VN Network: Embedding Newly Emerging Entities with Virtual Neighbors
This work addresses the challenge of efficiently embedding unseen entities in knowledge graphs, which is crucial for applications like recommendation systems and semantic search, though it is incremental as it builds on existing graph neural network methods.
The paper tackles the problem of embedding newly emerging entities in knowledge graphs by proposing the Virtual Neighbor (VN) network, which uses virtual neighbors inferred by rules and iterative learning to address neighbor sparsity and capture distant information, resulting in significant outperformance over state-of-the-art baselines on knowledge graph completion tasks.
Embedding entities and relations into continuous vector spaces has attracted a surge of interest in recent years. Most embedding methods assume that all test entities are available during training, which makes it time-consuming to retrain embeddings for newly emerging entities. To address this issue, recent works apply the graph neural network on the existing neighbors of the unseen entities. In this paper, we propose a novel framework, namely Virtual Neighbor (VN) network, to address three key challenges. Firstly, to reduce the neighbor sparsity problem, we introduce the concept of the virtual neighbors inferred by rules. And we assign soft labels to these neighbors by solving a rule-constrained problem, rather than simply regarding them as unquestionably true. Secondly, many existing methods only use one-hop or two-hop neighbors for aggregation and ignore the distant information that may be helpful. Instead, we identify both logic and symmetric path rules to capture complex patterns. Finally, instead of one-time injection of rules, we employ an iterative learning scheme between the embedding method and virtual neighbor prediction to capture the interactions within. Experimental results on two knowledge graph completion tasks demonstrate that our VN network significantly outperforms state-of-the-art baselines. Furthermore, results on Subject/Object-R show that our proposed VN network is highly robust to the neighbor sparsity problem.