2 papers
cs.LG2026
A Layer-wise Analysis of Supervised Fine-Tuning
Qinghua Zhao, Xueling Gong, Xinyu Chen +2
While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains el…
cs.LG2024
PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs
Shengwei Ji, Yujie Tian, Fei Liu +2
Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggreg…