Convolutional 2D Knowledge Graph Embeddings
Convolutional 2D Knowledge Graph Embeddings
复制标题
DOI：
10.1609/aaai.v32i1.11573
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Tim Dettmers;Pasquale Minervini;Pontus Stenetorp;S. Riedel
中科院分区：
文献类型：
--
作者：
Tim Dettmers;Pasquale Minervini;Pontus Stenetorp;S. Riedel
知识图的链接预测是预测实体之间缺失的关系的任务。 - 在这项工作中，这可能会限制性能。与我们模型分析的分析相同的性能和R-GCN相同。此外，由于测试集中存在的训练集，WN18和FB15K数据集遭受了测试集泄漏的影响 - 但是，该问题的程度尚未量化发现这个问题是严重的：一个简单的基于规则的模型可以在WN18和FB15K上实现最新结果，以确保在数据集中评估模型，在这些模型中，仅利用逆关系就无法产生竞争性结果验证几个常用的数据集 - 在必要时衍生出鲁棒的变体。
Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs. However, these models learn less expressive features than deep, multi-layer models — which potentially limits performance. In this work we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets. We also show that the model is highly parameter efficient, yielding the same performance as DistMult and R-GCN with 8x and 17x fewer parameters. Analysis of our model suggests that it is particularly effective at modelling nodes with high indegree — which are common in highly-connected, complex knowledge graphs such as Freebase and YAGO3. In addition, it has been noted that the WN18 and FB15k datasets suffer from test set leakage, due to inverse relations from the training set being present in the test set — however, the extent of this issue has so far not been quantified. We find this problem to be severe: a simple rule-based model can achieve state-of-the-art results on both WN18 and FB15k. To ensure that models are evaluated on datasets where simply exploiting inverse relations cannot yield competitive results, we investigate and validate several commonly used datasets — deriving robust variants where necessary. We then perform experiments on these robust datasets for our own and several previously proposed models, and find that ConvE achieves state-of-the-art Mean Reciprocal Rank across all datasets.