Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables
Researchers have developed a new framework called Neural Scalable Symbolic Search (NS3) to address the challenge of complex query answering over knowledge graphs. Existing methods struggle with queries involving multiple free variables, often relying on less accurate marginal rankings. NS3 approximates joint rankings by first answering marginalized sub-queries, then merging variables into pruned domains controlled by a dynamic budget, and progressively reducing the query complexity. AI
IMPACT Introduces a novel approach for more accurate joint ranking in complex knowledge graph queries, potentially improving AI reasoning capabilities.