Research & Papers

SeFoRA: Sketch-based federated LoRA beats state-of-the-art on GLUE

When clients use different LoRA ranks, aggregation breaks—SeFoRA fixes it with linear sketches.

Deep Dive

Researchers propose SeFoRA, a sketch-aggregated federated LoRA algorithm for parameter-efficient fine-tuning of large neural networks. It lets clients use different LoRA ranks by transmitting a linear sketch of their local updates, enabling direct aggregation at the federator and alleviating the bilinear mismatch. A rank-homogeneous version, SeFoRA-Ho, is shown to converge to a neighborhood of the first-order stationary point at a rate of O(1/T). Experiments fine-tuning RoBERTa-Large on GLUE datasets show the algorithms outperform the state of the art.

Key Points
  • SeFoRA uses linear sketches to aggregate LoRA updates from clients with heterogeneous ranks, solving dimension mismatch and bilinear mismatch.
  • Convergence to a first-order stationary point is proven at O(1/T) for the rank-homogeneous variant (SeFoRA-Ho).
  • Outperforms state-of-the-art federated PEFT when fine-tuning RoBERTa-Large on GLUE benchmarks, with lower communication costs.

Why It Matters

Enables practical federated fine-tuning where each client chooses its own LoRA rank, removing a major coordination bottleneck.

📬 Get the top 10 AI stories daily