# Multi-Task Learning on Multi-MNIST Fashion F+M (Runtime Evaluation)

Source: [Multi-Task Learning on Multi-MNIST Fashion F+M (Runtime Evaluation)](<https://www.sota2.com/research/sota/multi-task-learning-on-multi-mnist-fashion-f-plus-m-runtime-evaluation>)

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

Data updated: 2026-02-26T05:42:08.323Z

Evaluation of training efficiency and runtime performance (epochs, per-epoch time, total time) for Multi-Task Learning models on the Multi-MNIST Fashion F+M dataset.

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 | Multi-Task Learning |
| Dataset (including any stated split) | Multi-MNIST Fashion F+M |
| Metric | Epochs |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Epochs](<https://www.sota2.com/research/sota/multi-task-learning-on-multi-mnist-fashion-f-plus-m-runtime-evaluation.md?metric=Epochs>): Higher is better; unit: SCALAR.

- [Latency (Per-Epoch)](<https://www.sota2.com/research/sota/multi-task-learning-on-multi-mnist-fashion-f-plus-m-runtime-evaluation.md?metric=Latency%20(Per-Epoch)>): Lower is better; unit: TIME.

- [Total Runtime](<https://www.sota2.com/research/sota/multi-task-learning-on-multi-mnist-fashion-f-plus-m-runtime-evaluation.md?metric=Total%20Runtime>): Lower is better; unit: TIME.

## Recorded results

| Method | Epochs | Result date | Report paper |
| --- | --- | --- | --- |
| LS | 100 | Not recorded | 68fa5d2f1e209131ce9d7e68 |
| PMTL | 100 | Not recorded | 68fa5d2f1e209131ce9d7e68 |
| EPO | 100 | Not recorded | 68fa5d2f1e209131ce9d7e68 |
| FERERO | 100 | Not recorded | 68fa5d2f1e209131ce9d7e68 |

### LS

Epochs: 100. Result ID: 698bba967a967eddb770e9e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5d2f1e209131ce9d7e68.md>)

Recorded evaluation configuration: {"Algorithm":"Algorithm 3"}. This record does not assert independent reproduction.

### PMTL

Epochs: 100. Result ID: 698bba967a967eddb770e9ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5d2f1e209131ce9d7e68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12f9c.md>)

Recorded evaluation configuration: {"Algorithm":"Algorithm 3"}. This record does not assert independent reproduction.

### EPO

Epochs: 100. Result ID: 698bba967a967eddb770e9eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5d2f1e209131ce9d7e68.md>)

Recorded evaluation configuration: {"Algorithm":"Algorithm 3"}. This record does not assert independent reproduction.

### FERERO

Epochs: 100. Result ID: 698bba967a967eddb770e9ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5d2f1e209131ce9d7e68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5d2f1e209131ce9d7e68.md>)

[Implementation](<https://github.com/lisha-chen/FERERO/>)

Recorded evaluation configuration: {"Algorithm":"Algorithm 3"}. This record does not assert independent reproduction.

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