# Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learning

arXiv: https://arxiv.org/abs/2605.05009 · HTML: https://mlsanity.com/paper/2605.05009/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Personalized Federated Learning with First Order Model Optimization](https://mlsanity.com/paper/2012.08565/) (2020)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data](https://mlsanity.com/paper/2008.06180/) (2020)
- [Personalized Federated Learning through Local Memorization](https://mlsanity.com/paper/2111.09360/) (2021)
- [Test-Time Robust Personalization for Federated Learning](https://mlsanity.com/paper/2205.10920/) (2022)
- [Adaptive Test-Time Personalization for Federated Learning](https://mlsanity.com/paper/2310.18816/) (2023)
- [Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors](https://mlsanity.com/paper/2405.11525/) (2024)
- [Revisiting Ensembling in One-Shot Federated Learning](https://mlsanity.com/paper/2411.07182/) (2024)
- [Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning](https://mlsanity.com/paper/2304.04326/) (2023)
- [FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learning](https://mlsanity.com/paper/2410.14075/) (2024)
- [Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving](https://mlsanity.com/paper/2603.02214/) (2026)

## Abstract (arXiv)

Many decentralized distillation methods are designed around training-time coordination, yet deploy each node in isolation even when more capable neighbors remain available at inference time. This is an incomplete objective for settings such as IoT, where devices are heterogeneous, data is scarce and skewed, and a node's strongest neighbors may far exceed its own local capacity. We study how nodes should train so that their predictions compose well at deployment, and how each node should learn whom to trust. Under a server-free, model-agnostic protocol where nodes exchange only queries and soft predictions, we propose Learned Neighbor Trust (LNTrust) wherein each node learns a compact trust function over its neighborhood from local validation evidence. This trust function gates auxiliary distillation during training and defines a deployment ensemble at inference, so that collaboration learned during training transfers directly to deployment. Across datasets and topologies, LNTrust improves deployed accuracy over the strongest output-only baseline by large margins while using significantly less communication than previous methods.