Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning

Knowledge Graph (KG) reasoning, which aims to infer new facts from structured knowledge repositories, plays a vital role in Natural Language Processing (NLP) systems. Its effectiveness critically depends on constructing informative and contextually relevant reasoning paths. However, existing graph neural networks (GNNs) often adopt rigid, query-agnostic pathexploration strategies, limiting their ability to adapt to diverse linguistic contexts and semantic nuances. To address these limitations, we propose MoKGR, a mixture-of-experts framework that personalizes path exploration through two complementary components: (1) a mixture of length experts that adaptively selects and weights candidate path lengths according to query complexity, providing query-specific reasoning depth; and (2) a mixture of pruning experts that evaluates candidate paths from a complementary perspective, retaining the most informative paths for each query. Through comprehensive experiments on diverse benchmark, MoKGR demonstrates superior performance in both transductive and inductive settings, validating the effectiveness of personalized path exploration in KGs reasoning. 1 * Corresponding author 1 Code is available on https://github.com/EnjunDu/ MoKGR . (JACK, followed, ?) to find Chirs Evans naturally concludes within three hops. Conversely, addressing the query (JACK, watched, ?) to identify Avengers: Endgame might require exploration beyond three hops to capture critical relationships. These scenarios underscore the need for hop-level personalization, tailoring path exploration to query complexity to improve reasoning efficiency and accuracy.