# Federated Parameter-Efficient Fine-Tuning on Multi-task Federated Learning Seq, Token, Choice

Source: [Federated Parameter-Efficient Fine-Tuning on Multi-task Federated Learning Seq, Token, Choice](<https://www.sota2.com/research/sota/federated-parameter-efficient-fine-tuning-on-multi-task-federated-learning-seq-token-choice>)

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

Data updated: 2026-04-16T07:03:06.408Z

Evaluation of Parameter-Efficient Fine-Tuning methods within a federated learning context using the Multi-task Federated Learning Seq, Token, Choice dataset, typically measured by resource consumption like Memory Usage.

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 | Federated Parameter-Efficient Fine-Tuning |
| Dataset (including any stated split) | Multi-task Federated Learning Seq, Token, Choice |
| Metric | Memory Usage (GB) |
| Unit | SIZE |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Memory Usage (GB)](<https://www.sota2.com/research/sota/federated-parameter-efficient-fine-tuning-on-multi-task-federated-learning-seq-token-choice.md?metric=Memory%20Usage%20(GB)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Memory Usage (GB) | Result date | Report paper |
| --- | --- | --- | --- |
| UCB-DUAL | 3.72 | Not recorded | 68fa7a8f1e209131cea83e56 |
| HomoLoRA | 4.69 | Not recorded | 68fa7a8f1e209131cea83e56 |
| HetLoRA | 4.73 | Not recorded | 68fa7a8f1e209131cea83e56 |

### UCB-DUAL

Memory Usage (GB): 3.72. Result ID: 69e0881f47f34ce924c943d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a8f1e209131cea83e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8f1e209131cea83e56.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HomoLoRA

Memory Usage (GB): 4.69. Result ID: 69e0881f47f34ce924c943d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a8f1e209131cea83e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e761e209131cea40072.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HetLoRA

Memory Usage (GB): 4.73. Result ID: 69e0881f47f34ce924c943d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a8f1e209131cea83e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72481e209131cea5586e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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