MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering [article]

Viktoriia Chekalina, Anton Razzhigaev, Albert Sayapin, Evgeny Frolov, Alexander Panchenko
2022 arXiv   pre-print
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
more » ... 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.
arXiv:2204.10629v2 fatcat:vbijfw6nkze3ne2iawfez2scd4