GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs
Graph neural networks (GNNs) on text-attributed graphs (TAGs) typically encode node texts with pretrained language models (PLMs) and propagate the resulting embeddings through linear neighborhood aggregation. Yet PLM representation spaces are geometrically structured, so linear aggregation can distort semantic geometry...
Liangwei Yang, Jing Ma, Jianguo Zhang et al.
· ACM International Conference... · 1 citation