Knowledge graph (KG) embedding methods which map entities and relations to unique embeddings in the KG have shown promising results on many reasoning tasks. However, the same embedding dimension for both dense entities and sparse entities will cause either over parameterization (sparse entities) or under fitting (dense entities). Normally, a large dimension is set to get better performance. Meanwhile, the inference time grows log-linearly with the number of entities for all entities are traversed and compared. Both the parameter and inference become challenges when working with huge amounts of entities. Thus, we propose PIE, a \textbf{p}arameter and \textbf{i}nference \textbf{e}fficient solution. Inspired from tensor decomposition methods, we find that decompose entity embedding matrix into low rank matrices can reduce more than half of the parameters while maintaining comparable performance. To accelerate model inference, we propose a self-supervised auxiliary task, which can be seen as fine-grained entity typing. By randomly masking and recovering entities' connected relations, the task learns the co-occurrence of entity and relations. Utilizing the fine grained typing, we can filter unrelated entities during inference and get targets with possibly sub-linear time requirement. Experiments on link prediction benchmarks demonstrate the proposed key capabilities. Moreover, we prove effectiveness of the proposed solution on the Open Graph Benchmark large scale challenge dataset WikiKG90Mv2 and achieve the state of the art performance.
翻译:用于映射实体和与KG中独特嵌入点的关系的知识嵌入方法( KG) 嵌入方法在很多推理任务上显示了有希望的结果。 但是, 对于密度大的实体和稀散的实体, 同样的嵌入维度将导致参数化( 粗体实体) 或不适当( 高级实体) 。 通常, 一个大维将获得更好的性能。 与此同时, 推算时间随着所有实体的实体的数量而增加日志- 线性记录时间, 并与之比较。 当与大量实体合作时, 参数和推论都成为挑战。 因此, 我们提议 PIE, 是一个纯度实体键入, 一个 textbf{ p} 计 和\ textbf{i} nference 的嵌入维度层面, 或引出参数的参数范围不小维值 。 我们发现, 将实体嵌入低级矩阵的拆分解, 可以在保持可比性业绩的同时, 加速模型推算出一个自我校准的辅助任务, 这可以被视为精度实体的键盘输入。 。 通过随机掩视和正在修正的模型, 校准的校正的校正的校准的校正的校正的校正的校正的校正的校正的校正的校正关系, 校正的校正的校正的校正。