Edge-cloud Collaborative Learning with Federated and Centralized Features
This work addresses the problem of inefficient knowledge utilization in federated learning for scenarios like recommender systems, offering a novel approach that is incremental in combining edge and cloud features.
The paper tackles the limitation of federated learning where only edge data is used, by proposing a framework for edge-cloud collaborative learning that enables bi-directional knowledge transfer, resulting in enhanced personalization and reduced communication burdens as demonstrated on public and industrial datasets.
Federated learning (FL) is a popular way of edge computing that doesn't compromise users' privacy. Current FL paradigms assume that data only resides on the edge, while cloud servers only perform model averaging. However, in real-life situations such as recommender systems, the cloud server has the ability to store historical and interactive features. In this paper, our proposed Edge-Cloud Collaborative Knowledge Transfer Framework (ECCT) bridges the gap between the edge and cloud, enabling bi-directional knowledge transfer between both, sharing feature embeddings and prediction logits. ECCT consolidates various benefits, including enhancing personalization, enabling model heterogeneity, tolerating training asynchronization, and relieving communication burdens. Extensive experiments on public and industrial datasets demonstrate ECCT's effectiveness and potential for use in academia and industry.