TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction
This work addresses a bottleneck in knowledge graph embedding for researchers and practitioners, offering an incremental improvement over prior methods.
The paper tackles the suboptimal performance of knowledge graph completion due to hyper-ellipsoid restrictions in existing methods by proposing TranSHER, which uses relation-specific translations to relax these constraints, achieving significant performance improvements on link prediction across various datasets.
Knowledge graph embedding methods are important for the knowledge graph completion (or link prediction) task. One existing efficient method, PairRE, leverages two separate vectors to model complex relations (i.e., 1-to-N, N-to-1, and N-to-N) in knowledge graphs. However, such a method strictly restricts entities on the hyper-ellipsoid surfaces which limits the optimization of entity distribution, leading to suboptimal performance of knowledge graph completion. To address this issue, we propose a novel score function TranSHER, which leverages relation-specific translations between head and tail entities to relax the constraint of hyper-ellipsoid restrictions. By introducing an intuitive and simple relation-specific translation, TranSHER can provide more direct guidance on optimization and capture more semantic characteristics of entities with complex relations. Experimental results show that TranSHER achieves significant performance improvements on link prediction and generalizes well to datasets in different domains and scales. Our codes are public available at https://github.com/yizhilll/TranSHER.