MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering
This addresses memory efficiency for researchers and practitioners working with large-scale Knowledge Graphs in NLP, though it appears incremental as it builds on existing CP decomposition methods.
The authors tackled the memory cost issue of embedding large Knowledge Graphs by proposing MEKER, a memory-efficient model using a generalized CP decomposition that reduces training memory and achieves state-of-the-art comparable performance on link prediction and question answering tasks.
Knowledge Graphs (KGs) are symbolically structured storages of facts. The KG embedding contains concise data used in NLP tasks requiring implicit information about the real world. Furthermore, the size of KGs that may be useful in actual NLP assignments is enormous, and creating embedding over it has memory cost issues. We represent KG as a 3rd-order binary tensor and move beyond the standard CP decomposition by using a data-specific generalized version of it. The generalization of the standard CP-ALS algorithm allows obtaining optimization gradients without a backpropagation mechanism. It reduces the memory needed in training while providing computational benefits. We propose a MEKER, a memory-efficient KG embedding model, which yields SOTA-comparable performance on link prediction tasks and KG-based Question Answering.