# FedStrategist: A Meta-Learning Framework for Adaptive and Robust Aggregation in Federated Learning

arXiv: https://arxiv.org/abs/2507.14322 · HTML: https://mlsanity.com/paper/2507.14322/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 75 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## Builds on (most cited first, 30 of 36)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [Heterogeneous Federated Learning: State-of-the-art and Research Challenges](https://mlsanity.com/paper/2307.10616/) (2023)
- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [Free-riders in Federated Learning: Attacks and Defenses](https://mlsanity.com/paper/1911.12560/) (2019)
- [A Survey on Heterogeneous Federated Learning](https://mlsanity.com/paper/2210.04505/) (2022)
- [An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning](https://mlsanity.com/paper/2302.07173/) (2023)
- [FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors](https://mlsanity.com/paper/2503.15842/) (2025)
- [Robust Federated Learning with Attack-Adaptive Aggregation](https://mlsanity.com/paper/2102.05257/) (2021)
- [A Survey of Distributed Consensus Protocols for Blockchain Networks](https://mlsanity.com/paper/1904.04098/) (2019)
- [Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation](https://mlsanity.com/paper/2210.06894/) (2022)
- [Reputation as a Solution to Cooperation Collapse in LLM-based MASs](https://mlsanity.com/paper/2505.05029/) (2025)
- [Security Analysis Methods on Ethereum Smart Contract Vulnerabilities: A Survey](https://mlsanity.com/paper/1908.08605/) (2019)
- [Advancing Blockchain-based Federated Learning through Verifiable Off-chain Computations](https://mlsanity.com/paper/2206.11641/) (2022)
- [Securing Federated Learning against Overwhelming Collusive Attackers](https://mlsanity.com/paper/2209.14093/) (2022)
- [Blockchain-Enabled Federated Learning: A Reference Architecture Design, Implementation, and Verification](https://mlsanity.com/paper/2306.10841/) (2023)
- [Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspective](https://mlsanity.com/paper/2405.20431/) (2024)
- [MeritRank: Sybil Tolerant Reputation for Merit-based Tokenomics](https://mlsanity.com/paper/2207.09950/) (2022)
- [Federated Learning with Dual Attention for Robust Modulation Classification under Attacks](https://mlsanity.com/paper/2401.11039/) (2024)
- [DID-eFed: Facilitating Federated Learning as a Service with Decentralized Identities](https://mlsanity.com/paper/2105.08671/) (2021)
- [Cryptoeconomics and Tokenomics as Economics: A Survey with Opinions](https://mlsanity.com/paper/2407.15715/) (2024)
- [DMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differences](https://mlsanity.com/paper/2502.04771/) (2025)
- [FedCostAware: Enabling Cost-Aware Federated Learning on the Cloud](https://mlsanity.com/paper/2505.21727/) (2025)
- [Engineering Token Economy with System Modeling](https://mlsanity.com/paper/1907.00899/) (2019)

## Abstract (arXiv)

Federated Learning (FL) offers a paradigm for privacy-preserving collaborative AI, but its decentralized nature creates significant vulnerabilities to model poisoning attacks. While numerous static defenses exist, their effectiveness is highly context-dependent, often failing against adaptive adversaries or in heterogeneous data environments. This paper introduces FedStrategist, a novel meta-learning framework that reframes robust aggregation as a real-time, cost-aware control problem. We design a lightweight contextual bandit agent that dynamically selects the optimal aggregation rule from an arsenal of defenses based on real-time diagnostic metrics. Through comprehensive experiments, we demonstrate that no single static rule is universally optimal. We show that our adaptive agent successfully learns superior policies across diverse scenarios, including a ``Krum-favorable" environment and against a sophisticated "stealth" adversary designed to neutralize specific diagnostic signals. Critically, we analyze the paradoxical scenario where a non-robust baseline achieves high but compromised accuracy, and demonstrate that our agent learns a conservative policy to prioritize model integrity. Furthermore, we prove the agent's policy is controllable via a single "risk tolerance" parameter, allowing practitioners to explicitly manage the trade-off between performance and security. Our work provides a new, practical, and analyzable approach to creating resilient and intelligent decentralized AI systems.