Robust Clustering Using Hyperdimensional Computing
This paper addresses the clustering of data in the hyperdimensional computing (HDC) domain. In prior work, an HDC-based clustering framework, referred to as HDCluster, has been proposed. However, the performance of the existing HDCluster is not robust. The performance of HDCluster is degraded as the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Circuits and Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10480378/ |
| _version_ | 1797206061516587008 |
|---|---|
| author | Lulu Ge Keshab K. Parhi |
| author_facet | Lulu Ge Keshab K. Parhi |
| author_sort | Lulu Ge |
| collection | DOAJ |
| description | This paper addresses the clustering of data in the hyperdimensional computing (HDC) domain. In prior work, an HDC-based clustering framework, referred to as HDCluster, has been proposed. However, the performance of the existing HDCluster is not robust. The performance of HDCluster is degraded as the hypervectors for the clusters are chosen at random during the initialization step. To overcome this bottleneck, we assign the initial cluster hypervectors by exploring the similarity of the encoded data, referred to as query hypervectors. Intra-cluster hypervectors have a higher similarity than inter-cluster hypervectors. Harnessing the similarity results among query hypervectors, this paper proposes four HDC-based clustering algorithms: similarity-based k-means, equal bin-width histogram, equal bin-height histogram, and similarity-based affinity propagation. Experimental results illustrate that: (i) Compared to the existing HDCluster, our proposed HDC-based clustering algorithms can achieve better accuracy, more robust performance, fewer iterations, and less execution time. Similarity-based affinity propagation outperforms the other three HDC-based clustering algorithms on eight datasets by 2% ~ 38% in clustering accuracy. (ii) Even for one-pass clustering, i.e., without any iterative update of the cluster hypervectors, our proposed algorithms can provide more robust clustering accuracy than HDCluster. (iii) Over eight datasets, five out of eight can achieve higher or comparable accuracy when projected onto the hyperdimensional space. Traditional clustering is more desirable than HDC when the number of clusters, <inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>, is large. |
| first_indexed | 2024-04-24T09:01:02Z |
| format | Article |
| id | doaj.art-a509ee58a01f4c9389798b155b7aab78 |
| institution | Directory Open Access Journal |
| issn | 2644-1225 |
| language | English |
| last_indexed | 2024-04-24T09:01:02Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Circuits and Systems |
| spelling | doaj.art-a509ee58a01f4c9389798b155b7aab782024-04-15T23:01:17ZengIEEEIEEE Open Journal of Circuits and Systems2644-12252024-01-01510211610.1109/OJCAS.2024.338150810480378Robust Clustering Using Hyperdimensional ComputingLulu Ge0https://orcid.org/0000-0002-0043-6512Keshab K. Parhi1https://orcid.org/0000-0001-6543-2793Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USADepartment of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USAThis paper addresses the clustering of data in the hyperdimensional computing (HDC) domain. In prior work, an HDC-based clustering framework, referred to as HDCluster, has been proposed. However, the performance of the existing HDCluster is not robust. The performance of HDCluster is degraded as the hypervectors for the clusters are chosen at random during the initialization step. To overcome this bottleneck, we assign the initial cluster hypervectors by exploring the similarity of the encoded data, referred to as query hypervectors. Intra-cluster hypervectors have a higher similarity than inter-cluster hypervectors. Harnessing the similarity results among query hypervectors, this paper proposes four HDC-based clustering algorithms: similarity-based k-means, equal bin-width histogram, equal bin-height histogram, and similarity-based affinity propagation. Experimental results illustrate that: (i) Compared to the existing HDCluster, our proposed HDC-based clustering algorithms can achieve better accuracy, more robust performance, fewer iterations, and less execution time. Similarity-based affinity propagation outperforms the other three HDC-based clustering algorithms on eight datasets by 2% ~ 38% in clustering accuracy. (ii) Even for one-pass clustering, i.e., without any iterative update of the cluster hypervectors, our proposed algorithms can provide more robust clustering accuracy than HDCluster. (iii) Over eight datasets, five out of eight can achieve higher or comparable accuracy when projected onto the hyperdimensional space. Traditional clustering is more desirable than HDC when the number of clusters, <inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>, is large.https://ieeexplore.ieee.org/document/10480378/Hyperdimensional computing (HDC)clusteringk-meanshierarchical clusteringaffinity propagation |
| spellingShingle | Lulu Ge Keshab K. Parhi Robust Clustering Using Hyperdimensional Computing IEEE Open Journal of Circuits and Systems Hyperdimensional computing (HDC) clustering k-means hierarchical clustering affinity propagation |
| title | Robust Clustering Using Hyperdimensional Computing |
| title_full | Robust Clustering Using Hyperdimensional Computing |
| title_fullStr | Robust Clustering Using Hyperdimensional Computing |
| title_full_unstemmed | Robust Clustering Using Hyperdimensional Computing |
| title_short | Robust Clustering Using Hyperdimensional Computing |
| title_sort | robust clustering using hyperdimensional computing |
| topic | Hyperdimensional computing (HDC) clustering k-means hierarchical clustering affinity propagation |
| url | https://ieeexplore.ieee.org/document/10480378/ |
| work_keys_str_mv | AT luluge robustclusteringusinghyperdimensionalcomputing AT keshabkparhi robustclusteringusinghyperdimensionalcomputing |