Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version)

Shuang Liang, Yang Hua, Linshan Jiang, Peishen Yan, Tao Song, Bin Yao, Haibing Guan

TL;DR

SettleFL is presented, a trustless and scalable reward settlement protocol designed to minimize total economic friction by offering a family of two interoperable protocols that allows the protocol to flexibly adapt to varying latency and cost constraints while enforcing rational robustness without trusted coordination.

Abstract

In open Federated Learning (FL) environments where no central authority exists, ensuring collaboration fairness relies on decentralized reward settlement, yet the prohibitive cost of permissionless blockchains directly clashes with the high-frequency, iterative nature of model training. Existing solutions either compromise decentralization or suffer from scalability bottlenecks due to linear on-chain costs. To address this, we present SettleFL, a trustless and scalable reward settlement protocol designed to minimize total economic friction by offering a family of two interoperable protocols. Leveraging a shared domain-specific circuit architecture, SettleFL offers two interoperable strategies: (1) a Commit-and-Challenge variant that minimizes on-chain costs via optimistic execution and dispute-driven arbitration, and (2) a Commit-with-Proof variant that guarantees instant finality through per-round validity proofs. This design allows the protocol to flexibly adapt to varying latency and cost constraints while enforcing rational robustness without trusted coordination. We conduct extensive experiments combining real FL workloads and controlled simulations. Results show that SettleFL remains practical when scaling to 800 participants, achieving substantially lower gas cost.

SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version)

TL;DR

SettleFL is presented, a trustless and scalable reward settlement protocol designed to minimize total economic friction by offering a family of two interoperable protocols that allows the protocol to flexibly adapt to varying latency and cost constraints while enforcing rational robustness without trusted coordination.

Abstract

In open Federated Learning (FL) environments where no central authority exists, ensuring collaboration fairness relies on decentralized reward settlement, yet the prohibitive cost of permissionless blockchains directly clashes with the high-frequency, iterative nature of model training. Existing solutions either compromise decentralization or suffer from scalability bottlenecks due to linear on-chain costs. To address this, we present SettleFL, a trustless and scalable reward settlement protocol designed to minimize total economic friction by offering a family of two interoperable protocols. Leveraging a shared domain-specific circuit architecture, SettleFL offers two interoperable strategies: (1) a Commit-and-Challenge variant that minimizes on-chain costs via optimistic execution and dispute-driven arbitration, and (2) a Commit-with-Proof variant that guarantees instant finality through per-round validity proofs. This design allows the protocol to flexibly adapt to varying latency and cost constraints while enforcing rational robustness without trusted coordination. We conduct extensive experiments combining real FL workloads and controlled simulations. Results show that SettleFL remains practical when scaling to 800 participants, achieving substantially lower gas cost.
Paper Structure (64 sections, 1 theorem, 9 equations, 13 figures, 3 tables, 3 algorithms)

This paper contains 64 sections, 1 theorem, 9 equations, 13 figures, 3 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Preliminary
  3. Blockchain-based Federated Learning
  4. Anchored Finality.
  5. Interaction.
  6. Rollup Mechanisms.
  7. SNARKs
  8. System Overview
  9. System Model
  10. Threat Model
  11. Problem Formulation
  12. Solution Overview
  13. Boundary Strategies.
  14. The Proposed Solutions.
  15. Settlement Timeline.
  16. ...and 49 more sections

Key Result

Theorem 1

If all players are rational and protocol parameters are set properly, then the strategy profile $(s_{\mathcal{A}\xspace}^{\text{honest}}, s_{P_1}^{\text{honest}}, \dots, s_{P_N}^{\text{honest}})$ forms a Nash equilibrium of $\mathcal{G}$.

Figures (13)

  • Figure 1: Overview of SettleFL protocol family. Our protocol resolves the conflict between costly on-chain execution and high-frequency FL updates. It navigates the scalability-finality trade-off through two variants: Commit-and-Challenge for minimal cost, and Commit-with-Proof for instant finality. A shared SNARK architecture flexibly enforces correctness by either guaranteeing validity upfront or resolving disputes with minimal on-chain overhead.
  • Figure 2: Landscape of Settlement Strategies. Unlike the active baselines L2FL aliefFLB22023, StateFL iacobanStateFL2024, and BCFL xuBAFL2021 which require user participation, SettleFL enables passive interaction via its two variants, $\textsf{SettleFL-CC}$ (CC) and $\textsf{SettleFL-CP}$ (CP). Notably, if anchored finality is compromised to the windowed stage, the protocol essentially degrades to an $n$-round batched CC or CP.
  • Figure 3: Timeline Analysis of Latency. By synchronizing settlement with the aggregation cycle, SettleFL eliminates extrinsic delays, bounding latency to the theoretical minimum.
  • Figure 4: System architecture overview. Shared cryptographic primitives underpin the architecture, enabling specialized modules to enforce distinct security assumptions.
  • Figure 5: System Workflow. tx: on-chain transaction; event: smart contract event; peer: off-chain peer communication.
  • ...and 8 more figures

Theorems & Definitions (4)

  • Definition 1: BCFL
  • Definition 2: Total Economic Friction
  • Definition 3: Incentive Compatibility
  • Theorem 1: Nash Equilibrium under Rationality