← Search

Yanhong Wu

2 accepted papers

2026

Negative Sampling From the Ground Up: A Redesign for Graph-based Recommendations

ICML 2026poster

Negative sampling is an important yet challenging component in self-supervised graph representation learning, particularly for recommendation systems where user-item interactions are modeled as bipartite graphs. Existing methods often rely on heuristics or human-specified principles to design negati…

Cited by 0SourceScholar
2021

Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions

AAAI 2021technical

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the magnitude of feature variations under multiple perturbations or…

Cited by 16SourcePDFScholar