An Adversarial Transfer Network for Knowledge Representation Learning

TL;DR

This paper introduces ATransN, an adversarial transfer network that enhances knowledge graph embeddings by transferring information from multiple source graphs without data leakage, improving completion performance across datasets.

Contribution

The paper proposes a novel adversarial transfer approach that leverages entity representations and adversarial adaptation to improve knowledge graph learning without requiring relation data.

Findings

ATransN outperforms baselines on three datasets.

The method improves embedding quality with multiple teachers.

Ablation shows consistent gains across settings.

Abstract

Knowledge representation learning has received a lot of attention in the past few years. The success of existing methods heavily relies on the quality of knowledge graphs. The entities with few triplets tend to be learned with less expressive power. Fortunately, there are many knowledge graphs constructed from various sources, the representations of which could contain much information. We propose an adversarial embedding transfer network ATransN, which transfers knowledge from one or more teacher knowledge graphs to a target one through an aligned entity set without explicit data leakage. Specifically, we add soft constraints on aligned entity pairs and neighbours to the existing knowledge representation learning methods. To handle the problem of possible distribution differences between teacher and target knowledge graphs, we introduce an adversarial adaption module. The discriminator of this module evaluates the degree of consistency between the embeddings of an aligned entity pair. The consistency score is then used as the weights of soft constraints. It is not necessary to acquire the relations and triplets in teacher knowledge graphs because we only utilize the entity representations. Knowledge graph completion results show that ATransN achieves better performance against baselines without transfer on three datasets, CN3l, WK3l, and DWY100k. The ablation study demonstrates that ATransN can bring steady and consistent improvement in different settings. The extension of combining other knowledge graph embedding algorithms and the extension with three teacher graphs display the promising generalization of the adversarial transfer network.