# k-means clustering on YearPredictionMSD (train)

Source: [k-means clustering on YearPredictionMSD (train)](<https://www.sota2.com/research/sota/k-means-clustering-on-yearpredictionmsd-train>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:36:07.900Z

Evaluation of k-means clustering performance on the training split of the YearPredictionMSD dataset, measured using cost and communication complexity metrics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | k-means clustering |
| Dataset (including any stated split) | YearPredictionMSD (train) |
| Metric | Avg Cost |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 26 of 26 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Avg Cost](<https://www.sota2.com/research/sota/k-means-clustering-on-yearpredictionmsd-train.md?metric=Avg%20Cost>): Lower is better; unit: SCALAR.

- [Std Dev Cost](<https://www.sota2.com/research/sota/k-means-clustering-on-yearpredictionmsd-train.md?metric=Std%20Dev%20Cost>): Lower is better; unit: SCALAR.

- [Communication Complexity](<https://www.sota2.com/research/sota/k-means-clustering-on-yearpredictionmsd-train.md?metric=Communication%20Complexity>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Avg Cost | Result date | Report paper |
| --- | --- | --- | --- |
| KMEANS++ | 71.65 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-VKMC | 71.92 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-VKMC | 71.97 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-VKMC | 72.14 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-VKMC | 72.23 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-VKMC | 72.54 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-VKMC | 72.57 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-VKMC | 72.68 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-VKMC | 72.74 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-VKMC | 73.25 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-VKMC | 73.52 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-VKMC | 73.76 | Not recorded | 68fa6dc81e209131cea3c307 |
| DISTDIM | 74.89 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-VKMC | 74.91 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-DI | 75.27 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-DI | 75.32 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-DI | 75.49 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-DI | 75.52 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-DIST | 76.38 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-DIST | 76.44 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-DIST | 76.7 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-DI | 76.82 | Not recorded | 68fa6dc81e209131cea3c307 |
| C-DI | 77.75 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-DIST | 77.85 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-DIST | 78.13 | Not recorded | 68fa6dc81e209131cea3c307 |
| U-DIST | 78.87 | Not recorded | 68fa6dc81e209131cea3c307 |

### KMEANS++

Avg Cost: 71.65. Result ID: 698fe9a23a6c314849fcbf19.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Centralized k-means++","Coreset size":"N/A"}. This record does not assert independent reproduction.

### C-VKMC

Avg Cost: 71.92. Result ID: 698fe9a23a6c314849fcbf1f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Vertical federated coreset for k-means","Coreset size":6000}. This record does not assert independent reproduction.

### C-VKMC

Avg Cost: 71.97. Result ID: 698fe9a23a6c314849fcbf1e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Vertical federated coreset for k-means","Coreset size":5000}. This record does not assert independent reproduction.

### C-VKMC

Avg Cost: 72.14. Result ID: 698fe9a23a6c314849fcbf1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Vertical federated coreset for k-means","Coreset size":4000}. This record does not assert independent reproduction.

### C-VKMC

Avg Cost: 72.23. Result ID: 698fe9a23a6c314849fcbf1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Vertical federated coreset for k-means","Coreset size":3000}. This record does not assert independent reproduction.

### U-VKMC

Avg Cost: 72.54. Result ID: 698fe9a23a6c314849fcbf24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for k-means","Coreset size":5000}. This record does not assert independent reproduction.

### U-VKMC

Avg Cost: 72.57. Result ID: 698fe9a23a6c314849fcbf25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for k-means","Coreset size":6000}. This record does not assert independent reproduction.

### C-VKMC

Avg Cost: 72.68. Result ID: 698fe9a23a6c314849fcbf1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Vertical federated coreset for k-means","Coreset size":2000}. This record does not assert independent reproduction.

### U-VKMC

Avg Cost: 72.74. Result ID: 698fe9a23a6c314849fcbf23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for k-means","Coreset size":4000}. This record does not assert independent reproduction.

### U-VKMC

Avg Cost: 73.25. Result ID: 698fe9a23a6c314849fcbf22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for k-means","Coreset size":3000}. This record does not assert independent reproduction.

### U-VKMC

Avg Cost: 73.52. Result ID: 698fe9a23a6c314849fcbf21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for k-means","Coreset size":2000}. This record does not assert independent reproduction.

### C-VKMC

Avg Cost: 73.76. Result ID: 698fe9a23a6c314849fcbf1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Vertical federated coreset for k-means","Coreset size":1000}. This record does not assert independent reproduction.

### DISTDIM

Avg Cost: 74.89. Result ID: 698fe9a23a6c314849fcbf26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67001e209131cea13a25.md>)

Recorded evaluation configuration: {"Algorithm":"Distributed k-means baseline","Coreset size":"N/A"}. This record does not assert independent reproduction.

### U-VKMC

Avg Cost: 74.91. Result ID: 698fe9a23a6c314849fcbf20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for k-means","Coreset size":1000}. This record does not assert independent reproduction.

### C-DI

Avg Cost: 75.27. Result ID: 698fe9a23a6c314849fcbf2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Coreset for Distributed Clustering","Coreset size":5000}. This record does not assert independent reproduction.

### C-DI

Avg Cost: 75.32. Result ID: 698fe9a23a6c314849fcbf2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Coreset for Distributed Clustering","Coreset size":6000}. This record does not assert independent reproduction.

### C-DI

Avg Cost: 75.49. Result ID: 698fe9a23a6c314849fcbf2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Coreset for Distributed Clustering","Coreset size":4000}. This record does not assert independent reproduction.

### C-DI

Avg Cost: 75.52. Result ID: 698fe9a23a6c314849fcbf29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Coreset for Distributed Clustering","Coreset size":3000}. This record does not assert independent reproduction.

### U-DIST

Avg Cost: 76.38. Result ID: 698fe9a23a6c314849fcbf31.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for Distributed Clustering","Coreset size":5000}. This record does not assert independent reproduction.

### U-DIST

Avg Cost: 76.44. Result ID: 698fe9a23a6c314849fcbf32.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for Distributed Clustering","Coreset size":6000}. This record does not assert independent reproduction.

### U-DIST

Avg Cost: 76.7. Result ID: 698fe9a23a6c314849fcbf30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for Distributed Clustering","Coreset size":4000}. This record does not assert independent reproduction.

### C-DI

Avg Cost: 76.82. Result ID: 698fe9a23a6c314849fcbf28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Coreset for Distributed Clustering","Coreset size":2000}. This record does not assert independent reproduction.

### C-DI

Avg Cost: 77.75. Result ID: 698fe9a23a6c314849fcbf27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

[Implementation](<https://github.com/haoyuzhao123/coreset-vfl-codes>)

Recorded evaluation configuration: {"Algorithm":"Coreset for Distributed Clustering","Coreset size":1000}. This record does not assert independent reproduction.

### U-DIST

Avg Cost: 77.85. Result ID: 698fe9a23a6c314849fcbf2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for Distributed Clustering","Coreset size":3000}. This record does not assert independent reproduction.

### U-DIST

Avg Cost: 78.13. Result ID: 698fe9a23a6c314849fcbf2e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for Distributed Clustering","Coreset size":2000}. This record does not assert independent reproduction.

### U-DIST

Avg Cost: 78.87. Result ID: 698fe9a23a6c314849fcbf2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c307.md>)

Recorded evaluation configuration: {"Algorithm":"Uniform sampling for Distributed Clustering","Coreset size":1000}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
