5 citations · 10 across the 11 of their papers we have counts for
3 papers · 1 filter
GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs
Liangwei Yang, Jing Ma, Jianguo Zhang +11
Graph neural networks (GNNs) on text--attributed graphs (TAGs) typically encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear nei…
xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
Cheng Qian, Zuxin Liu, Shirley Kokane +10
Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle…
Improving Knowledge Distillation in Transfer Learning with Layer-wise Learning Rates
Shirley Kokane, Mostofa Rafid Uddin, Min Xu
Transfer learning methods start performing poorly when the complexity of the learning task is increased. Most of these methods calculate the cumulative differences of all the match…