Relation-aware Graph Attention Model With Adaptive Self-adversarial Training

TL;DR

This paper introduces RelGNN, a relation-aware graph attention model with adaptive self-adversarial training, improving relationship prediction in heterogeneous graphs by effectively modeling edge semantics and reducing false negatives.

Contribution

The paper proposes a novel relation-aware graph attention model and a parameter-free adaptive self-adversarial negative sampling technique for better relationship prediction.

Findings

RelGNN outperforms existing models on benchmark datasets.

ASA negative sampling reduces false negatives and improves training quality.

The combined approach achieves state-of-the-art results in relationship prediction.

Abstract

This paper describes an end-to-end solution for the relationship prediction task in heterogeneous, multi-relational graphs. We particularly address two building blocks in the pipeline, namely heterogeneous graph representation learning and negative sampling. Existing message passing-based graph neural networks use edges either for graph traversal and/or selection of message encoding functions. Ignoring the edge semantics could have severe repercussions on the quality of embeddings, especially when dealing with two nodes having multiple relations. Furthermore, the expressivity of the learned representation depends on the quality of negative samples used during training. Although existing hard negative sampling techniques can identify challenging negative relationships for optimization, new techniques are required to control false negatives during training as false negatives could corrupt the learning process. To address these issues, first, we propose RelGNN -- a message passing-based heterogeneous graph attention model. In particular, RelGNN generates the states of different relations and leverages them along with the node states to weigh the messages. RelGNN also adopts a self-attention mechanism to balance the importance of attribute features and topological features for generating the final entity embeddings. Second, we introduce a parameter-free negative sampling technique -- adaptive self-adversarial (ASA) negative sampling. ASA reduces the false-negative rate by leveraging positive relationships to effectively guide the identification of true negative samples. Our experimental evaluation demonstrates that RelGNN optimized by ASA for relationship prediction improves state-of-the-art performance across established benchmarks as well as on a real industrial dataset.