Energy-Efficient and Federated Meta-Learning via Projected Stochastic Gradient Ascent
This work addresses energy efficiency in federated meta-learning, which is incremental as it builds on existing methods by reducing computational and communication costs.
The paper tackles the problem of learning a meta-model for fast adaptation to new tasks in a distributed setting while minimizing energy consumption, achieving high performance with significantly less energy compared to state-of-the-art methods like MAML and iMAML in experiments on sinusoid regression and image classification.
In this paper, we propose an energy-efficient federated meta-learning framework. The objective is to enable learning a meta-model that can be fine-tuned to a new task with a few number of samples in a distributed setting and at low computation and communication energy consumption. We assume that each task is owned by a separate agent, so a limited number of tasks is used to train a meta-model. Assuming each task was trained offline on the agent's local data, we propose a lightweight algorithm that starts from the local models of all agents, and in a backward manner using projected stochastic gradient ascent (P-SGA) finds a meta-model. The proposed method avoids complex computations such as computing hessian, double looping, and matrix inversion, while achieving high performance at significantly less energy consumption compared to the state-of-the-art methods such as MAML and iMAML on conducted experiments for sinusoid regression and image classification tasks.