2 papers
cs.LG2025
Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs
Zuxin Ma, Yunhe Cui, Yongbin Qin
Non-uniform structured network pruning methods can effectively reduce Large Language Model (LLM) size by eliminating redundant channels or layers, offering lower performance degrad…
cs.LG2025
CEGRL-TKGR: A Causal Enhanced Graph Representation Learning Framework for Temporal Knowledge Graph Reasoning
Jinze Sun, Yongpan Sheng, Lirong He +3
Temporal knowledge graph reasoning (TKGR) is increasingly gaining attention for its ability to extrapolate new events from historical data, thereby enriching the inherently incompl…