Aligning Knowledge Graphs Provided by Humans and Generated from Neural Networks in Specific Tasks

arXiv:2404.16884v1 Announce Type: new
Abstract: This paper develops an innovative method that enables neural networks to generate and utilize knowledge graphs, which describe their concept-level knowledge and optimize network parameters through alignment with human-provided knowledge. This research addresses a gap where traditionally, network-generated knowledge has been limited to applications in downstream symbolic analysis or enhancing network transparency. By integrating a novel autoencoder design with the Vector Symbolic Architecture (VSA), we have introduced auxiliary tasks that support end-to-end training. Our approach …

abstract alignment arxiv concept cs.ai cs.lg gap generate generated graphs human humans knowledge knowledge graphs network networks neural networks paper parameters research specific tasks tasks through type