The authors developed MoSAIC, a mixture-of-experts architecture in which parameter-efficient LoRA adapters trained by individual clients become expert branches in a server model.
Federated robot learning preserves local expertise while cutting communication costs
RoboFL assembles locally trained adapters as routed experts, enabling institutions to jointly improve robot policies without pooling their interaction data.
Top University
Rongyu Zhang · Ruizhi Fan · Yunfan Lou · Hengyu Fang · Shenli Zheng · Chenrui Wu · +5 more
Nanjing University · Peking University · Simon Fraser University · Hong Kong University of Science and Technology
Research Digest··2 min read
Zhang et al.
Why this paper
From Nanjing University and 3 others
In one line
A federated method assembling local LoRA adapters as server MoE experts outperforms centralized PEFT by 12.23% with 86.81% less communication.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§