Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer

TL;DR

Bridged-GNN introduces a novel knowledge transfer framework using graph neural networks that enhances learning from limited or low-quality data by constructing a Bridged-Graph for targeted knowledge sharing.

Contribution

The paper proposes a new paradigm called Knowledge Bridge Learning (KBL) that leverages GNNs for robust, sample-wise knowledge transfer without strong assumptions, improving generalization in data-scarce scenarios.

Findings

Significant performance improvements over SOTA methods.

Effective in both relational and non-relational data scenarios.

Robust to noise in source data.

Abstract

The data-hungry problem, characterized by insufficiency and low-quality of data, poses obstacles for deep learning models. Transfer learning has been a feasible way to transfer knowledge from high-quality external data of source domains to limited data of target domains, which follows a domain-level knowledge transfer to learn a shared posterior distribution. However, they are usually built on strong assumptions, e.g., the domain invariant posterior distribution, which is usually unsatisfied and may introduce noises, resulting in poor generalization ability on target domains. Inspired by Graph Neural Networks (GNNs) that aggregate information from neighboring nodes, we redefine the paradigm as learning a knowledge-enhanced posterior distribution for target domains, namely Knowledge Bridge Learning (KBL). KBL first learns the scope of knowledge transfer by constructing a Bridged-Graph that connects knowledgeable samples to each target sample and then performs sample-wise knowledge transfer via GNNs.KBL is free from strong assumptions and is robust to noises in the source data. Guided by KBL, we propose the Bridged-GNN} including an Adaptive Knowledge Retrieval module to build Bridged-Graph and a Graph Knowledge Transfer module. Comprehensive experiments on both un-relational and relational data-hungry scenarios demonstrate the significant improvements of Bridged-GNN compared with SOTA methods