey, K. E., Ranson, S. L., & Horst, J. S. (2013) · Infant and Child Development · doi:10.1002/icd.1824 · Cited by 75
Bare Bones Particle Swarm Optimization With Scale Matrix Adaptation
Campos, M. C. M., Krohling, R. A., & Enriquez, I. R. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2290223 · Cited by 70
Xu, X., Shi, Z., & Pan, B. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.04.008 · Cited by 67
Adaptive particle swarmi optimization using velocity information of swarm
Yasuda, K., & Iwasaki, N. (2005) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2004.1400880 · Cited by 59 · cited 1×
“A common feature in these improvements is that particles regulate their own parameters according to their fitness [22]–[24], velocity [25], or population diversity [26], [27].”
BackgroundRosales, R., Rehfeldt, R. A., & Lovett, S. (2011) · The Analysis of Verbal Behavior · doi:10.1007/bf03393092 · Cited by 57 · cited 1×
“Moreover, many studies indicate that children with multiple exemplars can offer better words learning ability compared to those children who only learn from one exemplar [54]–[56].”
BackgroundNovel self-adaptive particle swarm optimization methods
Pornsing, C., Sodhi, M. S., & Lamond, B. F. (2015) · Soft Computing · doi:10.1007/s00500-015-1716-3 · Cited by 57 · cited 1×
“However, considering that the search process of PSO is nonlinear and complicated, various nonlinear-varying strategies are proposed to adjust the parameters [16]–[19] aiming to give particles diverse search behaviors.”
BackgroundImproving Estimation of Distribution Algorithm on Multimodal Problems by Detecting Promising Areas
Yang, P., Tang, K., & Lu, X. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2352411 · Cited by 50 · cited 1×
“On the contrary, areas with very steep surface curves are common around local optima [11], [57].”
BackgroundDirectionally Driven Self-Regulating Particle Swarm Optimization algorithm
Tanweer, M. R., Auditya, R., Sundaram, S., Sundararajan, N., & Srikanth, N. (2016) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2016.01.006 · Cited by 49 · cited 1×
“own parameters according to their fitness [22]–[24], velocity [25], or population diversity [26], [27].”
BackgroundXia, X., Liu, J., & Hu, Z. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2014.06.012 · Cited by 33 · cited 2×
“Due to space limitations, the basic information of the benchmark functions is given in Table S-I of the supplementary material, and the details of the functions can refer to [9], [13], [37], [45], and [58].”
BackgroundSelf-citationHanafi, I., Cabrera, F. M., Dimane, F., & Manzanares, J. T. (2016) · Procedia Technology · doi:10.1016/j.protcy.2016.01.044 · Cited by 26 · cited 1×
“Other distance-based [35] and fitness-based [36] selections of exemplars also manifest very favorable performance.”
BackgroundPan, B., Shi, Z., & Xu, X. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2853268 · Cited by 24
Bengoetxea, E., & Larrañaga, P. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15461-4_39 · Cited by 22 · cited 1×
“Apart from this, some studies manifest that hybridizing PSO with other evolutionary algorithms (EAs) also shows very promising performance [49]–[51].”
BackgroundThe Transfer of Object Learning after Training with Multiple Exemplars
Baeck, A., Maes, K., Meel, C. V., & de Beeck, H. O. (2016) · Frontiers in Psychology · doi:10.3389/fpsyg.2016.01386 · Cited by 14 · cited 1×
“Moreover, many studies indicate that children with multiple exemplars can offer better words learning ability compared to those children who only learn from one exemplar [54]–[56].”
Background
Cited by
Song, X.-F., Zhang, Y., Gong, D.-W., & Gao, X.-Z. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3061152 · Cited by 348
Self-citation
Metadata
- Authors
- Xia, X., Gui, L., Yu, F., Wu, H., Wei, B., Zhang, Y.-L., & Zhan, Z.-H.
- Venue
- IEEE Transactions on Cybernetics
- Published
- 2020-12
- Volume
- 50
- Issue
- 12
- Pages
- 4862-4875
- ISSN
- 2168-2267 (ISSN-L)
- 2168-2275
- OpenAlex
- W2979736100
- Cited by
- 235
- References
- 60
- FWCI
- 10.36
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.