Synapse: 通过类型化编目工件实现联邦工具路由
Synapse: Federated Tool Routing via Typed Compendium Artifacts
AI总结:
本文提出了一种名为Synapse的联邦工具路由编目系统,通过类型化联邦工件实现跨客户端的联邦学习,解决了在异构LLM和无共享数据的情况下,如何实现隐私保护、冲突解决和跨架构迁移的问题。
摘要:
在联邦学习中,协作单位决定了可以表达哪些保证。像权重、提示、原始示例这样的扁平单位没有类型签名,无法为隐私、冲突解决或跨模型迁移提供明确的操作。我们提出了类型化的联邦工件:经过模式验证的对象,其声明的字段结构使得每字段差分隐私、模式感知合并和跨架构迁移成为第一类操作,而非启发式近似。我们将此实现为SYNAPSE,一个用于在具有冻结、异构LLM且无共享数据或权重的客户端之间进行联邦工具路由的编目系统,这种设置下扁平单位无法处理,除非泄露梯度或丢弃结构。该编目系统允许带有字段级冲突解决的类型化合并运算符,对数值元数据提供形式化的DP保证,并在五个分布上经验性地刻画了条件检索失真和路由稳定性结果,包括一个收缩前提失败的分布。一个单一的编目系统在四个LLM家族(LLaMA 3.18B、LLaMA 3.2-3B、Mistral 7B、GPT 4o)之间转移,损失约2 pt,这种能力重量共享联邦无法在无架构匹配的情况下提供。
英文摘要:
The unit of collaboration in federated learning determines what guarantees are even expressible. Flat units like weights, prompts, raw examples, carry no type signature on which privacy, conflict resolution, or cross-model transfer can dispatch as well-defined operations. We propose typed federated artifacts: schema validated objects whose declared field structure makes per field differential privacy, schema aware merging, and cross architectural transfer first-class operations rather than heuristic approximations. We instantiate this as SYNAPSE, a compendium for federated tool routing across clients with frozen, heterogeneous LLMs and no shared data or weights which is a setting flat units cannot handle without either leaking gradients or discarding structure. The compendium admits a typed merge operator with field wise conflict resolution, a formal DP guarantee on numeric metadata, and conditional retrieval distortion and routing-stability results empirically characterized on five distributions, including one where the contraction premise fails. A single compendium transfers across four LLM families (LLaMA 3.18B,LLaMA 3.2-3B, Mistral 7B, GPT 4o) with approximately 2 pt loss, a capability weight-sharing federation cannot provide without architectural matching.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。