Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation

TL;DR

This paper introduces FedKD, a knowledge distillation method designed to compress high-dimensional federated knowledge graph embeddings into low-dimensional models, improving communication efficiency while maintaining performance.

Contribution

FedKD is a novel, lightweight knowledge distillation approach tailored for federated knowledge graph embedding, reducing model size and communication costs.

Findings

FedKD effectively compresses embeddings with minimal performance loss.

Experiments show improved communication efficiency in federated settings.

FedKD outperforms baseline methods in multiple datasets.

Abstract

Federated Knowledge Graph Embedding (FKGE) aims to facilitate collaborative learning of entity and relation embeddings from distributed Knowledge Graphs (KGs) across multiple clients, while preserving data privacy. Training FKGE models with higher dimensions is typically favored due to their potential for achieving superior performance. However, high-dimensional embeddings present significant challenges in terms of storage resource and inference speed. Unlike traditional KG embedding methods, FKGE involves multiple client-server communication rounds, where communication efficiency is critical. Existing embedding compression methods for traditional KGs may not be directly applicable to FKGE as they often require multiple model trainings which potentially incur substantial communication costs. In this paper, we propose a light-weight component based on Knowledge Distillation (KD) which is titled FedKD and tailored specifically for FKGE methods. During client-side local training, FedKD facilitates the low-dimensional student model to mimic the score distribution of triples from the high-dimensional teacher model using KL divergence loss. Unlike traditional KD way, FedKD adaptively learns a temperature to scale the score of positive triples and separately adjusts the scores of corresponding negative triples using a predefined temperature, thereby mitigating teacher over-confidence issue. Furthermore, we dynamically adjust the weight of KD loss to optimize the training process. Extensive experiments on three datasets support the effectiveness of FedKD.