Tag
LE4Mob is an inductive, distance-aware, and general-purpose location embedding framework for enhancing human mobility modeling in tasks such as next location prediction and commuter flow generation.
This paper extends the evaluation of the SNAP-KG framework to heterophilous graphs, showing that homophily in at least one view is crucial for performance in streaming entity integration, highlighting a shared assumption in multi-view graph clustering methods.
SNAP-KG is a framework that enables efficient integration of streaming entities into knowledge graphs via multi-view clustering and inductive inference, reducing inference time and candidate search space for downstream tasks like entity resolution and link prediction.
This paper introduces CoDiffGRN, a co-evolutionary discrete diffusion framework for gene regulatory network inference, along with a new benchmark BEELINE-KGC for inductive evaluation. It achieves state-of-the-art performance in novel regulatory discovery.
This paper proposes AdaTKG, a method for temporal knowledge graph reasoning that uses adaptive memory to refine entity representations dynamically as new interactions occur, improving performance over static baselines.