TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
This work addresses the need for foundation models in knowledge graphs, enabling zero-shot transfer across domains, though it appears incremental in improving expressiveness over existing methods.
The paper tackles the problem of zero-shot knowledge graph completion in unseen domains by introducing TRIX, a more expressive fully inductive model that outperforms state-of-the-art methods and large-context LLMs in entity and relation predictions.
Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an important capability towards the goal of having foundation models for knowledge graphs. In this work, we introduce a more expressive and capable fully inductive model, dubbed TRIX, which not only yields strictly more expressive triplet embeddings (head entity, relation, tail entity) compared to state-of-the-art methods, but also introduces a new capability: directly handling both entity and relation prediction tasks in inductive settings. Empirically, we show that TRIX outperforms the state-of-the-art fully inductive models in zero-shot entity and relation predictions in new domains, and outperforms large-context LLMs in out-of-domain predictions. The source code is available at https://github.com/yuchengz99/TRIX.