TRIX提升知识图谱零样本迁移能力，可同时预测实体与关系。
TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
- 采用更表达力的三元组嵌入方法，增强模型对新领域的适应性。
- 在未见领域上，实体与关系预测均优于现有先进模型。
- 适合需要跨域推理的知识图谱应用，尤其适用于无标注数据场景。
全归纳式知识图谱模型可在多个领域训练后，对未见的新领域实现零样本知识图谱补全，这是迈向知识图谱基础模型的重要一步。本文提出更具表达力和能力的全归纳模型TRIX，不仅在三元组嵌入（头实体、关系、尾实体）上比现有最优方法更具表达力，还首次实现直接处理归纳设置下的实体与关系预测任务。实验表明，TRIX在新领域上的零样本实体与关系预测性能超越当前最先进全归纳模型，并在跨域预测中优于大上下文大语言模型。代码已开源：https://github.com/yuchengz99/TRIX。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。