New Benchmark Tests Whether Trust Boundaries Hold Over Time in Receiver-Directed Federated Learning
A new arXiv paper introduces a long-horizon benchmark for receiver-directed federated learning, where each site draws a trust boundary and judges sources and model components on its own data.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-04 05:00 · arXiv cs.LG
Does the Trust Boundary Hold over Time? A Long-Horizon Benchmark for Receiver-Directed Federated Learning