Shichang Zhang

Motif-Driven Contrastive Learning of Graph Representations

2020 · arXiv (Cornell University)

Pre-training Graph Neural Networks (GNN) via self-supervised contrastive learning has recently drawn lots of attention. However, most existing works focus on node-level contrastive learning, which cannot capture global graph structure. The key challenge to conducting …

Parameter-Efficient Tuning Large Language Models for Graph Representation Learning

2024 · arXiv (Cornell University)

Text-rich graphs, which exhibit rich textual information on nodes and edges, are prevalent across a wide range of real-world business applications. Large Language Models (LLMs) have demonstrated remarkable abilities in understanding text, which also introduced …

Efficient Ensembles Improve Training Data Attribution

2024 · arXiv (Cornell University)

Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such as mislabel detection, data selection, and copyright compensation. However, …