Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces the Drift-Aware Temporal Graph Rewiring (DATGR) framework, which addresses the challenge of semantic drift in biomedical language by dynamically updating co-occurrence edges instead of retraining static embeddings. By employing a logistic update rule for edge weights, DATGR enhances retrieval and knowledge discovery tasks, achieving a significant mean AUROC improvement of 0.066 over static baselines while maintaining comparable precision. The results highlight the effectiveness of edge-level adaptation in capturing temporal semantic changes in rapidly evolving biomedical text, offering a computationally efficient solution for semantic modeling.
Edge-level adaptation can significantly improve link-prediction recall in biomedical text without sacrificing precision, showcasing a novel approach to semantic drift.
Biomedical language evolves rapidly as new discoveries emerge, causing traditional text models to lose semantic fidelity over time. Static embeddings and co-occurrence graphs cannot capture such evolution, leading to performance degradation in retrieval and knowledge discovery tasks. This paper introduces a Drift-Aware Temporal Graph Rewiring (DATGR) framework that models concept evolution by dynamically updating co-occurrence edges based on estimated semantic drift. Instead of retraining embeddings for each time slice, DATGR performs lightweight, feedback-driven rewiring using a logistic update rule applied to edge weights. Evaluated on the Biomedical Multi-Relation Corpus (BIOMRC), the method achieved a mean Area Under the Receiver Operating Characteristic (AUROC) improvement of approximately 0.066 absolute difference (0.699 vs. 0.633) over a static baseline. Area Under the Precision-Recall Curve (AUPRC) remained comparable (0.738 vs. 0.744), showing that drift-aware adaptation enhances link-prediction recall without a loss in precision. These results demonstrate that edge-level adaptation effectively captures temporal semantic change in evolving biomedical text while remaining computationally efficient and interpretable.