Hypernetwork Knowledge Graph Embeddings
This work addresses the challenge of improving interpretability and performance in knowledge graph completion for applications like recommendation systems, though it is incremental as it builds on existing factorization models.
The paper tackles the problem of link prediction in incomplete knowledge graphs by proposing a hypernetwork architecture that generates relation-specific convolutional filters, which outperforms the previous state-of-the-art ConvE method across standard datasets.
Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness. Inferring missing relations (links) between entities (nodes) is the task of link prediction. A recent state-of-the-art approach to link prediction, ConvE, implements a convolutional neural network to extract features from concatenated subject and relation vectors. Whilst results are impressive, the method is unintuitive and poorly understood. We propose a hypernetwork architecture that generates simplified relation-specific convolutional filters that (i) outperforms ConvE and all previous approaches across standard datasets; and (ii) can be framed as tensor factorization and thus set within a well established family of factorization models for link prediction. We thus demonstrate that convolution simply offers a convenient computational means of introducing sparsity and parameter tying to find an effective trade-off between non-linear expressiveness and the number of parameters to learn.