Shenghao Gao

2 accepted papers

2026

Forest-Based Graph Learning for Semi-Supervised Node Classification

Jin Li, Shenghao Gao, Kaichen Zhang, Xinlong Chen, Ying Sun, Hui Xiong

ICLR 2026poster

Existing Graph Neural Networks usually learn long-distance knowledge via stacked layers or global attention, but struggle to balance cost-effectiveness and global receptive field. In this work, we break the dilemma by proposing a novel forest-based graph learning (FGL) paradigm that enables efficien…

Cited by 0 Source ↗Scholar ↗

2026

Low-cost Full Fine-tuning: Learning What to Update for LLMs

Li, Yaming Guo, Shenghao Gao, Xinlong Chen, Zuhao Xu, Ying Sun +2

ICML 2026poster

While Large language models (LLMs) have strong abilities, they generally rely on fine-tuning to supplement downstream task-specific knowledge. Due to the prohibitive memory overhead of full fine-tuning (FT), existing parameter-efficient fine-tuning techniques, e.g., LoRA and Adapters, update paramet…

Cited by 0 Source ↗Scholar ↗