Benchmark
HtFLlib Benchmark
What is HtFLlib?
HtFLlib is a benchmark for heterogeneous federated learning that examines how 40 vision, NLP and sensor models and 10 algorithms collaborate under non-IID data.
- Released
- 2025-06-04
- Evaluates
- 安全, Safety, 其他, Other, 大语言模型, LLM, 安全对齐, Safety Alignment, 不支持, Unsupported
- Openness
- unknown
- Importer
- OpenCompass Hub
- Reported scores
- 0
Source provenance
- Original evidence https://hub.opencompass.org.cn/dataset-detail/HtFLlib
HtFLlib paper and code
- Paper https://arxiv.org/abs/2506.03954
- Paper https://arxiv.org/abs/2001.01523
- Paper https://arxiv.org/abs/2006.16765
- Paper https://arxiv.org/abs/2401.03230
- Paper https://arxiv.org/abs/2403.15760
- Paper https://arxiv.org/abs/2406.00488
- Paper https://arxiv.org/pdf/1811.11479.pdf
- Code https://github.com/TsingZ0/HtFLlib
No reported scores are on record for this benchmark yet.