A shallow neural model for relation prediction
This work addresses the problem of incomplete knowledge graphs for AI applications, offering an efficient and accurate solution, though it is incremental as it builds on existing relation prediction approaches.
The paper tackles knowledge graph completion by predicting missing relations between entities, framing it as multi-label classification and proposing a shallow neural model (SHALLOM) that outperforms state-of-the-art methods by up to 3% on FB15K-237 and 8% on WN18RR with training times under 8 minutes.
Knowledge graph completion refers to predicting missing triples. Most approaches achieve this goal by predicting entities, given an entity and a relation. We predict missing triples via the relation prediction. To this end, we frame the relation prediction problem as a multi-label classification problem and propose a shallow neural model (SHALLOM) that accurately infers missing relations from entities. SHALLOM is analogous to C-BOW as both approaches predict a central token (p) given surrounding tokens ((s,o)). Our experiments indicate that SHALLOM outperforms state-of-the-art approaches on the FB15K-237 and WN18RR with margins of up to $3\%$ and $8\%$ (absolute), respectively, while requiring a maximum training time of 8 minutes on these datasets. We ensure the reproducibility of our results by providing an open-source implementation including training and evaluation scripts at {\url{https://github.com/dice-group/Shallom}.}