Feature Aggregation with Latent Generative Replay for Federated Continual Learning of Socially Appropriate Robot Behaviours

TL;DR

This paper introduces FedRoot and FedLGR, novel federated learning strategies for social robot behavior adaptation, reducing resource use and mitigating forgetting in collaborative, real-world environments.

Contribution

It proposes FedRoot averaging for feature disentanglement and FedLGR for resource-efficient continual learning with pseudo-rehearsal in federated social robot training.

Findings

FedRoot reduces resource consumption significantly.

FedLGR outperforms existing methods in continual learning tasks.

Resource savings up to 86% CPU and 72% GPU usage.

Abstract

It is critical for robots to explore Federated Learning (FL) settings where several robots, deployed in parallel, can learn independently while also sharing their learning with each other. This collaborative learning in real-world environments requires social robots to adapt dynamically to changing and unpredictable situations and varying task settings. Our work contributes to addressing these challenges by exploring a simulated living room environment where robots need to learn the social appropriateness of their actions. First, we propose Federated Root (FedRoot) averaging, a novel weight aggregation strategy which disentangles feature learning across clients from individual task-based learning. Second, to adapt to challenging environments, we extend FedRoot to Federated Latent Generative Replay (FedLGR), a novel Federated Continual Learning (FCL) strategy that uses FedRoot-based weight aggregation and embeds each client with a generator model for pseudo-rehearsal of learnt feature embeddings to mitigate forgetting in a resource-efficient manner. Our results show that FedRoot-based methods offer competitive performance while also resulting in a sizeable reduction in resource consumption (up to 86% for CPU usage and up to 72% for GPU usage). Additionally, our results demonstrate that FedRoot-based FCL methods outperform other methods while also offering an efficient solution (up to 84% CPU and 92% GPU usage reduction), with FedLGR providing the best results across evaluations.