Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation
For federated learning practitioners, FedNL addresses Non-IID client data by learning optimization rules rather than static models, but the gains are incremental over existing methods.
FedNL reformulates federated learning as a three-level nested optimization system, enabling zero-shot test-time adaptation via Titans-based linear attention. It achieves competitive short-context reasoning and improved long-context retrieval with constant inference memory.
We rethink Federated Learning (FL) from a nested learning perspective, framing the core challenge as how to collaboratively learn optimization rules, not just static models, to tackle Non-IID client data. To address this, we propose Federated Nested Learning (FedNL), a novel framework that reformulates FL as a three-level nested optimization system. FedNL embeds Titans-based linear attention into FL, enabling clients to perform lightweight, zero-shot test-time adaptation by treating a delta rule as an online gradient step. Experiments on Non-IID MMLU and long-context benchmarks show that FedNL achieves competitive performance in short-context reasoning, enhances the performance of long-context retrieval and streaming Cross-Entropy, and maintains constant inference memory.