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

Source: [Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learning](<https://www.sota2.com/research/paper/69fc1c945497b3b670c88567>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-08T05:00:14.135Z

Authors: Michael Lanier, Luise Ge, Sastry Kompella, Yevgeniy Vorobeychik

Published: 2026-05-06T15:07:40.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on EuroSAT geographic (50 regions) (test)](<https://www.sota2.com/research/sota/image-classification-on-eurosat-geographic-50-regions-test.md>): Image Classification; EuroSAT geographic (50 regions) (test); Accuracy: 96.7.

- [Image Classification on CIFAR-100 (test) (Accuracy and Throughput)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-accuracy-and-throughput.md>): Image Classification; CIFAR-100 (test); Accuracy: 61.5.

- [Image Classification on CIFAR-10 (test) (Accuracy and Sparsity)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-and-sparsity.md>): Image Classification; CIFAR-10 (test); Accuracy: 86.5.

- [Image Classification on CIFAR-10 (Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy.md>): Image Classification; CIFAR-10; Accuracy: 80.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.05009>)

[PDF](<https://arxiv.org/pdf/2605.05009.pdf>)