# Learning from Heterogeneous Data Based on Social Interactions over Graphs

arXiv: https://arxiv.org/abs/2112.09483 · HTML: https://mlsanity.com/paper/2112.09483/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 45 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Norm-Based Capacity Control in Neural Networks](https://mlsanity.com/paper/1503.00036/) (2015)
- [Fast Convergence Rates for Distributed Non-Bayesian Learning](https://mlsanity.com/paper/1508.05161/) (2015)
- [Social Learning and Distributed Hypothesis Testing](https://mlsanity.com/paper/1410.4307/) (2014)
- [Social Learning over Weakly-Connected Graphs](https://mlsanity.com/paper/1609.03703/) (2016)
- [Non-Bayesian Social Learning with Uncertain Models](https://mlsanity.com/paper/1909.09228/) (2019)
- [Interplay between Topology and Social Learning over Weak Graphs](https://mlsanity.com/paper/1910.13905/) (2019)
- [A General Framework for Distributed Inference with Uncertain Models](https://mlsanity.com/paper/2011.10669/) (2020)
- [Adaptation in Online Social Learning](https://mlsanity.com/paper/2003.01948/) (2020)
- [Network Classifiers Based on Social Learning](https://mlsanity.com/paper/2010.12306/) (2020)

## Built on by (most cited first, 4 of 4)

- [On the Fusion Strategies for Federated Decision Making](https://mlsanity.com/paper/2303.06109/) (2023)
- [Non-Asymptotic Performance of Social Machine Learning Under Limited Data](https://mlsanity.com/paper/2306.09397/) (2023)
- [Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments](https://mlsanity.com/paper/2407.04974/) (2024)
- [Doubly Adaptive Social Learning](https://mlsanity.com/paper/2504.17370/) (2025)

## Abstract (arXiv)

This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions and arising from possibly different distributions. In the context of social learning, several useful strategies have been developed, which solve decision making problems through local cooperation across distributed agents and allow them to learn from streaming data. However, traditional social learning strategies rely on the fundamental assumption that each agent has significant prior knowledge of the underlying distribution of the observations. In this work we overcome this issue by introducing a machine learning framework that exploits social interactions over a graph, leading to a fully data-driven solution to the distributed classification problem. In the proposed social machine learning (SML) strategy, two phases are present: in the training phase, classifiers are independently trained to generate a belief over a set of hypotheses using a finite number of training samples; in the prediction phase, classifiers evaluate streaming unlabeled observations and share their instantaneous beliefs with neighboring classifiers. We show that the SML strategy enables the agents to learn consistently under this highly-heterogeneous setting and allows the network to continue learning even during the prediction phase when it is deciding on unlabeled samples. The prediction decisions are used to continually improve performance thereafter in a manner that is markedly different from most existing static classification schemes where, following training, the decisions on unlabeled data are not re-used to improve future performance.